update VERSION for v1.2.2

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

.exrc

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

.gitignore

@@ -1,19 +1,19 @@
 config-devices.*
 config-all-devices.*
-config-all-disas.*
 config-host.*
 config-target.*
-trace/generated-tracers.h
-trace/generated-tracers.c
-trace/generated-tracers-dtrace.h
-trace/generated-tracers-dtrace.dtrace
-libcacard/trace/generated-tracers.c
+trace.h
+trace.c
+trace-dtrace.h
+trace-dtrace.dtrace
 *-timestamp
 *-softmmu
 *-darwin-user
 *-linux-user
 *-bsd-user
 libdis*
+libhw32
+libhw64
 libuser
 linux-headers/asm
 qapi-generated
@@ -49,7 +49,6 @@ test-qmp-output-visitor
 test-string-input-visitor
 test-string-output-visitor
 test-visitor-serialization
-fsdev/virtfs-proxy-helper
 fsdev/virtfs-proxy-helper.1
 fsdev/virtfs-proxy-helper.pod
 .gdbinit
@@ -71,7 +70,6 @@ fsdev/virtfs-proxy-helper.pod
 *.tp
 *.vr
 *.d
-!scripts/qemu-guest-agent/fsfreeze-hook.d
 *.o
 *.lo
 *.la

.gitmodules

@@ -19,6 +19,3 @@
 [submodule "roms/sgabios"]
 	path = roms/sgabios
 	url = git://git.qemu.org/sgabios.git
-[submodule "pixman"]
-	path = pixman
-	url = git://anongit.freedesktop.org/pixman

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
@@ -91,11 +91,10 @@ emulators.
 
 4. String manipulation
 
-Do not use the strncpy function.  As mentioned in the man page, it does *not*
-guarantee a NULL-terminated buffer, which makes it extremely dangerous to use.
-It also zeros trailing destination bytes out to the specified length.  Instead,
-use this similar function when possible, but note its different signature:
-void pstrcpy(char *dest, int dest_buf_size, const char *src)
+Do not use the strncpy function.  According to the man page, it does
+*not* guarantee a NULL-terminated buffer, which makes it extremely dangerous
+to use.  Instead, use functionally equivalent function:
+void pstrcpy(char *buf, int buf_size, const char *str)
 
 Don't use strcat because it can't check for buffer overflows, but:
 char *pstrcat(char *buf, int buf_size, const char *s)
@@ -123,23 +122,3 @@ gcc's printf attribute directive in the prototype.
 This makes it so gcc's -Wformat and -Wformat-security options can do
 their jobs and cross-check format strings with the number and types
 of arguments.
-
-6. C standard, implementation defined and undefined behaviors
-
-C code in QEMU should be written to the C99 language specification. A copy
-of the final version of the C99 standard with corrigenda TC1, TC2, and TC3
-included, formatted as a draft, can be downloaded from:
- http://www.open-std.org/jtc1/sc22/WG14/www/docs/n1256.pdf
-
-The C language specification defines regions of undefined behavior and
-implementation defined behavior (to give compiler authors enough leeway to
-produce better code).  In general, code in QEMU should follow the language
-specification and avoid both undefined and implementation defined
-constructs. ("It works fine on the gcc I tested it with" is not a valid
-argument...) However there are a few areas where we allow ourselves to
-assume certain behaviors because in practice all the platforms we care about
-behave in the same way and writing strictly conformant code would be
-painful. These are:
- * you may assume that integers are 2s complement representation
- * you may assume that right shift of a signed integer duplicates
-   the sign bit (ie it is an arithmetic shift, not a logical shift)

MAINTAINERS

@@ -98,7 +98,6 @@ S: Maintained
 F: target-ppc/
 
 S390
-M: Richard Henderson <rth@twiddle.net>
 M: Alexander Graf <agraf@suse.de>
 S: Maintained
 F: target-s390x/
@@ -133,7 +132,7 @@ Guest CPU Cores (KVM):
 ----------------------
 
 Overall
-M: Gleb Natapov <gleb@redhat.com>
+M: Avi Kivity <avi@redhat.com>
 M: Marcelo Tosatti <mtosatti@redhat.com>
 L: kvm@vger.kernel.org
 S: Supported
@@ -151,7 +150,7 @@ S: Maintained
 F: target-s390x/kvm.c
 
 X86
-M: Gleb Natapov <gleb@redhat.com>
+M: Avi Kivity <avi@redhat.com>
 M: Marcelo Tosatti <mtosatti@redhat.com>
 L: kvm@vger.kernel.org
 S: Supported
@@ -269,7 +268,6 @@ S: Maintained
 F: hw/xilinx_zynq.c
 F: hw/zynq_slcr.c
 F: hw/cadence_*
-F: hw/xilinx_spips.c
 
 CRIS Machines
 -------------
@@ -351,36 +349,14 @@ PowerPC Machines
 405
 M: Alexander Graf <agraf@suse.de>
 L: qemu-ppc@nongnu.org
-S: Odd Fixes
+S: Maintained
 F: hw/ppc405_boards.c
 
-Bamboo
-M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/ppc440_bamboo.c
-
-e500
-M: Alexander Graf <agraf@suse.de>
-M: Scott Wood <scottwood@freescale.com>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/ppc/e500.[hc]
-F: hw/ppc/e500plat.c
-
-mpc8544ds
-M: Alexander Graf <agraf@suse.de>
-M: Scott Wood <scottwood@freescale.com>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/ppc/mpc8544ds.c
-F: hw/mpc8544_guts.c
-
 New World
 M: Alexander Graf <agraf@suse.de>
 L: qemu-ppc@nongnu.org
 S: Maintained
-F: hw/ppc/mac_newworld.c
+F: hw/ppc_newworld.c
 F: hw/unin_pci.c
 F: hw/dec_pci.[hc]
 
@@ -388,29 +364,15 @@ Old World
 M: Alexander Graf <agraf@suse.de>
 L: qemu-ppc@nongnu.org
 S: Maintained
-F: hw/ppc/mac_oldworld.c
+F: hw/ppc_oldworld.c
 F: hw/grackle_pci.c
 
 PReP
 M: Andreas Färber <andreas.faerber@web.de>
 L: qemu-ppc@nongnu.org
 S: Odd Fixes
-F: hw/ppc/prep.c
+F: hw/ppc_prep.c
 F: hw/prep_pci.[hc]
-F: hw/pc87312.[hc]
-
-sPAPR
-M: David Gibson <david@gibson.dropbear.id.au>
-M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/spapr*
-
-virtex_ml507
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/virtex_ml507.c
 
 SH4 Machines
 ------------
@@ -492,23 +454,9 @@ F: hw/omap*
 PCI
 M: Michael S. Tsirkin <mst@redhat.com>
 S: Supported
-F: hw/pci/*
 F: hw/pci*
 F: hw/piix*
 
-ppc4xx
-M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/ppc4xx*.[hc]
-
-ppce500
-M: Alexander Graf <agraf@suse.de>
-M: Scott Wood <scottwood@freescale.com>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/ppce500_*
-
 SCSI
 M: Paolo Bonzini <pbonzini@redhat.com>
 S: Supported
@@ -521,22 +469,11 @@ M: Paul Brook <paul@codesourcery.com>
 S: Odd Fixes
 F: hw/lsi53c895a.c
 
-SSI
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-S: Maintained
-F: hw/ssi.*
-F: hw/m25p80.c
-
 USB
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Maintained
 F: hw/usb*
 
-VFIO
-M: Alex Williamson <alex.williamson@redhat.com>
-S: Supported
-F: hw/vfio*
-
 vhost
 M: Michael S. Tsirkin <mst@redhat.com>
 S: Supported
@@ -556,7 +493,6 @@ T: git git://github.com/kvaneesh/QEMU.git
 
 virtio-blk
 M: Kevin Wolf <kwolf@redhat.com>
-M: Stefan Hajnoczi <stefanha@redhat.com>
 S: Supported
 F: hw/virtio-blk*
 
@@ -576,7 +512,6 @@ F: hw/xilinx_intc.c
 F: hw/xilinx_ethlite.c
 F: hw/xilinx_timer.c
 F: hw/xilinx.h
-F: hw/xilinx_spi.c
 
 Subsystems
 ----------
@@ -587,7 +522,6 @@ F: audio/
 
 Block
 M: Kevin Wolf <kwolf@redhat.com>
-M: Stefan Hajnoczi <stefanha@redhat.com>
 S: Supported
 F: block*
 F: block/
@@ -602,7 +536,6 @@ M: Andreas Färber <afaerber@suse.de>
 S: Supported
 F: qom/cpu.c
 F: include/qemu/cpu.h
-F: target-i386/cpu.c
 
 Device Tree
 M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
@@ -647,7 +580,7 @@ F: monitor.c
 
 Network device layer
 M: Anthony Liguori <aliguori@us.ibm.com>
-M: Stefan Hajnoczi <stefanha@redhat.com>
+M: Stefan Hajnoczi <stefanha@gmail.com>
 S: Maintained
 F: net/
 T: git git://github.com/stefanha/qemu.git net
@@ -667,7 +600,7 @@ F: slirp/
 T: git git://git.kiszka.org/qemu.git queues/slirp
 
 Tracing
-M: Stefan Hajnoczi <stefanha@redhat.com>
+M: Stefan Hajnoczi <stefanha@gmail.com>
 S: Maintained
 F: trace/
 F: scripts/tracetool.py

Makefile

@@ -8,38 +8,22 @@ ifneq ($(wildcard config-host.mak),)
 # Put the all: rule here so that config-host.mak can contain dependencies.
 all:
 include config-host.mak
-
-# Check that we're not trying to do an out-of-tree build from
-# a tree that's been used for an in-tree build.
-ifneq ($(realpath $(SRC_PATH)),$(realpath .))
-ifneq ($(wildcard $(SRC_PATH)/config-host.mak),)
-$(error This is an out of tree build but your source tree ($(SRC_PATH)) \
-seems to have been used for an in-tree build. You can fix this by running \
-"make distclean && rm -rf *-linux-user *-softmmu" in your source tree)
-endif
-endif
-
 include $(SRC_PATH)/rules.mak
 config-host.mak: $(SRC_PATH)/configure
 	@echo $@ is out-of-date, running configure
 	@sed -n "/.*Configured with/s/[^:]*: //p" $@ | sh
 else
 config-host.mak:
-ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
 	@echo "Please call configure before running make!"
 	@exit 1
 endif
-endif
 
-GENERATED_HEADERS = config-host.h qemu-options.def
-GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h
-GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c
-
-GENERATED_HEADERS += trace/generated-tracers.h
+GENERATED_HEADERS = config-host.h trace.h qemu-options.def
 ifeq ($(TRACE_BACKEND),dtrace)
-GENERATED_HEADERS += trace/generated-tracers-dtrace.h
+GENERATED_HEADERS += trace-dtrace.h
 endif
-GENERATED_SOURCES += trace/generated-tracers.c
+GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h
+GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c trace.c
 
 # Don't try to regenerate Makefile or configure
 # We don't generate any of them
@@ -102,18 +86,6 @@ defconfig:
 	rm -f config-all-devices.mak $(SUBDIR_DEVICES_MAK)
 
 -include config-all-devices.mak
--include config-all-disas.mak
-CONFIG_SOFTMMU := $(if $(filter %-softmmu,$(TARGET_DIRS)),y)
-CONFIG_USER_ONLY := $(if $(filter %-user,$(TARGET_DIRS)),y)
-CONFIG_ALL=y
-
-ifneq ($(wildcard config-host.mak),)
-include $(SRC_PATH)/Makefile.objs
-include $(SRC_PATH)/tests/Makefile
-endif
-ifeq ($(CONFIG_SMARTCARD_NSS),y)
-include $(SRC_PATH)/libcacard/Makefile
-endif
 
 all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all
 
@@ -127,16 +99,15 @@ SUBDIR_RULES=$(patsubst %,subdir-%, $(TARGET_DIRS))
 subdir-%:
 	$(call quiet-command,$(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)
+subdir-libcacard: $(oslib-obj-y) $(trace-obj-y) qemu-timer-common.o
 
-$(SRC_PATH)/pixman/configure:
-	(cd $(SRC_PATH)/pixman; autoreconf -v --install)
+$(filter %-softmmu,$(SUBDIR_RULES)): $(universal-obj-y) $(trace-obj-y) $(common-obj-y) $(extra-obj-y) subdir-libdis
 
-$(SUBDIR_RULES): libqemuutil.a libqemustub.a $(common-obj-y)
+$(filter %-user,$(SUBDIR_RULES)): $(universal-obj-y) $(trace-obj-y) subdir-libdis-user subdir-libuser
 
 ROMSUBDIR_RULES=$(patsubst %,romsubdir-%, $(ROMS))
 romsubdir-%:
@@ -146,31 +117,61 @@ ALL_SUBDIRS=$(TARGET_DIRS) $(patsubst %,pc-bios/%, $(ROMS))
 
 recurse-all: $(SUBDIR_RULES) $(ROMSUBDIR_RULES)
 
+audio/audio.o audio/fmodaudio.o: QEMU_CFLAGS += $(FMOD_CFLAGS)
+
+QEMU_CFLAGS+=$(CURL_CFLAGS)
+
+QEMU_CFLAGS += -I$(SRC_PATH)/include
+
+ui/cocoa.o: ui/cocoa.m
+
+ui/sdl.o audio/sdlaudio.o ui/sdl_zoom.o hw/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
-Makefile: $(version-obj-y)
-
 ######################################################################
-# Build libraries
+# Support building shared library libcacard
 
-libqemustub.a: $(stub-obj-y)
-libqemuutil.a: $(util-obj-y)
+.PHONY: libcacard.la install-libcacard
+ifeq ($(LIBTOOL),)
+libcacard.la:
+	@echo "libtool is missing, please install and rerun configure"; exit 1
+
+install-libcacard:
+	@echo "libtool is missing, please install and rerun configure"; exit 1
+else
+libcacard.la: $(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$(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 cmd.o $(block-obj-y) libqemuutil.a libqemustub.a
+tools-obj-y = $(oslib-obj-y) $(trace-obj-y) qemu-tool.o qemu-timer.o \
+	qemu-timer-common.o main-loop.o notify.o \
+	iohandler.o cutils.o iov.o async.o
+tools-obj-$(CONFIG_POSIX) += compatfd.o
+
+qemu-img$(EXESUF): qemu-img.o $(tools-obj-y) $(block-obj-y)
+qemu-nbd$(EXESUF): qemu-nbd.o $(tools-obj-y) $(block-obj-y)
+qemu-io$(EXESUF): qemu-io.o cmd.o $(tools-obj-y) $(block-obj-y)
 
 qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o
 
-fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/virtio-9p-marshal.o libqemuutil.a libqemustub.a
+vscclient$(EXESUF): $(libcacard-y) $(oslib-obj-y) $(trace-obj-y) $(tools-obj-y) qemu-timer-common.o libcacard/vscclient.o
+	$(call quiet-command,$(CC) $(LDFLAGS) -o $@ $^ $(libcacard_libs) $(LIBS),"  LINK  $@")
+
+fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/virtio-9p-marshal.o oslib-posix.o $(trace-obj-y)
 fsdev/virtfs-proxy-helper$(EXESUF): LIBS += -lcap
 
 qemu-img-cmds.h: $(SRC_PATH)/qemu-img-cmds.hx
@@ -181,16 +182,20 @@ qemu-ga$(EXESUF): QEMU_CFLAGS += -I qga/qapi-generated
 
 gen-out-type = $(subst .,-,$(suffix $@))
 
+ifneq ($(wildcard config-host.mak),)
+include $(SRC_PATH)/tests/Makefile
+endif
+
 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 $(qapi-py)
+$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, "  GEN   $@")
 qga/qapi-generated/qga-qapi-visit.c qga/qapi-generated/qga-qapi-visit.h :\
-$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
+$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, "  GEN   $@")
 qga/qapi-generated/qga-qmp-commands.h qga/qapi-generated/qga-qmp-marshal.c :\
-$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
+$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, "  GEN   $@")
 
 qapi-types.c qapi-types.h :\
@@ -206,27 +211,27 @@ $(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
 QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
 $(qga-obj-y) qemu-ga.o: $(QGALIB_GEN)
 
-qemu-ga$(EXESUF): $(qga-obj-y) libqemuutil.a libqemustub.a
-	$(call LINK, $^)
+qemu-ga$(EXESUF): qemu-ga.o $(qga-obj-y) $(tools-obj-y) $(qapi-obj-y) $(qobject-obj-y) $(version-obj-y)
+
+QEMULIBS=libhw32 libhw64 libuser libdis libdis-user
 
 clean:
 # avoid old build problems by removing potentially incorrect old files
 	rm -f config.mak op-i386.h opc-i386.h gen-op-i386.h op-arm.h opc-arm.h gen-op-arm.h
 	rm -f qemu-options.def
-	find . -name '*.[oda]' -type f -exec rm -f {} +
-	find . -name '*.l[oa]' -type f -exec rm -f {} +
-	rm -f $(TOOLS) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
+	find . -name '*.[od]' -exec rm -f {} +
+	rm -f *.a *.lo $(TOOLS) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
 	rm -Rf .libs
 	rm -f qemu-img-cmds.h
+	rm -f trace-dtrace.dtrace trace-dtrace.dtrace-timestamp
 	@# May not be present in GENERATED_HEADERS
-	rm -f trace/generated-tracers-dtrace.dtrace*
-	rm -f trace/generated-tracers-dtrace.h*
+	rm -f trace-dtrace.h trace-dtrace.h-timestamp
 	rm -f $(foreach f,$(GENERATED_HEADERS),$(f) $(f)-timestamp)
 	rm -f $(foreach f,$(GENERATED_SOURCES),$(f) $(f)-timestamp)
 	rm -rf qapi-generated
 	rm -rf qga/qapi-generated
 	$(MAKE) -C tests/tcg clean
-	for d in $(ALL_SUBDIRS); do \
+	for d in $(ALL_SUBDIRS) $(QEMULIBS) libcacard; do \
 	if test -d $$d; then $(MAKE) -C $$d $@ || exit 1; fi; \
 	rm -f $$d/qemu-options.def; \
         done
@@ -240,7 +245,7 @@ qemu-%.tar.bz2:
 
 distclean: clean
 	rm -f config-host.mak config-host.h* config-host.ld $(DOCS) qemu-options.texi qemu-img-cmds.texi qemu-monitor.texi
-	rm -f config-all-devices.mak config-all-disas.mak
+	rm -f config-all-devices.mak
 	rm -f roms/seabios/config.mak roms/vgabios/config.mak
 	rm -f qemu-doc.info qemu-doc.aux qemu-doc.cp qemu-doc.cps qemu-doc.dvi
 	rm -f qemu-doc.fn qemu-doc.fns qemu-doc.info qemu-doc.ky qemu-doc.kys
@@ -249,10 +254,9 @@ distclean: clean
 	rm -f config.log
 	rm -f linux-headers/asm
 	rm -f qemu-tech.info qemu-tech.aux qemu-tech.cp qemu-tech.dvi qemu-tech.fn qemu-tech.info qemu-tech.ky qemu-tech.log qemu-tech.pdf qemu-tech.pg qemu-tech.toc qemu-tech.tp qemu-tech.vr
-	for d in $(TARGET_DIRS); do \
+	for d in $(TARGET_DIRS) $(QEMULIBS); do \
 	rm -rf $$d || exit 1 ; \
         done
-	if test -f pixman/config.log; then make -C pixman distclean; fi
 
 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 \
@@ -262,7 +266,6 @@ bepo
 ifdef INSTALL_BLOBS
 BLOBS=bios.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
 vgabios-stdvga.bin vgabios-vmware.bin vgabios-qxl.bin \
-acpi-dsdt.aml q35-acpi-dsdt.aml \
 ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc \
 pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
 pxe-pcnet.rom pxe-rtl8139.rom pxe-virtio.rom \
@@ -299,6 +302,7 @@ install-confdir:
 
 install-sysconfig: install-datadir install-confdir
 	$(INSTALL_DATA) $(SRC_PATH)/sysconfigs/target/target-x86_64.conf "$(DESTDIR)$(qemu_confdir)"
+	$(INSTALL_DATA) $(SRC_PATH)/sysconfigs/target/cpus-x86_64.conf "$(DESTDIR)$(qemu_datadir)"
 
 install: all $(if $(BUILD_DOCS),install-doc) install-sysconfig install-datadir
 	$(INSTALL_DIR) "$(DESTDIR)$(bindir)"
@@ -399,9 +403,7 @@ qemu-doc.dvi qemu-doc.html qemu-doc.info qemu-doc.pdf: \
 
 # 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
 
 # Include automatically generated dependency files
 # Dependencies in Makefile.objs files come from our recursive subdir rules

Makefile.dis

@@ -0,0 +1,20 @@
+# 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 *~

Makefile.hw

@@ -0,0 +1,23 @@
+# 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, $(SRC_PATH))
+
+QEMU_CFLAGS+=-I..
+QEMU_CFLAGS += -I$(SRC_PATH)/include
+
+include $(SRC_PATH)/Makefile.objs
+
+all: $(hw-obj-y)
+# Dummy command so that make thinks it has done something
+	@true
+
+clean:
+	rm -f $(addsuffix *.o, $(sort $(dir $(hw-obj-y))))
+	rm -f $(addsuffix *.d, $(sort $(dir $(hw-obj-y))))

Makefile.objs

@@ -1,31 +1,52 @@
 #######################################################################
-# Common libraries for tools and emulators
-stub-obj-y = stubs/
-util-obj-y = util/ qobject/ qapi/ trace/
+# Target-independent parts used in system and user emulation
+universal-obj-y =
+universal-obj-y += qemu-log.o
+
+#######################################################################
+# QObject
+qobject-obj-y = qint.o qstring.o qdict.o qlist.o qfloat.o qbool.o
+qobject-obj-y += qjson.o json-lexer.o json-streamer.o json-parser.o
+qobject-obj-y += qerror.o error.o qemu-error.o
+
+universal-obj-y += $(qobject-obj-y)
+
+#######################################################################
+# QOM
+qom-obj-y = qom/
+
+universal-obj-y += $(qom-obj-y)
+
+#######################################################################
+# oslib-obj-y is code depending on the OS (win32 vs posix)
+oslib-obj-y = osdep.o
+oslib-obj-$(CONFIG_WIN32) += oslib-win32.o qemu-thread-win32.o
+oslib-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-thread-posix.o
+
+#######################################################################
+# coroutines
+coroutine-obj-y = qemu-coroutine.o qemu-coroutine-lock.o qemu-coroutine-io.o
+coroutine-obj-y += qemu-coroutine-sleep.o
+ifeq ($(CONFIG_UCONTEXT_COROUTINE),y)
+coroutine-obj-$(CONFIG_POSIX) += coroutine-ucontext.o
+else
+ifeq ($(CONFIG_SIGALTSTACK_COROUTINE),y)
+coroutine-obj-$(CONFIG_POSIX) += coroutine-sigaltstack.o
+else
+coroutine-obj-$(CONFIG_POSIX) += coroutine-gthread.o
+endif
+endif
+coroutine-obj-$(CONFIG_WIN32) += coroutine-win32.o
 
 #######################################################################
 # block-obj-y is code used by both qemu system emulation and qemu-img
 
-block-obj-y = async.o thread-pool.o
-block-obj-y += nbd.o block.o blockjob.o
-block-obj-y += main-loop.o iohandler.o qemu-timer.o
-block-obj-$(CONFIG_POSIX) += aio-posix.o
-block-obj-$(CONFIG_WIN32) += aio-win32.o
+block-obj-y = cutils.o iov.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-$(CONFIG_LINUX_AIO) += linux-aio.o
 block-obj-y += block/
-block-obj-y += qapi-types.o qapi-visit.o
-
-block-obj-y += qemu-coroutine.o qemu-coroutine-lock.o qemu-coroutine-io.o
-block-obj-y += qemu-coroutine-sleep.o
-ifeq ($(CONFIG_UCONTEXT_COROUTINE),y)
-block-obj-$(CONFIG_POSIX) += coroutine-ucontext.o
-else
-ifeq ($(CONFIG_SIGALTSTACK_COROUTINE),y)
-block-obj-$(CONFIG_POSIX) += coroutine-sigaltstack.o
-else
-block-obj-$(CONFIG_POSIX) += coroutine-gthread.o
-endif
-endif
-block-obj-$(CONFIG_WIN32) += coroutine-win32.o
 
 ifeq ($(CONFIG_VIRTIO)$(CONFIG_VIRTFS)$(CONFIG_PCI),yyy)
 # Lots of the fsdev/9pcode is pulled in by vl.c via qemu_fsdev_add.
@@ -33,6 +54,155 @@ ifeq ($(CONFIG_VIRTIO)$(CONFIG_VIRTFS)$(CONFIG_PCI),yyy)
 CONFIG_REALLY_VIRTFS=y
 endif
 
+######################################################################
+# 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.o net/
+common-obj-y += qom/
+common-obj-y += readline.o console.o cursor.o
+common-obj-y += $(oslib-obj-y)
+common-obj-$(CONFIG_WIN32) += os-win32.o
+common-obj-$(CONFIG_POSIX) += os-posix.o
+
+common-obj-$(CONFIG_LINUX) += fsdev/
+extra-obj-$(CONFIG_LINUX) += fsdev/
+
+common-obj-y += tcg-runtime.o host-utils.o main-loop.o
+common-obj-y += input.o
+common-obj-y += buffered_file.o migration.o migration-tcp.o
+common-obj-y += qemu-char.o #aio.o
+common-obj-y += block-migration.o iohandler.o
+common-obj-y += pflib.o
+common-obj-y += bitmap.o bitops.o
+common-obj-y += page_cache.o
+
+common-obj-$(CONFIG_POSIX) += migration-exec.o migration-unix.o migration-fd.o
+common-obj-$(CONFIG_WIN32) += version.o
+
+common-obj-$(CONFIG_SPICE) += spice-qemu-char.o
+
+common-obj-y += audio/
+common-obj-y += hw/
+common-obj-y += ui/
+common-obj-y += bt-host.o bt-vhci.o
+
+common-obj-y += iov.o acl.o
+common-obj-$(CONFIG_POSIX) += compatfd.o
+common-obj-y += notify.o event_notifier.o
+common-obj-y += qemu-timer.o qemu-timer-common.o
+
+common-obj-$(CONFIG_SLIRP) += slirp/
+
+######################################################################
+# libseccomp
+ifeq ($(CONFIG_SECCOMP),y)
+common-obj-y += qemu-seccomp.o
+endif
+
+######################################################################
+# 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 iov.o cache-utils.o
+user-obj-y += module.o
+user-obj-y += qemu-user.o
+user-obj-y += $(trace-obj-y)
+user-obj-y += qom/
+
+######################################################################
+# libhw
+
+hw-obj-y = vl.o dma-helpers.o qtest.o hw/
+
+######################################################################
+# libdis
+# NOTE: the disassembler code is only needed for debugging
+
+libdis-y =
+libdis-$(CONFIG_ALPHA_DIS) += alpha-dis.o
+libdis-$(CONFIG_ARM_DIS) += arm-dis.o
+libdis-$(CONFIG_CRIS_DIS) += cris-dis.o
+libdis-$(CONFIG_HPPA_DIS) += hppa-dis.o
+libdis-$(CONFIG_I386_DIS) += i386-dis.o
+libdis-$(CONFIG_IA64_DIS) += ia64-dis.o
+libdis-$(CONFIG_M68K_DIS) += m68k-dis.o
+libdis-$(CONFIG_MICROBLAZE_DIS) += microblaze-dis.o
+libdis-$(CONFIG_MIPS_DIS) += mips-dis.o
+libdis-$(CONFIG_PPC_DIS) += ppc-dis.o
+libdis-$(CONFIG_S390_DIS) += s390-dis.o
+libdis-$(CONFIG_SH4_DIS) += sh4-dis.o
+libdis-$(CONFIG_SPARC_DIS) += sparc-dis.o
+libdis-$(CONFIG_LM32_DIS) += lm32-dis.o
+
+######################################################################
+# trace
+
+ifeq ($(TRACE_BACKEND),dtrace)
+TRACE_H_EXTRA_DEPS=trace-dtrace.h
+endif
+trace.h: trace.h-timestamp $(TRACE_H_EXTRA_DEPS)
+trace.h-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak
+	$(call quiet-command,$(TRACETOOL) \
+		--format=h \
+		--backend=$(TRACE_BACKEND) \
+		< $< > $@,"  GEN   trace.h")
+	@cmp -s $@ trace.h || cp $@ trace.h
+
+trace.c: trace.c-timestamp
+trace.c-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak
+	$(call quiet-command,$(TRACETOOL) \
+		--format=c \
+		--backend=$(TRACE_BACKEND) \
+		< $< > $@,"  GEN   trace.c")
+	@cmp -s $@ trace.c || cp $@ trace.c
+
+trace.o: trace.c $(GENERATED_HEADERS)
+
+trace-dtrace.h: trace-dtrace.dtrace
+	$(call quiet-command,dtrace -o $@ -h -s $<, "  GEN   trace-dtrace.h")
+
+# Normal practice is to name DTrace probe file with a '.d' extension
+# but that gets picked up by QEMU's Makefile as an external dependency
+# rule file. So we use '.dtrace' instead
+trace-dtrace.dtrace: trace-dtrace.dtrace-timestamp
+trace-dtrace.dtrace-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak
+	$(call quiet-command,$(TRACETOOL) \
+		--format=d \
+		--backend=$(TRACE_BACKEND) \
+		< $< > $@,"  GEN   trace-dtrace.dtrace")
+	@cmp -s $@ trace-dtrace.dtrace || cp $@ trace-dtrace.dtrace
+
+trace-dtrace.o: trace-dtrace.dtrace $(GENERATED_HEADERS)
+	$(call quiet-command,dtrace -o $@ -G -s $<, "  GEN   trace-dtrace.o")
+
+ifeq ($(LIBTOOL),)
+trace-dtrace.lo: trace-dtrace.dtrace
+	@echo "missing libtool. please install and rerun configure."; exit 1
+else
+trace-dtrace.lo: trace-dtrace.dtrace
+	$(call quiet-command,$(LIBTOOL) --mode=compile --tag=CC dtrace -o $@ -G -s $<, "  lt GEN trace-dtrace.o")
+endif
+
+trace/simple.o: trace/simple.c $(GENERATED_HEADERS)
+
+trace-obj-$(CONFIG_TRACE_DTRACE) += trace-dtrace.o
+ifneq ($(TRACE_BACKEND),dtrace)
+trace-obj-y = trace.o
+endif
+
+trace-obj-$(CONFIG_TRACE_DEFAULT) += trace/default.o
+trace-obj-$(CONFIG_TRACE_SIMPLE) += trace/simple.o
+trace-obj-$(CONFIG_TRACE_SIMPLE) += qemu-timer-common.o
+trace-obj-$(CONFIG_TRACE_STDERR) += trace/stderr.o
+trace-obj-y += trace/control.o
+
+$(trace-obj-y): $(GENERATED_HEADERS)
+
 ######################################################################
 # smartcard
 
@@ -42,68 +212,25 @@ libcacard-y += libcacard/vcard_emul_nss.o
 libcacard-y += libcacard/vcard_emul_type.o
 libcacard-y += libcacard/card_7816.o
 
-######################################################################
-# Target independent part of system emulation. The long term path is to
-# suppress *all* target specific code in case of system emulation, i.e. a
-# single QEMU executable should support all CPUs and machines.
-
-ifeq ($(CONFIG_SOFTMMU),y)
-common-obj-y = $(block-obj-y) blockdev.o blockdev-nbd.o block/
-common-obj-y += net/
-common-obj-y += readline.o
-common-obj-$(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 += 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
-
-common-obj-y += dma-helpers.o
-common-obj-y += qtest.o
-common-obj-y += vl.o
-
-common-obj-$(CONFIG_SLIRP) += slirp/
-
-common-obj-y += backends/
-
-common-obj-$(CONFIG_SECCOMP) += qemu-seccomp.o
-
 common-obj-$(CONFIG_SMARTCARD_NSS) += $(libcacard-y)
 
 ######################################################################
 # qapi
 
+qapi-obj-y = qapi/
+qapi-obj-y += qapi-types.o qapi-visit.o
+
 common-obj-y += qmp-marshal.o qapi-visit.o qapi-types.o
 common-obj-y += qmp.o hmp.o
-endif
 
-#######################################################################
-# Target-independent parts used in system and user emulation
-common-obj-y += qemu-log.o
-common-obj-y += tcg-runtime.o
-common-obj-y += hw/
-common-obj-y += qom/
-common-obj-y += disas/
+universal-obj-y += $(qapi-obj-y)
 
 ######################################################################
 # guest agent
 
-# FIXME: a few definitions from qapi-types.o/qapi-visit.o are needed
-# by libqemuutil.a.  These should be moved to a separate .json schema.
-qga-obj-y = qga/ qapi-types.o qapi-visit.o
+qga-obj-y = qga/ qemu-ga.o module.o
+qga-obj-$(CONFIG_WIN32) += oslib-win32.o
+qga-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-sockets.o qemu-option.o
 
 vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
 
@@ -112,9 +239,12 @@ vl.o: QEMU_CFLAGS+=$(SDL_CFLAGS)
 QEMU_CFLAGS+=$(GLIB_CFLAGS)
 
 nested-vars += \
-	stub-obj-y \
-	util-obj-y \
+	hw-obj-y \
 	qga-obj-y \
 	block-obj-y \
-	common-obj-y
+	qom-obj-y \
+	qapi-obj-y \
+	user-obj-y \
+	common-obj-y \
+	extra-obj-y
 dummy := $(call unnest-vars)

Makefile.target

@@ -4,6 +4,9 @@ include ../config-host.mak
 include config-devices.mak
 include config-target.mak
 include $(SRC_PATH)/rules.mak
+ifneq ($(HWDIR),)
+include $(HWDIR)/config.mak
+endif
 
 $(call set-vpath, $(SRC_PATH))
 ifdef CONFIG_LINUX
@@ -54,7 +57,7 @@ $(QEMU_PROG).stp: $(SRC_PATH)/trace-events
 		--binary=$(bindir)/$(QEMU_PROG) \
 		--target-arch=$(TARGET_ARCH) \
 		--target-type=$(TARGET_TYPE) \
-		< $< > $@,"  GEN   $(TARGET_DIR)$(QEMU_PROG).stp")
+		< $< > $@,"  GEN   $(QEMU_PROG).stp")
 else
 stap:
 endif
@@ -69,12 +72,14 @@ all: $(PROGS) stap
 obj-y = exec.o translate-all.o cpu-exec.o
 obj-y += tcg/tcg.o tcg/optimize.o
 obj-$(CONFIG_TCG_INTERPRETER) += tci.o
-obj-$(CONFIG_TCG_INTERPRETER) += disas/tci.o
 obj-y += fpu/softfloat.o
-obj-y += target-$(TARGET_BASE_ARCH)/
 obj-y += disas.o
+obj-$(CONFIG_TCI_DIS) += tci-dis.o
+obj-y += target-$(TARGET_BASE_ARCH)/
 obj-$(CONFIG_GDBSTUB_XML) += gdbstub-xml.o
 
+tci-dis.o: QEMU_CFLAGS += -I$(SRC_PATH)/tcg -I$(SRC_PATH)/tcg/tci
+
 #########################################################
 # Linux user emulator target
 
@@ -83,7 +88,7 @@ ifdef CONFIG_LINUX_USER
 QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) -I$(SRC_PATH)/linux-user
 
 obj-y += linux-user/
-obj-y += gdbstub.o thunk.o user-exec.o
+obj-y += gdbstub.o thunk.o user-exec.o $(oslib-obj-y)
 
 endif #CONFIG_LINUX_USER
 
@@ -95,7 +100,7 @@ ifdef CONFIG_BSD_USER
 QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ARCH)
 
 obj-y += bsd-user/
-obj-y += gdbstub.o user-exec.o
+obj-y += gdbstub.o user-exec.o $(oslib-obj-y)
 
 endif #CONFIG_BSD_USER
 
@@ -119,6 +124,11 @@ obj-$(CONFIG_NO_GET_MEMORY_MAPPING) += memory_mapping-stub.o
 obj-$(CONFIG_NO_CORE_DUMP) += dump-stub.o
 LIBS+=-lz
 
+QEMU_CFLAGS += $(VNC_TLS_CFLAGS)
+QEMU_CFLAGS += $(VNC_SASL_CFLAGS)
+QEMU_CFLAGS += $(VNC_JPEG_CFLAGS)
+QEMU_CFLAGS += $(VNC_PNG_CFLAGS)
+
 # xen support
 obj-$(CONFIG_XEN) += xen-all.o xen-mapcache.o
 obj-$(CONFIG_NO_XEN) += xen-stub.o
@@ -136,25 +146,32 @@ GENERATED_HEADERS += hmp-commands.h qmp-commands-old.h
 
 endif # CONFIG_SOFTMMU
 
-# Workaround for http://gcc.gnu.org/PR55489, see configure.
-%/translate.o: QEMU_CFLAGS += $(TRANSLATE_OPT_CFLAGS)
-
 nested-vars += obj-y
 
 # This resolves all nested paths, so it must come last
 include $(SRC_PATH)/Makefile.objs
 
 all-obj-y = $(obj-y)
+all-obj-y += $(addprefix ../, $(universal-obj-y))
+
+ifdef CONFIG_SOFTMMU
 all-obj-y += $(addprefix ../, $(common-obj-y))
+all-obj-y += $(addprefix ../libdis/, $(libdis-y))
+all-obj-y += $(addprefix $(HWDIR)/, $(hw-obj-y))
+all-obj-y += $(addprefix ../, $(trace-obj-y))
+else
+all-obj-y += $(addprefix ../libuser/, $(user-obj-y))
+all-obj-y += $(addprefix ../libdis-user/, $(libdis-y))
+endif #CONFIG_LINUX_USER
 
 ifdef QEMU_PROGW
 # The linker builds a windows executable. Make also a console executable.
-$(QEMU_PROGW): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
+$(QEMU_PROGW): $(all-obj-y)
 	$(call LINK,$^)
 $(QEMU_PROG): $(QEMU_PROGW)
 	$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG),"  GEN   $(TARGET_DIR)$(QEMU_PROG)")
 else
-$(QEMU_PROG): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
+$(QEMU_PROG): $(all-obj-y)
 	$(call LINK,$^)
 endif
 

Makefile.user

@@ -0,0 +1,24 @@
+# Makefile for qemu target independent user files.
+
+include ../config-host.mak
+include $(SRC_PATH)/rules.mak
+-include config.mak
+
+.PHONY: all
+
+$(call set-vpath, $(SRC_PATH))
+
+QEMU_CFLAGS+=-I..
+QEMU_CFLAGS += -I$(SRC_PATH)/include
+QEMU_CFLAGS += -DCONFIG_USER_ONLY
+
+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

QMP/qemu-ga-client

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

QMP/qmp-events.txt

@@ -50,8 +50,7 @@ Emitted when a block job has been cancelled.
 
 Data:
 
-- "type":     Job type (json-string; "stream" for image streaming
-                                     "commit" for block commit)
+- "type":     Job type ("stream" for image streaming, json-string)
 - "device":   Device name (json-string)
 - "len":      Maximum progress value (json-int)
 - "offset":   Current progress value (json-int)
@@ -74,8 +73,7 @@ Emitted when a block job has completed.
 
 Data:
 
-- "type":     Job type (json-string; "stream" for image streaming
-                                     "commit" for block commit)
+- "type":     Job type ("stream" for image streaming, json-string)
 - "device":   Device name (json-string)
 - "len":      Maximum progress value (json-int)
 - "offset":   Current progress value (json-int)
@@ -96,46 +94,6 @@ Example:
                "speed": 0 },
      "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }
 
-BLOCK_JOB_ERROR
----------------
-
-Emitted when a block job encounters an error.
-
-Data:
-
-- "device": device name (json-string)
-- "operation": I/O operation (json-string, "read" or "write")
-- "action": action that has been taken, it's one of the following (json-string):
-    "ignore": error has been ignored, the job may fail later
-    "report": error will be reported and the job canceled
-    "stop": error caused job to be paused
-
-Example:
-
-{ "event": "BLOCK_JOB_ERROR",
-    "data": { "device": "ide0-hd1",
-              "operation": "write",
-              "action": "stop" },
-    "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
-BLOCK_JOB_READY
----------------
-
-Emitted when a block job is ready to complete.
-
-Data:
-
-- "device": device name (json-string)
-
-Example:
-
-{ "event": "BLOCK_JOB_READY",
-    "data": { "device": "ide0-hd1" },
-    "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
-Note: The "ready to complete" status is always reset by a BLOCK_JOB_ERROR
-event.
-
 DEVICE_TRAY_MOVED
 -----------------
 

QMP/qmp-shell

@@ -33,7 +33,6 @@
 import qmp
 import readline
 import sys
-import pprint
 
 class QMPCompleter(list):
     def complete(self, text, state):
@@ -53,11 +52,10 @@ class QMPShellBadPort(QMPShellError):
 # TODO: QMPShell's interface is a bit ugly (eg. _fill_completion() and
 #       _execute_cmd()). Let's design a better one.
 class QMPShell(qmp.QEMUMonitorProtocol):
-    def __init__(self, address, pp=None):
+    def __init__(self, address):
         qmp.QEMUMonitorProtocol.__init__(self, self.__get_address(address))
         self._greeting = None
         self._completer = None
-        self._pp = pp
 
     def __get_address(self, arg):
         """
@@ -116,11 +114,7 @@ class QMPShell(qmp.QEMUMonitorProtocol):
         if resp is None:
             print 'Disconnected'
             return False
-
-        if self._pp is not None:
-            self._pp.pprint(resp)
-        else:
-            print resp
+        print resp
         return True
 
     def connect(self):
@@ -228,36 +222,22 @@ def die(msg):
 def fail_cmdline(option=None):
     if option:
         sys.stderr.write('ERROR: bad command-line option \'%s\'\n' % option)
-    sys.stderr.write('qemu-shell [ -p ] [ -H ] < UNIX socket path> | < TCP address:port >\n')
+    sys.stderr.write('qemu-shell [ -H ] < UNIX socket path> | < TCP address:port >\n')
     sys.exit(1)
 
 def main():
     addr = ''
-    qemu = None
-    hmp = False
-    pp = None
-
     try:
-        for arg in sys.argv[1:]:
-            if arg == "-H":
-                if qemu is not None:
-                    fail_cmdline(arg)
-                hmp = True
-            elif arg == "-p":
-                if pp is not None:
-                    fail_cmdline(arg)
-                pp = pprint.PrettyPrinter(indent=4)
-            else:
-                if qemu is not None:
-                    fail_cmdline(arg)
-                if hmp:
-                    qemu = HMPShell(arg)
-                else:
-                    qemu = QMPShell(arg, pp)
-                addr = arg
-
-        if qemu is None:
-            fail_cmdline()
+        if len(sys.argv) == 2:
+            qemu = QMPShell(sys.argv[1])
+            addr = sys.argv[1]
+        elif len(sys.argv) == 3:
+            if sys.argv[1] != '-H':
+                fail_cmdline(sys.argv[1])
+            qemu = HMPShell(sys.argv[2])
+            addr = sys.argv[2]
+        else:
+                fail_cmdline()
     except QMPShellBadPort:
         die('bad port number in command-line')
 

QMP/qmp.py

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

VERSION

@@ -1 +1 @@
-1.4.1
+1.2.2

a.out.h

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

acl.c

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

acl.h

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

aes.c

@@ -28,7 +28,7 @@
  * EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 #include "qemu-common.h"
-#include "block/aes.h"
+#include "aes.h"
 
 #ifndef NDEBUG
 #define NDEBUG

aio-posix.c

@@ -1,269 +0,0 @@
-/*
- * QEMU aio implementation
- *
- * Copyright IBM, Corp. 2008
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
- * Contributions after 2012-01-13 are licensed under the terms of the
- * GNU GPL, version 2 or (at your option) any later version.
- */
-
-#include "qemu-common.h"
-#include "block/block.h"
-#include "qemu/queue.h"
-#include "qemu/sockets.h"
-
-struct AioHandler
-{
-    GPollFD pfd;
-    IOHandler *io_read;
-    IOHandler *io_write;
-    AioFlushHandler *io_flush;
-    int deleted;
-    void *opaque;
-    QLIST_ENTRY(AioHandler) node;
-};
-
-static AioHandler *find_aio_handler(AioContext *ctx, int fd)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->pfd.fd == fd)
-            if (!node->deleted)
-                return node;
-    }
-
-    return NULL;
-}
-
-void aio_set_fd_handler(AioContext *ctx,
-                        int fd,
-                        IOHandler *io_read,
-                        IOHandler *io_write,
-                        AioFlushHandler *io_flush,
-                        void *opaque)
-{
-    AioHandler *node;
-
-    node = find_aio_handler(ctx, fd);
-
-    /* Are we deleting the fd handler? */
-    if (!io_read && !io_write) {
-        if (node) {
-            g_source_remove_poll(&ctx->source, &node->pfd);
-
-            /* If the lock is held, just mark the node as deleted */
-            if (ctx->walking_handlers) {
-                node->deleted = 1;
-                node->pfd.revents = 0;
-            } else {
-                /* Otherwise, delete it for real.  We can't just mark it as
-                 * deleted because deleted nodes are only cleaned up after
-                 * releasing the walking_handlers lock.
-                 */
-                QLIST_REMOVE(node, node);
-                g_free(node);
-            }
-        }
-    } else {
-        if (node == NULL) {
-            /* Alloc and insert if it's not already there */
-            node = g_malloc0(sizeof(AioHandler));
-            node->pfd.fd = fd;
-            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
-
-            g_source_add_poll(&ctx->source, &node->pfd);
-        }
-        /* Update handler with latest information */
-        node->io_read = io_read;
-        node->io_write = io_write;
-        node->io_flush = io_flush;
-        node->opaque = opaque;
-
-        node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP : 0);
-        node->pfd.events |= (io_write ? G_IO_OUT : 0);
-    }
-
-    aio_notify(ctx);
-}
-
-void aio_set_event_notifier(AioContext *ctx,
-                            EventNotifier *notifier,
-                            EventNotifierHandler *io_read,
-                            AioFlushEventNotifierHandler *io_flush)
-{
-    aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
-                       (IOHandler *)io_read, NULL,
-                       (AioFlushHandler *)io_flush, notifier);
-}
-
-bool aio_pending(AioContext *ctx)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        int revents;
-
-        /*
-         * FIXME: right now we cannot get G_IO_HUP and G_IO_ERR because
-         * main-loop.c is still select based (due to the slirp legacy).
-         * If main-loop.c ever switches to poll, G_IO_ERR should be
-         * tested too.  Dispatching G_IO_ERR to both handlers should be
-         * okay, since handlers need to be ready for spurious wakeups.
-         */
-        revents = node->pfd.revents & node->pfd.events;
-        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
-            return true;
-        }
-        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
-            return true;
-        }
-    }
-
-    return false;
-}
-
-bool aio_poll(AioContext *ctx, bool blocking)
-{
-    static struct timeval tv0;
-    AioHandler *node;
-    fd_set rdfds, wrfds;
-    int max_fd = -1;
-    int ret;
-    bool busy, progress;
-
-    progress = false;
-
-    /*
-     * If there are callbacks left that have been queued, we need to call then.
-     * Do not call select in this case, because it is possible that the caller
-     * does not need a complete flush (as is the case for qemu_aio_wait loops).
-     */
-    if (aio_bh_poll(ctx)) {
-        blocking = false;
-        progress = true;
-    }
-
-    /*
-     * Then dispatch any pending callbacks from the GSource.
-     *
-     * We have to walk very carefully in case qemu_aio_set_fd_handler is
-     * called while we're walking.
-     */
-    node = QLIST_FIRST(&ctx->aio_handlers);
-    while (node) {
-        AioHandler *tmp;
-        int revents;
-
-        ctx->walking_handlers++;
-
-        revents = node->pfd.revents & node->pfd.events;
-        node->pfd.revents = 0;
-
-        /* See comment in aio_pending.  */
-        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
-            node->io_read(node->opaque);
-            progress = true;
-        }
-        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
-            node->io_write(node->opaque);
-            progress = true;
-        }
-
-        tmp = node;
-        node = QLIST_NEXT(node, node);
-
-        ctx->walking_handlers--;
-
-        if (!ctx->walking_handlers && tmp->deleted) {
-            QLIST_REMOVE(tmp, node);
-            g_free(tmp);
-        }
-    }
-
-    if (progress && !blocking) {
-        return true;
-    }
-
-    ctx->walking_handlers++;
-
-    FD_ZERO(&rdfds);
-    FD_ZERO(&wrfds);
-
-    /* fill fd sets */
-    busy = false;
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        /* If there aren't pending AIO operations, don't invoke callbacks.
-         * Otherwise, if there are no AIO requests, qemu_aio_wait() would
-         * wait indefinitely.
-         */
-        if (!node->deleted && node->io_flush) {
-            if (node->io_flush(node->opaque) == 0) {
-                continue;
-            }
-            busy = true;
-        }
-        if (!node->deleted && node->io_read) {
-            FD_SET(node->pfd.fd, &rdfds);
-            max_fd = MAX(max_fd, node->pfd.fd + 1);
-        }
-        if (!node->deleted && node->io_write) {
-            FD_SET(node->pfd.fd, &wrfds);
-            max_fd = MAX(max_fd, node->pfd.fd + 1);
-        }
-    }
-
-    ctx->walking_handlers--;
-
-    /* No AIO operations?  Get us out of here */
-    if (!busy) {
-        return progress;
-    }
-
-    /* wait until next event */
-    ret = select(max_fd, &rdfds, &wrfds, NULL, blocking ? NULL : &tv0);
-
-    /* if we have any readable fds, dispatch event */
-    if (ret > 0) {
-        /* we have to walk very carefully in case
-         * qemu_aio_set_fd_handler is called while we're walking */
-        node = QLIST_FIRST(&ctx->aio_handlers);
-        while (node) {
-            AioHandler *tmp;
-
-            ctx->walking_handlers++;
-
-            if (!node->deleted &&
-                FD_ISSET(node->pfd.fd, &rdfds) &&
-                node->io_read) {
-                node->io_read(node->opaque);
-                progress = true;
-            }
-            if (!node->deleted &&
-                FD_ISSET(node->pfd.fd, &wrfds) &&
-                node->io_write) {
-                node->io_write(node->opaque);
-                progress = true;
-            }
-
-            tmp = node;
-            node = QLIST_NEXT(node, node);
-
-            ctx->walking_handlers--;
-
-            if (!ctx->walking_handlers && tmp->deleted) {
-                QLIST_REMOVE(tmp, node);
-                g_free(tmp);
-            }
-        }
-    }
-
-    assert(progress || busy);
-    return true;
-}

aio-win32.c

@@ -1,219 +0,0 @@
-/*
- * QEMU aio implementation
- *
- * Copyright IBM Corp., 2008
- * Copyright Red Hat Inc., 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *  Paolo Bonzini     <pbonzini@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
- * Contributions after 2012-01-13 are licensed under the terms of the
- * GNU GPL, version 2 or (at your option) any later version.
- */
-
-#include "qemu-common.h"
-#include "block/block.h"
-#include "qemu/queue.h"
-#include "qemu/sockets.h"
-
-struct AioHandler {
-    EventNotifier *e;
-    EventNotifierHandler *io_notify;
-    AioFlushEventNotifierHandler *io_flush;
-    GPollFD pfd;
-    int deleted;
-    QLIST_ENTRY(AioHandler) node;
-};
-
-void aio_set_event_notifier(AioContext *ctx,
-                            EventNotifier *e,
-                            EventNotifierHandler *io_notify,
-                            AioFlushEventNotifierHandler *io_flush)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->e == e && !node->deleted) {
-            break;
-        }
-    }
-
-    /* Are we deleting the fd handler? */
-    if (!io_notify) {
-        if (node) {
-            g_source_remove_poll(&ctx->source, &node->pfd);
-
-            /* If the lock is held, just mark the node as deleted */
-            if (ctx->walking_handlers) {
-                node->deleted = 1;
-                node->pfd.revents = 0;
-            } else {
-                /* Otherwise, delete it for real.  We can't just mark it as
-                 * deleted because deleted nodes are only cleaned up after
-                 * releasing the walking_handlers lock.
-                 */
-                QLIST_REMOVE(node, node);
-                g_free(node);
-            }
-        }
-    } else {
-        if (node == NULL) {
-            /* Alloc and insert if it's not already there */
-            node = g_malloc0(sizeof(AioHandler));
-            node->e = e;
-            node->pfd.fd = (uintptr_t)event_notifier_get_handle(e);
-            node->pfd.events = G_IO_IN;
-            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
-
-            g_source_add_poll(&ctx->source, &node->pfd);
-        }
-        /* Update handler with latest information */
-        node->io_notify = io_notify;
-        node->io_flush = io_flush;
-    }
-
-    aio_notify(ctx);
-}
-
-bool aio_pending(AioContext *ctx)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->pfd.revents && node->io_notify) {
-            return true;
-        }
-    }
-
-    return false;
-}
-
-bool aio_poll(AioContext *ctx, bool blocking)
-{
-    AioHandler *node;
-    HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
-    bool busy, progress;
-    int count;
-
-    progress = false;
-
-    /*
-     * If there are callbacks left that have been queued, we need to call then.
-     * Do not call select in this case, because it is possible that the caller
-     * does not need a complete flush (as is the case for qemu_aio_wait loops).
-     */
-    if (aio_bh_poll(ctx)) {
-        blocking = false;
-        progress = true;
-    }
-
-    /*
-     * Then dispatch any pending callbacks from the GSource.
-     *
-     * We have to walk very carefully in case qemu_aio_set_fd_handler is
-     * called while we're walking.
-     */
-    node = QLIST_FIRST(&ctx->aio_handlers);
-    while (node) {
-        AioHandler *tmp;
-
-        ctx->walking_handlers++;
-
-        if (node->pfd.revents && node->io_notify) {
-            node->pfd.revents = 0;
-            node->io_notify(node->e);
-            progress = true;
-        }
-
-        tmp = node;
-        node = QLIST_NEXT(node, node);
-
-        ctx->walking_handlers--;
-
-        if (!ctx->walking_handlers && tmp->deleted) {
-            QLIST_REMOVE(tmp, node);
-            g_free(tmp);
-        }
-    }
-
-    if (progress && !blocking) {
-        return true;
-    }
-
-    ctx->walking_handlers++;
-
-    /* fill fd sets */
-    busy = false;
-    count = 0;
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        /* If there aren't pending AIO operations, don't invoke callbacks.
-         * Otherwise, if there are no AIO requests, qemu_aio_wait() would
-         * wait indefinitely.
-         */
-        if (!node->deleted && node->io_flush) {
-            if (node->io_flush(node->e) == 0) {
-                continue;
-            }
-            busy = true;
-        }
-        if (!node->deleted && node->io_notify) {
-            events[count++] = event_notifier_get_handle(node->e);
-        }
-    }
-
-    ctx->walking_handlers--;
-
-    /* No AIO operations?  Get us out of here */
-    if (!busy) {
-        return progress;
-    }
-
-    /* wait until next event */
-    while (count > 0) {
-        int timeout = blocking ? INFINITE : 0;
-        int ret = WaitForMultipleObjects(count, events, FALSE, timeout);
-
-        /* if we have any signaled events, dispatch event */
-        if ((DWORD) (ret - WAIT_OBJECT_0) >= count) {
-            break;
-        }
-
-        blocking = false;
-
-        /* we have to walk very carefully in case
-         * qemu_aio_set_fd_handler is called while we're walking */
-        node = QLIST_FIRST(&ctx->aio_handlers);
-        while (node) {
-            AioHandler *tmp;
-
-            ctx->walking_handlers++;
-
-            if (!node->deleted &&
-                event_notifier_get_handle(node->e) == events[ret - WAIT_OBJECT_0] &&
-                node->io_notify) {
-                node->io_notify(node->e);
-                progress = true;
-            }
-
-            tmp = node;
-            node = QLIST_NEXT(node, node);
-
-            ctx->walking_handlers--;
-
-            if (!ctx->walking_handlers && tmp->deleted) {
-                QLIST_REMOVE(tmp, node);
-                g_free(tmp);
-            }
-        }
-
-        /* Try again, but only call each handler once.  */
-        events[ret - WAIT_OBJECT_0] = events[--count];
-    }
-
-    assert(progress || busy);
-    return true;
-}

aio.c

@@ -0,0 +1,194 @@
+/*
+ * QEMU aio implementation
+ *
+ * Copyright IBM, Corp. 2008
+ *
+ * Authors:
+ *  Anthony Liguori   <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "qemu-common.h"
+#include "block.h"
+#include "qemu-queue.h"
+#include "qemu_socket.h"
+
+typedef struct AioHandler AioHandler;
+
+/* The list of registered AIO handlers */
+static QLIST_HEAD(, AioHandler) aio_handlers;
+
+/* This is a simple lock used to protect the aio_handlers list.  Specifically,
+ * it's used to ensure that no callbacks are removed while we're walking and
+ * dispatching callbacks.
+ */
+static int walking_handlers;
+
+struct AioHandler
+{
+    int fd;
+    IOHandler *io_read;
+    IOHandler *io_write;
+    AioFlushHandler *io_flush;
+    int deleted;
+    void *opaque;
+    QLIST_ENTRY(AioHandler) node;
+};
+
+static AioHandler *find_aio_handler(int fd)
+{
+    AioHandler *node;
+
+    QLIST_FOREACH(node, &aio_handlers, node) {
+        if (node->fd == fd)
+            if (!node->deleted)
+                return node;
+    }
+
+    return NULL;
+}
+
+int qemu_aio_set_fd_handler(int fd,
+                            IOHandler *io_read,
+                            IOHandler *io_write,
+                            AioFlushHandler *io_flush,
+                            void *opaque)
+{
+    AioHandler *node;
+
+    node = find_aio_handler(fd);
+
+    /* Are we deleting the fd handler? */
+    if (!io_read && !io_write) {
+        if (node) {
+            /* If the lock is held, just mark the node as deleted */
+            if (walking_handlers)
+                node->deleted = 1;
+            else {
+                /* Otherwise, delete it for real.  We can't just mark it as
+                 * deleted because deleted nodes are only cleaned up after
+                 * releasing the walking_handlers lock.
+                 */
+                QLIST_REMOVE(node, node);
+                g_free(node);
+            }
+        }
+    } else {
+        if (node == NULL) {
+            /* Alloc and insert if it's not already there */
+            node = g_malloc0(sizeof(AioHandler));
+            node->fd = fd;
+            QLIST_INSERT_HEAD(&aio_handlers, node, node);
+        }
+        /* Update handler with latest information */
+        node->io_read = io_read;
+        node->io_write = io_write;
+        node->io_flush = io_flush;
+        node->opaque = opaque;
+    }
+
+    qemu_set_fd_handler2(fd, NULL, io_read, io_write, opaque);
+
+    return 0;
+}
+
+void qemu_aio_flush(void)
+{
+    while (qemu_aio_wait());
+}
+
+bool qemu_aio_wait(void)
+{
+    AioHandler *node;
+    fd_set rdfds, wrfds;
+    int max_fd = -1;
+    int ret;
+    bool busy;
+
+    /*
+     * If there are callbacks left that have been queued, we need to call then.
+     * Do not call select in this case, because it is possible that the caller
+     * does not need a complete flush (as is the case for qemu_aio_wait loops).
+     */
+    if (qemu_bh_poll()) {
+        return true;
+    }
+
+    walking_handlers = 1;
+
+    FD_ZERO(&rdfds);
+    FD_ZERO(&wrfds);
+
+    /* fill fd sets */
+    busy = false;
+    QLIST_FOREACH(node, &aio_handlers, node) {
+        /* If there aren't pending AIO operations, don't invoke callbacks.
+         * Otherwise, if there are no AIO requests, qemu_aio_wait() would
+         * wait indefinitely.
+         */
+        if (node->io_flush) {
+            if (node->io_flush(node->opaque) == 0) {
+                continue;
+            }
+            busy = true;
+        }
+        if (!node->deleted && node->io_read) {
+            FD_SET(node->fd, &rdfds);
+            max_fd = MAX(max_fd, node->fd + 1);
+        }
+        if (!node->deleted && node->io_write) {
+            FD_SET(node->fd, &wrfds);
+            max_fd = MAX(max_fd, node->fd + 1);
+        }
+    }
+
+    walking_handlers = 0;
+
+    /* No AIO operations?  Get us out of here */
+    if (!busy) {
+        return false;
+    }
+
+    /* wait until next event */
+    ret = select(max_fd, &rdfds, &wrfds, NULL, NULL);
+
+    /* if we have any readable fds, dispatch event */
+    if (ret > 0) {
+        walking_handlers = 1;
+
+        /* we have to walk very carefully in case
+         * qemu_aio_set_fd_handler is called while we're walking */
+        node = QLIST_FIRST(&aio_handlers);
+        while (node) {
+            AioHandler *tmp;
+
+            if (!node->deleted &&
+                FD_ISSET(node->fd, &rdfds) &&
+                node->io_read) {
+                node->io_read(node->opaque);
+            }
+            if (!node->deleted &&
+                FD_ISSET(node->fd, &wrfds) &&
+                node->io_write) {
+                node->io_write(node->opaque);
+            }
+
+            tmp = node;
+            node = QLIST_NEXT(node, node);
+
+            if (tmp->deleted) {
+                QLIST_REMOVE(tmp, node);
+                g_free(tmp);
+            }
+        }
+
+        walking_handlers = 0;
+    }
+
+    return true;
+}

alpha-dis.c

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

arch_init.c

@@ -29,26 +29,22 @@
 #include <sys/mman.h>
 #endif
 #include "config.h"
-#include "monitor/monitor.h"
-#include "sysemu/sysemu.h"
-#include "qemu/bitops.h"
-#include "qemu/bitmap.h"
-#include "sysemu/arch_init.h"
+#include "monitor.h"
+#include "sysemu.h"
+#include "arch_init.h"
 #include "audio/audio.h"
 #include "hw/pc.h"
-#include "hw/pci/pci.h"
+#include "hw/pci.h"
 #include "hw/audiodev.h"
-#include "sysemu/kvm.h"
-#include "migration/migration.h"
-#include "exec/gdbstub.h"
+#include "kvm.h"
+#include "migration.h"
+#include "net.h"
+#include "gdbstub.h"
 #include "hw/smbios.h"
-#include "exec/address-spaces.h"
+#include "exec-memory.h"
 #include "hw/pcspk.h"
-#include "migration/page_cache.h"
-#include "qemu/config-file.h"
+#include "qemu/page_cache.h"
 #include "qmp-commands.h"
-#include "trace.h"
-#include "exec/cpu-all.h"
 
 #ifdef DEBUG_ARCH_INIT
 #define DPRINTF(fmt, ...) \
@@ -140,6 +136,7 @@ static struct defconfig_file {
     /* Indicates it is an user config file (disabled by -no-user-config) */
     bool userconfig;
 } default_config_files[] = {
+    { CONFIG_QEMU_DATADIR "/cpus-" TARGET_ARCH ".conf",  false },
     { CONFIG_QEMU_CONFDIR "/qemu.conf",                   true },
     { CONFIG_QEMU_CONFDIR "/target-" TARGET_ARCH ".conf", true },
     { NULL }, /* end of list */
@@ -265,21 +262,16 @@ uint64_t xbzrle_mig_pages_overflow(void)
     return acct_info.xbzrle_overflows;
 }
 
-static size_t save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
-                             int cont, int flag)
+static void save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
+        int cont, int flag)
 {
-    size_t size;
+        qemu_put_be64(f, offset | cont | flag);
+        if (!cont) {
+                qemu_put_byte(f, strlen(block->idstr));
+                qemu_put_buffer(f, (uint8_t *)block->idstr,
+                                strlen(block->idstr));
+        }
 
-    qemu_put_be64(f, offset | cont | flag);
-    size = 8;
-
-    if (!cont) {
-        qemu_put_byte(f, strlen(block->idstr));
-        qemu_put_buffer(f, (uint8_t *)block->idstr,
-                        strlen(block->idstr));
-        size += 1 + strlen(block->idstr);
-    }
-    return size;
 }
 
 #define ENCODING_FLAG_XBZRLE 0x1
@@ -326,147 +318,56 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
     }
 
     /* Send XBZRLE based compressed page */
-    bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_XBZRLE);
+    save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_XBZRLE);
     qemu_put_byte(f, ENCODING_FLAG_XBZRLE);
     qemu_put_be16(f, encoded_len);
     qemu_put_buffer(f, XBZRLE.encoded_buf, encoded_len);
-    bytes_sent += encoded_len + 1 + 2;
+    bytes_sent = encoded_len + 1 + 2;
     acct_info.xbzrle_pages++;
     acct_info.xbzrle_bytes += bytes_sent;
 
     return bytes_sent;
 }
 
-
-/* This is the last block that we have visited serching for dirty pages
- */
-static RAMBlock *last_seen_block;
-/* This is the last block from where we have sent data */
-static RAMBlock *last_sent_block;
+static RAMBlock *last_block;
 static ram_addr_t last_offset;
-static unsigned long *migration_bitmap;
-static uint64_t migration_dirty_pages;
-static uint32_t last_version;
-
-static inline
-ram_addr_t migration_bitmap_find_and_reset_dirty(MemoryRegion *mr,
-                                                 ram_addr_t start)
-{
-    unsigned long base = mr->ram_addr >> TARGET_PAGE_BITS;
-    unsigned long nr = base + (start >> TARGET_PAGE_BITS);
-    unsigned long size = base + (int128_get64(mr->size) >> TARGET_PAGE_BITS);
-
-    unsigned long next = find_next_bit(migration_bitmap, size, nr);
-
-    if (next < size) {
-        clear_bit(next, migration_bitmap);
-        migration_dirty_pages--;
-    }
-    return (next - base) << TARGET_PAGE_BITS;
-}
-
-static inline bool migration_bitmap_set_dirty(MemoryRegion *mr,
-                                              ram_addr_t offset)
-{
-    bool ret;
-    int nr = (mr->ram_addr + offset) >> TARGET_PAGE_BITS;
-
-    ret = test_and_set_bit(nr, migration_bitmap);
-
-    if (!ret) {
-        migration_dirty_pages++;
-    }
-    return ret;
-}
-
-static void migration_bitmap_sync(void)
-{
-    RAMBlock *block;
-    ram_addr_t addr;
-    uint64_t num_dirty_pages_init = migration_dirty_pages;
-    MigrationState *s = migrate_get_current();
-    static int64_t start_time;
-    static int64_t num_dirty_pages_period;
-    int64_t end_time;
-
-    if (!start_time) {
-        start_time = qemu_get_clock_ms(rt_clock);
-    }
-
-    trace_migration_bitmap_sync_start();
-    memory_global_sync_dirty_bitmap(get_system_memory());
-
-    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
-        for (addr = 0; addr < block->length; addr += TARGET_PAGE_SIZE) {
-            if (memory_region_test_and_clear_dirty(block->mr,
-                                                   addr, TARGET_PAGE_SIZE,
-                                                   DIRTY_MEMORY_MIGRATION)) {
-                migration_bitmap_set_dirty(block->mr, addr);
-            }
-        }
-    }
-    trace_migration_bitmap_sync_end(migration_dirty_pages
-                                    - num_dirty_pages_init);
-    num_dirty_pages_period += migration_dirty_pages - num_dirty_pages_init;
-    end_time = qemu_get_clock_ms(rt_clock);
-
-    /* more than 1 second = 1000 millisecons */
-    if (end_time > start_time + 1000) {
-        s->dirty_pages_rate = num_dirty_pages_period * 1000
-            / (end_time - start_time);
-        start_time = end_time;
-        num_dirty_pages_period = 0;
-    }
-}
 
 /*
  * ram_save_block: Writes a page of memory to the stream f
  *
- * Returns:  The number of bytes written.
- *           0 means no dirty pages
+ * Returns:  0: if the page hasn't changed
+ *          -1: if there are no more dirty pages
+ *           n: the amount of bytes written in other case
  */
 
 static int ram_save_block(QEMUFile *f, bool last_stage)
 {
-    RAMBlock *block = last_seen_block;
+    RAMBlock *block = last_block;
     ram_addr_t offset = last_offset;
-    bool complete_round = false;
-    int bytes_sent = 0;
+    int bytes_sent = -1;
     MemoryRegion *mr;
     ram_addr_t current_addr;
 
     if (!block)
-        block = QTAILQ_FIRST(&ram_list.blocks);
+        block = QLIST_FIRST(&ram_list.blocks);
 
-    while (true) {
+    do {
         mr = block->mr;
-        offset = migration_bitmap_find_and_reset_dirty(mr, offset);
-        if (complete_round && block == last_seen_block &&
-            offset >= last_offset) {
-            break;
-        }
-        if (offset >= block->length) {
-            offset = 0;
-            block = QTAILQ_NEXT(block, next);
-            if (!block) {
-                block = QTAILQ_FIRST(&ram_list.blocks);
-                complete_round = true;
-            }
-        } else {
+        if (memory_region_get_dirty(mr, offset, TARGET_PAGE_SIZE,
+                                    DIRTY_MEMORY_MIGRATION)) {
             uint8_t *p;
-            int cont = (block == last_sent_block) ?
-                RAM_SAVE_FLAG_CONTINUE : 0;
+            int cont = (block == last_block) ? RAM_SAVE_FLAG_CONTINUE : 0;
+
+            memory_region_reset_dirty(mr, offset, TARGET_PAGE_SIZE,
+                                      DIRTY_MEMORY_MIGRATION);
 
             p = memory_region_get_ram_ptr(mr) + offset;
 
-            /* In doubt sent page as normal */
-            bytes_sent = -1;
             if (is_dup_page(p)) {
                 acct_info.dup_pages++;
-                bytes_sent = save_block_hdr(f, block, offset, cont,
-                                            RAM_SAVE_FLAG_COMPRESS);
+                save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_COMPRESS);
                 qemu_put_byte(f, *p);
-                bytes_sent += 1;
+                bytes_sent = 1;
             } else if (migrate_use_xbzrle()) {
                 current_addr = block->offset + offset;
                 bytes_sent = save_xbzrle_page(f, p, current_addr, block,
@@ -476,22 +377,30 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
                 }
             }
 
-            /* XBZRLE overflow or normal page */
+            /* either we didn't send yet (we may have had XBZRLE overflow) */
             if (bytes_sent == -1) {
-                bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
+                save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
                 qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
-                bytes_sent += TARGET_PAGE_SIZE;
+                bytes_sent = TARGET_PAGE_SIZE;
                 acct_info.norm_pages++;
             }
 
             /* if page is unmodified, continue to the next */
-            if (bytes_sent > 0) {
-                last_sent_block = block;
+            if (bytes_sent != 0) {
                 break;
             }
         }
-    }
-    last_seen_block = block;
+
+        offset += TARGET_PAGE_SIZE;
+        if (offset >= block->length) {
+            offset = 0;
+            block = QLIST_NEXT(block, next);
+            if (!block)
+                block = QLIST_FIRST(&ram_list.blocks);
+        }
+    } while (block != last_block || offset != last_offset);
+
+    last_block = block;
     last_offset = offset;
 
     return bytes_sent;
@@ -501,7 +410,7 @@ static uint64_t bytes_transferred;
 
 static ram_addr_t ram_save_remaining(void)
 {
-    return migration_dirty_pages;
+    return ram_list.dirty_pages;
 }
 
 uint64_t ram_bytes_remaining(void)
@@ -519,21 +428,46 @@ uint64_t ram_bytes_total(void)
     RAMBlock *block;
     uint64_t total = 0;
 
-    QTAILQ_FOREACH(block, &ram_list.blocks, next)
+    QLIST_FOREACH(block, &ram_list.blocks, next)
         total += block->length;
 
     return total;
 }
 
+static int block_compar(const void *a, const void *b)
+{
+    RAMBlock * const *ablock = a;
+    RAMBlock * const *bblock = b;
+
+    return strcmp((*ablock)->idstr, (*bblock)->idstr);
+}
+
+static void sort_ram_list(void)
+{
+    RAMBlock *block, *nblock, **blocks;
+    int n;
+    n = 0;
+    QLIST_FOREACH(block, &ram_list.blocks, next) {
+        ++n;
+    }
+    blocks = g_malloc(n * sizeof *blocks);
+    n = 0;
+    QLIST_FOREACH_SAFE(block, &ram_list.blocks, next, nblock) {
+        blocks[n++] = block;
+        QLIST_REMOVE(block, next);
+    }
+    qsort(blocks, n, sizeof *blocks, block_compar);
+    while (--n >= 0) {
+        QLIST_INSERT_HEAD(&ram_list.blocks, blocks[n], next);
+    }
+    g_free(blocks);
+}
+
 static void migration_end(void)
 {
-    if (migration_bitmap) {
-        memory_global_dirty_log_stop();
-        g_free(migration_bitmap);
-        migration_bitmap = NULL;
-    }
+    memory_global_dirty_log_stop();
 
-    if (XBZRLE.cache) {
+    if (migrate_use_xbzrle()) {
         cache_fini(XBZRLE.cache);
         g_free(XBZRLE.cache);
         g_free(XBZRLE.encoded_buf);
@@ -548,28 +482,17 @@ static void ram_migration_cancel(void *opaque)
     migration_end();
 }
 
-static void reset_ram_globals(void)
-{
-    last_seen_block = NULL;
-    last_sent_block = NULL;
-    last_offset = 0;
-    last_version = ram_list.version;
-}
-
 #define MAX_WAIT 50 /* ms, half buffered_file limit */
 
 static int ram_save_setup(QEMUFile *f, void *opaque)
 {
+    ram_addr_t addr;
     RAMBlock *block;
-    int64_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;
 
-    migration_bitmap = bitmap_new(ram_pages);
-    bitmap_set(migration_bitmap, 0, ram_pages);
-    migration_dirty_pages = ram_pages;
-
-    qemu_mutex_lock_ramlist();
     bytes_transferred = 0;
-    reset_ram_globals();
+    last_block = NULL;
+    last_offset = 0;
+    sort_ram_list();
 
     if (migrate_use_xbzrle()) {
         XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
@@ -584,18 +507,26 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
         acct_clear();
     }
 
+    /* Make sure all dirty bits are set */
+    QLIST_FOREACH(block, &ram_list.blocks, next) {
+        for (addr = 0; addr < block->length; addr += TARGET_PAGE_SIZE) {
+            if (!memory_region_get_dirty(block->mr, addr, TARGET_PAGE_SIZE,
+                                         DIRTY_MEMORY_MIGRATION)) {
+                memory_region_set_dirty(block->mr, addr, TARGET_PAGE_SIZE);
+            }
+        }
+    }
+
     memory_global_dirty_log_start();
-    migration_bitmap_sync();
 
     qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
 
-    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
+    QLIST_FOREACH(block, &ram_list.blocks, next) {
         qemu_put_byte(f, strlen(block->idstr));
         qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr));
         qemu_put_be64(f, block->length);
     }
 
-    qemu_mutex_unlock_ramlist();
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
 
     return 0;
@@ -603,28 +534,25 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
 
 static int ram_save_iterate(QEMUFile *f, void *opaque)
 {
+    uint64_t bytes_transferred_last;
+    double bwidth = 0;
     int ret;
     int i;
-    int64_t t0;
-    int total_sent = 0;
+    uint64_t expected_time;
 
-    qemu_mutex_lock_ramlist();
+    bytes_transferred_last = bytes_transferred;
+    bwidth = qemu_get_clock_ns(rt_clock);
 
-    if (ram_list.version != last_version) {
-        reset_ram_globals();
-    }
-
-    t0 = qemu_get_clock_ns(rt_clock);
     i = 0;
     while ((ret = qemu_file_rate_limit(f)) == 0) {
         int bytes_sent;
 
         bytes_sent = ram_save_block(f, false);
         /* no more blocks to sent */
-        if (bytes_sent == 0) {
+        if (bytes_sent < 0) {
             break;
         }
-        total_sent += bytes_sent;
+        bytes_transferred += bytes_sent;
         acct_info.iterations++;
         /* we want to check in the 1st loop, just in case it was the 1st time
            and we had to sync the dirty bitmap.
@@ -632,7 +560,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
            iterations
         */
         if ((i & 63) == 0) {
-            uint64_t t1 = (qemu_get_clock_ns(rt_clock) - t0) / 1000000;
+            uint64_t t1 = (qemu_get_clock_ns(rt_clock) - bwidth) / 1000000;
             if (t1 > MAX_WAIT) {
                 DPRINTF("big wait: %" PRIu64 " milliseconds, %d iterations\n",
                         t1, i);
@@ -642,24 +570,38 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
         i++;
     }
 
-    qemu_mutex_unlock_ramlist();
-
     if (ret < 0) {
-        bytes_transferred += total_sent;
         return ret;
     }
 
-    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
-    total_sent += 8;
-    bytes_transferred += total_sent;
+    bwidth = qemu_get_clock_ns(rt_clock) - bwidth;
+    bwidth = (bytes_transferred - bytes_transferred_last) / bwidth;
 
-    return total_sent;
+    /* if we haven't transferred anything this round, force expected_time to a
+     * a very high value, but without crashing */
+    if (bwidth == 0) {
+        bwidth = 0.000001;
+    }
+
+    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
+
+    expected_time = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
+
+    DPRINTF("ram_save_live: expected(%" PRIu64 ") <= max(%" PRIu64 ")?\n",
+            expected_time, migrate_max_downtime());
+
+    if (expected_time <= migrate_max_downtime()) {
+        memory_global_sync_dirty_bitmap(get_system_memory());
+        expected_time = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
+
+        return expected_time <= migrate_max_downtime();
+    }
+    return 0;
 }
 
 static int ram_save_complete(QEMUFile *f, void *opaque)
 {
-    qemu_mutex_lock_ramlist();
-    migration_bitmap_sync();
+    memory_global_sync_dirty_bitmap(get_system_memory());
 
     /* try transferring iterative blocks of memory */
 
@@ -669,32 +611,18 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
 
         bytes_sent = ram_save_block(f, true);
         /* no more blocks to sent */
-        if (bytes_sent == 0) {
+        if (bytes_sent < 0) {
             break;
         }
         bytes_transferred += bytes_sent;
     }
-    migration_end();
+    memory_global_dirty_log_stop();
 
-    qemu_mutex_unlock_ramlist();
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
 
     return 0;
 }
 
-static uint64_t ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
-{
-    uint64_t remaining_size;
-
-    remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
-
-    if (remaining_size < max_size) {
-        migration_bitmap_sync();
-        remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
-    }
-    return remaining_size;
-}
-
 static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
 {
     int ret, rc = 0;
@@ -757,7 +685,7 @@ static inline void *host_from_stream_offset(QEMUFile *f,
     qemu_get_buffer(f, (uint8_t *)id, len);
     id[len] = 0;
 
-    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
+    QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (!strncmp(id, block->idstr, sizeof(id)))
             return memory_region_get_ram_ptr(block->mr) + offset;
     }
@@ -801,7 +729,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                     id[len] = 0;
                     length = qemu_get_be64(f);
 
-                    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
+                    QLIST_FOREACH(block, &ram_list.blocks, next) {
                         if (!strncmp(id, block->idstr, sizeof(id))) {
                             if (block->length != length) {
                                 ret =  -EINVAL;
@@ -836,8 +764,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
             memset(host, ch, TARGET_PAGE_SIZE);
 #ifndef _WIN32
             if (ch == 0 &&
-                (!kvm_enabled() || kvm_has_sync_mmu()) &&
-                getpagesize() <= TARGET_PAGE_SIZE) {
+                (!kvm_enabled() || kvm_has_sync_mmu())) {
                 qemu_madvise(host, TARGET_PAGE_SIZE, QEMU_MADV_DONTNEED);
             }
 #endif
@@ -851,6 +778,9 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
 
             qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
         } else if (flags & RAM_SAVE_FLAG_XBZRLE) {
+            if (!migrate_use_xbzrle()) {
+                return -EINVAL;
+            }
             void *host = host_from_stream_offset(f, addr, flags);
             if (!host) {
                 return -EINVAL;
@@ -878,7 +808,6 @@ SaveVMHandlers savevm_ram_handlers = {
     .save_live_setup = ram_save_setup,
     .save_live_iterate = ram_save_iterate,
     .save_live_complete = ram_save_complete,
-    .save_live_pending = ram_save_pending,
     .load_state = ram_load,
     .cancel = ram_migration_cancel,
 };

arch_init.h

@@ -34,6 +34,6 @@ int tcg_available(void);
 int kvm_available(void);
 int xen_available(void);
 
-CpuDefinitionInfoList *arch_query_cpu_definitions(Error **errp);
+CpuDefinitionInfoList GCC_WEAK_DECL *arch_query_cpu_definitions(Error **errp);
 
 #endif

arm-dis.c

@@ -22,7 +22,7 @@
 /* Start of qemu specific additions.  Mostly this is stub definitions
    for things we don't care about.  */
 
-#include "disas/bfd.h"
+#include "dis-asm.h"
 #define ATTRIBUTE_UNUSED __attribute__((unused))
 #define ISSPACE(x) ((x) == ' ' || (x) == '\t' || (x) == '\n')
 

async.c

@@ -23,14 +23,16 @@
  */
 
 #include "qemu-common.h"
-#include "block/aio.h"
-#include "qemu/main-loop.h"
+#include "qemu-aio.h"
+#include "main-loop.h"
+
+/* Anchor of the list of Bottom Halves belonging to the context */
+static struct QEMUBH *first_bh;
 
 /***********************************************************/
 /* bottom halves (can be seen as timers which expire ASAP) */
 
 struct QEMUBH {
-    AioContext *ctx;
     QEMUBHFunc *cb;
     void *opaque;
     QEMUBH *next;
@@ -39,27 +41,27 @@ struct QEMUBH {
     bool deleted;
 };
 
-QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
+QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque)
 {
     QEMUBH *bh;
     bh = g_malloc0(sizeof(QEMUBH));
-    bh->ctx = ctx;
     bh->cb = cb;
     bh->opaque = opaque;
-    bh->next = ctx->first_bh;
-    ctx->first_bh = bh;
+    bh->next = first_bh;
+    first_bh = bh;
     return bh;
 }
 
-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) {
+    for (bh = first_bh; bh; bh = next) {
         next = bh->next;
         if (!bh->deleted && bh->scheduled) {
             bh->scheduled = 0;
@@ -70,11 +72,11 @@ int aio_bh_poll(AioContext *ctx)
         }
     }
 
-    ctx->walking_bh--;
+    nesting--;
 
     /* remove deleted bhs */
-    if (!ctx->walking_bh) {
-        bhp = &ctx->first_bh;
+    if (!nesting) {
+        bhp = &first_bh;
         while (*bhp) {
             bh = *bhp;
             if (bh->deleted) {
@@ -103,7 +105,8 @@ void qemu_bh_schedule(QEMUBH *bh)
         return;
     bh->scheduled = 1;
     bh->idle = 0;
-    aio_notify(bh->ctx);
+    /* stop the currently executing CPU to execute the BH ASAP */
+    qemu_notify_event();
 }
 
 void qemu_bh_cancel(QEMUBH *bh)
@@ -117,101 +120,23 @@ void qemu_bh_delete(QEMUBH *bh)
     bh->deleted = 1;
 }
 
-static gboolean
-aio_ctx_prepare(GSource *source, gint    *timeout)
+void qemu_bh_update_timeout(uint32_t *timeout)
 {
-    AioContext *ctx = (AioContext *) source;
     QEMUBH *bh;
 
-    for (bh = ctx->first_bh; bh; bh = bh->next) {
+    for (bh = first_bh; bh; bh = bh->next) {
         if (!bh->deleted && bh->scheduled) {
             if (bh->idle) {
                 /* idle bottom halves will be polled at least
                  * every 10ms */
-                *timeout = 10;
+                *timeout = MIN(10, *timeout);
             } else {
                 /* non-idle bottom halves will be executed
                  * immediately */
                 *timeout = 0;
-                return true;
+                break;
             }
         }
     }
-
-    return false;
 }
 
-static gboolean
-aio_ctx_check(GSource *source)
-{
-    AioContext *ctx = (AioContext *) source;
-    QEMUBH *bh;
-
-    for (bh = ctx->first_bh; bh; bh = bh->next) {
-        if (!bh->deleted && bh->scheduled) {
-            return true;
-	}
-    }
-    return aio_pending(ctx);
-}
-
-static gboolean
-aio_ctx_dispatch(GSource     *source,
-                 GSourceFunc  callback,
-                 gpointer     user_data)
-{
-    AioContext *ctx = (AioContext *) source;
-
-    assert(callback == NULL);
-    aio_poll(ctx, false);
-    return true;
-}
-
-static void
-aio_ctx_finalize(GSource     *source)
-{
-    AioContext *ctx = (AioContext *) source;
-
-    aio_set_event_notifier(ctx, &ctx->notifier, NULL, NULL);
-    event_notifier_cleanup(&ctx->notifier);
-}
-
-static GSourceFuncs aio_source_funcs = {
-    aio_ctx_prepare,
-    aio_ctx_check,
-    aio_ctx_dispatch,
-    aio_ctx_finalize
-};
-
-GSource *aio_get_g_source(AioContext *ctx)
-{
-    g_source_ref(&ctx->source);
-    return &ctx->source;
-}
-
-void aio_notify(AioContext *ctx)
-{
-    event_notifier_set(&ctx->notifier);
-}
-
-AioContext *aio_context_new(void)
-{
-    AioContext *ctx;
-    ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext));
-    event_notifier_init(&ctx->notifier, false);
-    aio_set_event_notifier(ctx, &ctx->notifier, 
-                           (EventNotifierHandler *)
-                           event_notifier_test_and_clear, NULL);
-
-    return ctx;
-}
-
-void aio_context_ref(AioContext *ctx)
-{
-    g_source_ref(&ctx->source);
-}
-
-void aio_context_unref(AioContext *ctx)
-{
-    g_source_unref(&ctx->source);
-}

audio/Makefile.objs

@@ -12,6 +12,3 @@ common-obj-$(CONFIG_WINWAVE) += winwaveaudio.o
 common-obj-$(CONFIG_AUDIO_PT_INT) += audio_pt_int.o
 common-obj-$(CONFIG_AUDIO_WIN_INT) += audio_win_int.o
 common-obj-y += wavcapture.o
-
-$(obj)/audio.o $(obj)/fmodaudio.o: QEMU_CFLAGS += $(FMOD_CFLAGS)
-$(obj)/sdlaudio.o: QEMU_CFLAGS += $(SDL_CFLAGS)

audio/alsaaudio.c

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

audio/audio.c

@@ -23,9 +23,9 @@
  */
 #include "hw/hw.h"
 #include "audio.h"
-#include "monitor/monitor.h"
-#include "qemu/timer.h"
-#include "sysemu/sysemu.h"
+#include "monitor.h"
+#include "qemu-timer.h"
+#include "sysemu.h"
 
 #define AUDIO_CAP "audio"
 #include "audio_int.h"
@@ -828,9 +828,8 @@ static int audio_attach_capture (HWVoiceOut *hw)
         QLIST_INSERT_HEAD (&hw_cap->sw_head, sw, entries);
         QLIST_INSERT_HEAD (&hw->cap_head, sc, entries);
 #ifdef DEBUG_CAPTURE
-        sw->name = g_strdup_printf ("for %p %d,%d,%d",
-                                    hw, sw->info.freq, sw->info.bits,
-                                    sw->info.nchannels);
+        asprintf (&sw->name, "for %p %d,%d,%d",
+                  hw, sw->info.freq, sw->info.bits, sw->info.nchannels);
         dolog ("Added %s active = %d\n", sw->name, sw->active);
 #endif
         if (sw->active) {

audio/audio.h

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

audio/noaudio.c

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

audio/ossaudio.c

@@ -31,8 +31,8 @@
 #include <sys/soundcard.h>
 #endif
 #include "qemu-common.h"
-#include "qemu/main-loop.h"
-#include "qemu/host-utils.h"
+#include "host-utils.h"
+#include "qemu-char.h"
 #include "audio.h"
 
 #define AUDIO_CAP "oss"

audio/spiceaudio.c

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

audio/wavaudio.c

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

audio/wavcapture.c

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

audio/winwaveaudio.c

@@ -1,7 +1,7 @@
 /* public domain */
 
 #include "qemu-common.h"
-#include "sysemu/sysemu.h"
+#include "sysemu.h"
 #include "audio.h"
 
 #define AUDIO_CAP "winwave"

backends/Makefile.objs

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

backends/rng-egd.c

@@ -1,224 +0,0 @@
-/*
- * QEMU Random Number Generator Backend
- *
- * Copyright IBM, Corp. 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include "qemu/rng.h"
-#include "char/char.h"
-#include "qapi/qmp/qerror.h"
-#include "hw/qdev.h" /* just for DEFINE_PROP_CHR */
-
-#define TYPE_RNG_EGD "rng-egd"
-#define RNG_EGD(obj) OBJECT_CHECK(RngEgd, (obj), TYPE_RNG_EGD)
-
-typedef struct RngEgd
-{
-    RngBackend parent;
-
-    CharDriverState *chr;
-    char *chr_name;
-
-    GSList *requests;
-} RngEgd;
-
-typedef struct RngRequest
-{
-    EntropyReceiveFunc *receive_entropy;
-    uint8_t *data;
-    void *opaque;
-    size_t offset;
-    size_t size;
-} RngRequest;
-
-static void rng_egd_request_entropy(RngBackend *b, size_t size,
-                                    EntropyReceiveFunc *receive_entropy,
-                                    void *opaque)
-{
-    RngEgd *s = RNG_EGD(b);
-    RngRequest *req;
-
-    req = g_malloc(sizeof(*req));
-
-    req->offset = 0;
-    req->size = size;
-    req->receive_entropy = receive_entropy;
-    req->opaque = opaque;
-    req->data = g_malloc(req->size);
-
-    while (size > 0) {
-        uint8_t header[2];
-        uint8_t len = MIN(size, 255);
-
-        /* synchronous entropy request */
-        header[0] = 0x02;
-        header[1] = len;
-
-        qemu_chr_fe_write(s->chr, header, sizeof(header));
-
-        size -= len;
-    }
-
-    s->requests = g_slist_append(s->requests, req);
-}
-
-static void rng_egd_free_request(RngRequest *req)
-{
-    g_free(req->data);
-    g_free(req);
-}
-
-static int rng_egd_chr_can_read(void *opaque)
-{
-    RngEgd *s = RNG_EGD(opaque);
-    GSList *i;
-    int size = 0;
-
-    for (i = s->requests; i; i = i->next) {
-        RngRequest *req = i->data;
-        size += req->size - req->offset;
-    }
-
-    return size;
-}
-
-static void rng_egd_chr_read(void *opaque, const uint8_t *buf, int size)
-{
-    RngEgd *s = RNG_EGD(opaque);
-
-    while (size > 0 && s->requests) {
-        RngRequest *req = s->requests->data;
-        int len = MIN(size, req->size - req->offset);
-
-        memcpy(req->data + req->offset, buf, len);
-        req->offset += len;
-        size -= len;
-
-        if (req->offset == req->size) {
-            s->requests = g_slist_remove_link(s->requests, s->requests);
-
-            req->receive_entropy(req->opaque, req->data, req->size);
-
-            rng_egd_free_request(req);
-        }
-    }
-}
-
-static void rng_egd_free_requests(RngEgd *s)
-{
-    GSList *i;
-
-    for (i = s->requests; i; i = i->next) {
-        rng_egd_free_request(i->data);
-    }
-
-    g_slist_free(s->requests);
-    s->requests = NULL;
-}
-
-static void rng_egd_cancel_requests(RngBackend *b)
-{
-    RngEgd *s = RNG_EGD(b);
-
-    /* We simply delete the list of pending requests.  If there is data in the 
-     * queue waiting to be read, this is okay, because there will always be
-     * more data than we requested originally
-     */
-    rng_egd_free_requests(s);
-}
-
-static void rng_egd_opened(RngBackend *b, Error **errp)
-{
-    RngEgd *s = RNG_EGD(b);
-
-    if (s->chr_name == NULL) {
-        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
-                  "chardev", "a valid character device");
-        return;
-    }
-
-    s->chr = qemu_chr_find(s->chr_name);
-    if (s->chr == NULL) {
-        error_set(errp, QERR_DEVICE_NOT_FOUND, s->chr_name);
-        return;
-    }
-
-    /* FIXME we should resubmit pending requests when the CDS reconnects. */
-    qemu_chr_add_handlers(s->chr, rng_egd_chr_can_read, rng_egd_chr_read,
-                          NULL, s);
-}
-
-static void rng_egd_set_chardev(Object *obj, const char *value, Error **errp)
-{
-    RngBackend *b = RNG_BACKEND(obj);
-    RngEgd *s = RNG_EGD(b);
-
-    if (b->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-    } else {
-        g_free(s->chr_name);
-        s->chr_name = g_strdup(value);
-    }
-}
-
-static char *rng_egd_get_chardev(Object *obj, Error **errp)
-{
-    RngEgd *s = RNG_EGD(obj);
-
-    if (s->chr && s->chr->label) {
-        return g_strdup(s->chr->label);
-    }
-
-    return NULL;
-}
-
-static void rng_egd_init(Object *obj)
-{
-    object_property_add_str(obj, "chardev",
-                            rng_egd_get_chardev, rng_egd_set_chardev,
-                            NULL);
-}
-
-static void rng_egd_finalize(Object *obj)
-{
-    RngEgd *s = RNG_EGD(obj);
-
-    if (s->chr) {
-        qemu_chr_add_handlers(s->chr, NULL, NULL, NULL, NULL);
-    }
-
-    g_free(s->chr_name);
-
-    rng_egd_free_requests(s);
-}
-
-static void rng_egd_class_init(ObjectClass *klass, void *data)
-{
-    RngBackendClass *rbc = RNG_BACKEND_CLASS(klass);
-
-    rbc->request_entropy = rng_egd_request_entropy;
-    rbc->cancel_requests = rng_egd_cancel_requests;
-    rbc->opened = rng_egd_opened;
-}
-
-static 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

@@ -1,161 +0,0 @@
-/*
- * QEMU Random Number Generator Backend
- *
- * Copyright IBM, Corp. 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include "qemu/rng-random.h"
-#include "qemu/rng.h"
-#include "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);
-    g_assert(len != -1);
-
-    s->receive_func(s->opaque, buffer, len);
-    s->receive_func = NULL;
-
-    qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
-}
-
-static void rng_random_request_entropy(RngBackend *b, size_t size,
-                                        EntropyReceiveFunc *receive_entropy,
-                                        void *opaque)
-{
-    RndRandom *s = RNG_RANDOM(b);
-
-    if (s->receive_func) {
-        s->receive_func(s->opaque, NULL, 0);
-    }
-
-    s->receive_func = receive_entropy;
-    s->opaque = opaque;
-    s->size = size;
-
-    qemu_set_fd_handler(s->fd, entropy_available, NULL, s);
-}
-
-static void rng_random_opened(RngBackend *b, Error **errp)
-{
-    RndRandom *s = RNG_RANDOM(b);
-
-    if (s->filename == NULL) {
-        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
-                  "filename", "a valid filename");
-    } else {
-        s->fd = open(s->filename, O_RDONLY | O_NONBLOCK);
-
-        if (s->fd == -1) {
-            error_set(errp, QERR_OPEN_FILE_FAILED, s->filename);
-        }
-    }
-}
-
-static char *rng_random_get_filename(Object *obj, Error **errp)
-{
-    RndRandom *s = RNG_RANDOM(obj);
-
-    if (s->filename) {
-        return g_strdup(s->filename);
-    }
-
-    return NULL;
-}
-
-static void rng_random_set_filename(Object *obj, const char *filename,
-                                 Error **errp)
-{
-    RngBackend *b = RNG_BACKEND(obj);
-    RndRandom *s = RNG_RANDOM(obj);
-
-    if (b->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-        return;
-    }
-
-    if (s->filename) {
-        g_free(s->filename);
-    }
-
-    s->filename = g_strdup(filename);
-}
-
-static void rng_random_init(Object *obj)
-{
-    RndRandom *s = RNG_RANDOM(obj);
-
-    object_property_add_str(obj, "filename",
-                            rng_random_get_filename,
-                            rng_random_set_filename,
-                            NULL);
-
-    s->filename = g_strdup("/dev/random");
-}
-
-static void rng_random_finalize(Object *obj)
-{
-    RndRandom *s = RNG_RANDOM(obj);
-
-    qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
-
-    if (s->fd != -1) {
-        close(s->fd);
-    }
-
-    g_free(s->filename);
-}
-
-static void rng_random_class_init(ObjectClass *klass, void *data)
-{
-    RngBackendClass *rbc = RNG_BACKEND_CLASS(klass);
-
-    rbc->request_entropy = rng_random_request_entropy;
-    rbc->opened = rng_random_opened;
-}
-
-static const TypeInfo rng_random_info = {
-    .name = TYPE_RNG_RANDOM,
-    .parent = TYPE_RNG_BACKEND,
-    .instance_size = sizeof(RndRandom),
-    .class_init = rng_random_class_init,
-    .instance_init = rng_random_init,
-    .instance_finalize = rng_random_finalize,
-};
-
-static void register_types(void)
-{
-    type_register_static(&rng_random_info);
-}
-
-type_init(register_types);

backends/rng.c

@@ -1,93 +0,0 @@
-/*
- * QEMU Random Number Generator Backend
- *
- * Copyright IBM, Corp. 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include "qemu/rng.h"
-#include "qapi/qmp/qerror.h"
-
-void rng_backend_request_entropy(RngBackend *s, size_t size,
-                                 EntropyReceiveFunc *receive_entropy,
-                                 void *opaque)
-{
-    RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
-
-    if (k->request_entropy) {
-        k->request_entropy(s, size, receive_entropy, opaque);
-    }
-}
-
-void rng_backend_cancel_requests(RngBackend *s)
-{
-    RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
-
-    if (k->cancel_requests) {
-        k->cancel_requests(s);
-    }
-}
-
-static bool rng_backend_prop_get_opened(Object *obj, Error **errp)
-{
-    RngBackend *s = RNG_BACKEND(obj);
-
-    return s->opened;
-}
-
-void rng_backend_open(RngBackend *s, Error **errp)
-{
-    object_property_set_bool(OBJECT(s), true, "opened", errp);
-}
-
-static void rng_backend_prop_set_opened(Object *obj, bool value, Error **errp)
-{
-    RngBackend *s = RNG_BACKEND(obj);
-    RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
-
-    if (value == s->opened) {
-        return;
-    }
-
-    if (!value && s->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-        return;
-    }
-
-    if (k->opened) {
-        k->opened(s, errp);
-    }
-
-    if (!error_is_set(errp)) {
-        s->opened = value;
-    }
-}
-
-static void rng_backend_init(Object *obj)
-{
-    object_property_add_bool(obj, "opened",
-                             rng_backend_prop_get_opened,
-                             rng_backend_prop_set_opened,
-                             NULL);
-}
-
-static const TypeInfo rng_backend_info = {
-    .name = TYPE_RNG_BACKEND,
-    .parent = TYPE_OBJECT,
-    .instance_size = sizeof(RngBackend),
-    .instance_init = rng_backend_init,
-    .class_size = sizeof(RngBackendClass),
-    .abstract = true,
-};
-
-static void register_types(void)
-{
-    type_register_static(&rng_backend_info);
-}
-
-type_init(register_types);

balloon.c

@@ -24,13 +24,13 @@
  * 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"
+#include "qjson.h"
 
 static QEMUBalloonEvent *balloon_event_fn;
 static QEMUBalloonStatus *balloon_stat_fn;

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);

bitmap.c

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

bitmap.h

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

bitops.c

@@ -11,7 +11,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include "qemu/bitops.h"
+#include "bitops.h"
 
 #define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
 
@@ -60,7 +60,7 @@ found_first:
         return result + size;	/* Nope. */
     }
 found_middle:
-    return result + bitops_ctzl(tmp);
+    return result + bitops_ffsl(tmp);
 }
 
 /*
@@ -109,7 +109,7 @@ found_first:
         return result + size;	/* Nope. */
     }
 found_middle:
-    return result + bitops_ctol(tmp);
+    return result + ffz(tmp);
 }
 
 unsigned long find_last_bit(const unsigned long *addr, unsigned long size)

bitops.h

@@ -13,7 +13,6 @@
 #define BITOPS_H
 
 #include "qemu-common.h"
-#include "host-utils.h"
 
 #define BITS_PER_BYTE           CHAR_BIT
 #define BITS_PER_LONG           (sizeof (unsigned long) * BITS_PER_BYTE)
@@ -24,29 +23,41 @@
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 
 /**
- * bitops_ctzl - count trailing zeroes in word.
+ * bitops_ffs - find first bit in word.
  * @word: The word to search
  *
- * Returns -1 if no bit exists.  Note that compared to the C library
- * routine ffsl, this one returns one less.
+ * Undefined if no bit exists, so code should check against 0 first.
  */
-static unsigned long bitops_ctzl(unsigned long word)
+static unsigned long bitops_ffsl(unsigned long word)
 {
-#if QEMU_GNUC_PREREQ(3, 4)
-    return __builtin_ffsl(word) - 1;
-#else
-    if (!word) {
-        return -1;
-    }
+	int num = 0;
 
-    if (sizeof(long) == 4) {
-        return ctz32(word);
-    } else if (sizeof(long) == 8) {
-        return ctz64(word);
-    } else {
-        abort();
-    }
+#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;
 }
 
 /**
@@ -88,14 +99,14 @@ static inline unsigned long bitops_flsl(unsigned long word)
 }
 
 /**
- * cto - count trailing ones in word.
+ * ffz - find first zero in word.
  * @word: The word to search
  *
- * Returns -1 if all bit are set.
+ * Undefined if no zero exists, so code should check against ~0UL first.
  */
-static inline unsigned long bitops_ctol(unsigned long word)
+static inline unsigned long ffz(unsigned long word)
 {
-    return bitops_ctzl(~word);
+    return bitops_ffsl(~word);
 }
 
 /**

block-migration.c

@@ -14,17 +14,16 @@
  */
 
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include "hw/hw.h"
-#include "qemu/queue.h"
-#include "qemu/timer.h"
-#include "migration/block.h"
-#include "migration/migration.h"
-#include "sysemu/blockdev.h"
+#include "qemu-queue.h"
+#include "qemu-timer.h"
+#include "block-migration.h"
+#include "migration.h"
+#include "blockdev.h"
 #include <assert.h>
 
-#define BLOCK_SIZE                       (1 << 20)
-#define BDRV_SECTORS_PER_DIRTY_CHUNK     (BLOCK_SIZE >> BDRV_SECTOR_BITS)
+#define BLOCK_SIZE (BDRV_SECTORS_PER_DIRTY_CHUNK << BDRV_SECTOR_BITS)
 
 #define BLK_MIG_FLAG_DEVICE_BLOCK       0x01
 #define BLK_MIG_FLAG_EOS                0x02
@@ -78,7 +77,9 @@ typedef struct BlkMigState {
     int64_t total_sector_sum;
     int prev_progress;
     int bulk_completed;
+    long double total_time;
     long double prev_time_offset;
+    int reads;
 } BlkMigState;
 
 static BlkMigState block_mig_state;
@@ -131,6 +132,12 @@ uint64_t blk_mig_bytes_total(void)
     return sum << BDRV_SECTOR_BITS;
 }
 
+static inline long double compute_read_bwidth(void)
+{
+    assert(block_mig_state.total_time != 0);
+    return (block_mig_state.reads / block_mig_state.total_time) * BLOCK_SIZE;
+}
+
 static int bmds_aio_inflight(BlkMigDevState *bmds, int64_t sector)
 {
     int64_t chunk = sector / (int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK;
@@ -184,6 +191,8 @@ static void blk_mig_read_cb(void *opaque, int ret)
 
     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);
@@ -255,7 +264,7 @@ static void set_dirty_tracking(int enable)
     BlkMigDevState *bmds;
 
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        bdrv_set_dirty_tracking(bmds->bs, enable ? BLOCK_SIZE : 0);
+        bdrv_set_dirty_tracking(bmds->bs, enable);
     }
 }
 
@@ -301,6 +310,8 @@ 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.total_time = 0;
+    block_mig_state.reads = 0;
 
     bdrv_iterate(init_blk_migration_it, NULL);
 }
@@ -412,23 +423,20 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
 
 error:
     DPRINTF("Error reading sector %" PRId64 "\n", sector);
+    qemu_file_set_error(f, ret);
     g_free(blk->buf);
     g_free(blk);
-    return ret;
+    return 0;
 }
 
-/* return value:
- * 0: too much data for max_downtime
- * 1: few enough data for max_downtime
-*/
 static int blk_mig_save_dirty_block(QEMUFile *f, int is_async)
 {
     BlkMigDevState *bmds;
-    int ret = 1;
+    int ret = 0;
 
     QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
-        ret = mig_save_device_dirty(f, bmds, is_async);
-        if (ret <= 0) {
+        if (mig_save_device_dirty(f, bmds, is_async) == 0) {
+            ret = 1;
             break;
         }
     }
@@ -436,10 +444,9 @@ static int blk_mig_save_dirty_block(QEMUFile *f, int is_async)
     return ret;
 }
 
-static int flush_blks(QEMUFile *f)
+static void flush_blks(QEMUFile* f)
 {
     BlkMigBlock *blk;
-    int ret = 0;
 
     DPRINTF("%s Enter submitted %d read_done %d transferred %d\n",
             __FUNCTION__, block_mig_state.submitted, block_mig_state.read_done,
@@ -450,7 +457,7 @@ static int flush_blks(QEMUFile *f)
             break;
         }
         if (blk->ret < 0) {
-            ret = blk->ret;
+            qemu_file_set_error(f, blk->ret);
             break;
         }
         blk_send(f, blk);
@@ -467,7 +474,6 @@ static int flush_blks(QEMUFile *f)
     DPRINTF("%s Exit submitted %d read_done %d transferred %d\n", __FUNCTION__,
             block_mig_state.submitted, block_mig_state.read_done,
             block_mig_state.transferred);
-    return ret;
 }
 
 static int64_t get_remaining_dirty(void)
@@ -479,7 +485,33 @@ static int64_t get_remaining_dirty(void)
         dirty += bdrv_get_dirty_count(bmds->bs);
     }
 
-    return dirty << BDRV_SECTOR_BITS;
+    return dirty * BLOCK_SIZE;
+}
+
+static int is_stage2_completed(void)
+{
+    int64_t remaining_dirty;
+    long double bwidth;
+
+    if (block_mig_state.bulk_completed == 1) {
+
+        remaining_dirty = get_remaining_dirty();
+        if (remaining_dirty == 0) {
+            return 1;
+        }
+
+        bwidth = compute_read_bwidth();
+
+        if ((remaining_dirty / bwidth) <=
+            migrate_max_downtime()) {
+            /* finish stage2 because we think that we can finish remaining work
+               below max_downtime */
+
+            return 1;
+        }
+    }
+
+    return 0;
 }
 
 static void blk_mig_cleanup(void)
@@ -487,8 +519,6 @@ static void blk_mig_cleanup(void)
     BlkMigDevState *bmds;
     BlkMigBlock *blk;
 
-    bdrv_drain_all();
-
     set_dirty_tracking(0);
 
     while ((bmds = QSIMPLEQ_FIRST(&block_mig_state.bmds_list)) != NULL) {
@@ -523,7 +553,9 @@ static int block_save_setup(QEMUFile *f, void *opaque)
     /* start track dirty blocks */
     set_dirty_tracking(1);
 
-    ret = flush_blks(f);
+    flush_blks(f);
+
+    ret = qemu_file_get_error(f);
     if (ret) {
         blk_mig_cleanup();
         return ret;
@@ -539,12 +571,13 @@ static int block_save_setup(QEMUFile *f, void *opaque)
 static int block_save_iterate(QEMUFile *f, void *opaque)
 {
     int ret;
-    int64_t last_ftell = qemu_ftell(f);
 
     DPRINTF("Enter save live iterate submitted %d transferred %d\n",
             block_mig_state.submitted, block_mig_state.transferred);
 
-    ret = flush_blks(f);
+    flush_blks(f);
+
+    ret = qemu_file_get_error(f);
     if (ret) {
         blk_mig_cleanup();
         return ret;
@@ -563,19 +596,16 @@ static int block_save_iterate(QEMUFile *f, void *opaque)
                 block_mig_state.bulk_completed = 1;
             }
         } else {
-            ret = blk_mig_save_dirty_block(f, 1);
-            if (ret != 0) {
+            if (blk_mig_save_dirty_block(f, 1) == 0) {
                 /* no more dirty blocks */
                 break;
             }
         }
     }
-    if (ret < 0) {
-        blk_mig_cleanup();
-        return ret;
-    }
 
-    ret = flush_blks(f);
+    flush_blks(f);
+
+    ret = qemu_file_get_error(f);
     if (ret) {
         blk_mig_cleanup();
         return ret;
@@ -583,7 +613,7 @@ static int block_save_iterate(QEMUFile *f, void *opaque)
 
     qemu_put_be64(f, BLK_MIG_FLAG_EOS);
 
-    return qemu_ftell(f) - last_ftell;
+    return is_stage2_completed();
 }
 
 static int block_save_complete(QEMUFile *f, void *opaque)
@@ -593,7 +623,9 @@ static int block_save_complete(QEMUFile *f, void *opaque)
     DPRINTF("Enter save live complete submitted %d transferred %d\n",
             block_mig_state.submitted, block_mig_state.transferred);
 
-    ret = flush_blks(f);
+    flush_blks(f);
+
+    ret = qemu_file_get_error(f);
     if (ret) {
         blk_mig_cleanup();
         return ret;
@@ -605,17 +637,19 @@ static int block_save_complete(QEMUFile *f, void *opaque)
        all async read completed */
     assert(block_mig_state.submitted == 0);
 
-    do {
-        ret = blk_mig_save_dirty_block(f, 0);
-    } while (ret == 0);
-
-    blk_mig_cleanup();
-    if (ret < 0) {
-        return ret;
+    while (blk_mig_save_dirty_block(f, 0) != 0) {
+        /* Do nothing */
     }
+    blk_mig_cleanup();
+
     /* report completion */
     qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
 
+    ret = qemu_file_get_error(f);
+    if (ret) {
+        return ret;
+    }
+
     DPRINTF("Block migration completed\n");
 
     qemu_put_be64(f, BLK_MIG_FLAG_EOS);
@@ -623,22 +657,6 @@ static int block_save_complete(QEMUFile *f, void *opaque)
     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 = 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;
-    }
-
-    DPRINTF("Enter save live pending  %" PRIu64 "\n", pending);
-    return pending;
-}
-
 static int block_load(QEMUFile *f, void *opaque, int version_id)
 {
     static int banner_printed;
@@ -704,7 +722,7 @@ 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);
@@ -735,7 +753,6 @@ SaveVMHandlers savevm_block_handlers = {
     .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,

block.h

@@ -1,16 +1,14 @@
 #ifndef BLOCK_H
 #define BLOCK_H
 
-#include "block/aio.h"
+#include "qemu-aio.h"
 #include "qemu-common.h"
-#include "qemu/option.h"
-#include "block/coroutine.h"
-#include "qapi/qmp/qobject.h"
-#include "qapi-types.h"
+#include "qemu-option.h"
+#include "qemu-coroutine.h"
+#include "qobject.h"
 
 /* block.c */
 typedef struct BlockDriver BlockDriver;
-typedef struct BlockJob BlockJob;
 
 typedef struct BlockDriverInfo {
     /* in bytes, 0 if irrelevant */
@@ -91,23 +89,21 @@ typedef struct BlockDevOps {
 #define BDRV_SECTOR_MASK   ~(BDRV_SECTOR_SIZE - 1)
 
 typedef enum {
-    BDRV_ACTION_REPORT, BDRV_ACTION_IGNORE, BDRV_ACTION_STOP
+    BLOCK_ERR_REPORT, BLOCK_ERR_IGNORE, BLOCK_ERR_STOP_ENOSPC,
+    BLOCK_ERR_STOP_ANY
 } BlockErrorAction;
 
-typedef QSIMPLEQ_HEAD(BlockReopenQueue, BlockReopenQueueEntry) BlockReopenQueue;
-
-typedef struct BDRVReopenState {
-    BlockDriverState *bs;
-    int flags;
-    void *opaque;
-} BDRVReopenState;
-
+typedef enum {
+    BDRV_ACTION_REPORT, BDRV_ACTION_IGNORE, BDRV_ACTION_STOP
+} BlockQMPEventAction;
 
 void bdrv_iostatus_enable(BlockDriverState *bs);
 void bdrv_iostatus_reset(BlockDriverState *bs);
 void bdrv_iostatus_disable(BlockDriverState *bs);
 bool bdrv_iostatus_is_enabled(const BlockDriverState *bs);
 void bdrv_iostatus_set_err(BlockDriverState *bs, int error);
+void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
+                               BlockQMPEventAction action, int is_read);
 void bdrv_info_print(Monitor *mon, const QObject *data);
 void bdrv_info(Monitor *mon, QObject **ret_data);
 void bdrv_stats_print(Monitor *mon, const QObject *data);
@@ -133,19 +129,9 @@ void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top);
 void bdrv_delete(BlockDriverState *bs);
 int bdrv_parse_cache_flags(const char *mode, int *flags);
 int bdrv_file_open(BlockDriverState **pbs, const char *filename, int flags);
-int bdrv_open_backing_file(BlockDriverState *bs);
 int bdrv_open(BlockDriverState *bs, const char *filename, int flags,
               BlockDriver *drv);
-BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
-                                    BlockDriverState *bs, int flags);
-int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp);
-int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp);
-int bdrv_reopen_prepare(BDRVReopenState *reopen_state,
-                        BlockReopenQueue *queue, Error **errp);
-void bdrv_reopen_commit(BDRVReopenState *reopen_state);
-void bdrv_reopen_abort(BDRVReopenState *reopen_state);
 void bdrv_close(BlockDriverState *bs);
-void bdrv_add_close_notifier(BlockDriverState *bs, Notifier *notify);
 int bdrv_attach_dev(BlockDriverState *bs, void *dev);
 void bdrv_attach_dev_nofail(BlockDriverState *bs, void *dev);
 void bdrv_detach_dev(BlockDriverState *bs, void *dev);
@@ -200,11 +186,6 @@ int bdrv_commit_all(void);
 int bdrv_change_backing_file(BlockDriverState *bs,
     const char *backing_file, const char *backing_fmt);
 void bdrv_register(BlockDriver *bdrv);
-int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top,
-                           BlockDriverState *base);
-BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
-                                    BlockDriverState *bs);
-BlockDriverState *bdrv_find_base(BlockDriverState *bs);
 
 
 typedef struct BdrvCheckResult {
@@ -279,12 +260,9 @@ int bdrv_has_zero_init(BlockDriverState *bs);
 int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
                       int *pnum);
 
-void bdrv_set_on_error(BlockDriverState *bs, BlockdevOnError on_read_error,
-                       BlockdevOnError on_write_error);
-BlockdevOnError bdrv_get_on_error(BlockDriverState *bs, bool is_read);
-BlockErrorAction bdrv_get_error_action(BlockDriverState *bs, bool is_read, int error);
-void bdrv_error_action(BlockDriverState *bs, BlockErrorAction action,
-                       bool is_read, int error);
+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);
@@ -309,18 +287,12 @@ int bdrv_get_flags(BlockDriverState *bs);
 int bdrv_write_compressed(BlockDriverState *bs, int64_t sector_num,
                           const uint8_t *buf, int nb_sectors);
 int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi);
-void bdrv_round_to_clusters(BlockDriverState *bs,
-                            int64_t sector_num, int nb_sectors,
-                            int64_t *cluster_sector_num,
-                            int *cluster_nb_sectors);
 
 const char *bdrv_get_encrypted_filename(BlockDriverState *bs);
 void bdrv_get_backing_filename(BlockDriverState *bs,
                                char *filename, int filename_size);
 void bdrv_get_full_backing_filename(BlockDriverState *bs,
                                     char *dest, size_t sz);
-BlockInfo *bdrv_query_info(BlockDriverState *s);
-BlockStats *bdrv_query_stats(const BlockDriverState *bs);
 int bdrv_can_snapshot(BlockDriverState *bs);
 int bdrv_is_snapshot(BlockDriverState *bs);
 BlockDriverState *bdrv_snapshots(void);
@@ -347,20 +319,19 @@ int bdrv_save_vmstate(BlockDriverState *bs, const uint8_t *buf,
 int bdrv_load_vmstate(BlockDriverState *bs, uint8_t *buf,
                       int64_t pos, int size);
 
-void bdrv_img_create(const char *filename, const char *fmt,
-                     const char *base_filename, const char *base_fmt,
-                     char *options, uint64_t img_size, int flags, Error **errp);
+int bdrv_img_create(const char *filename, const char *fmt,
+                    const char *base_filename, const char *base_fmt,
+                    char *options, uint64_t img_size, int flags);
 
 void bdrv_set_buffer_alignment(BlockDriverState *bs, int align);
 void *qemu_blockalign(BlockDriverState *bs, size_t size);
-bool bdrv_qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov);
 
-struct HBitmapIter;
-void bdrv_set_dirty_tracking(BlockDriverState *bs, int granularity);
+#define BDRV_SECTORS_PER_DIRTY_CHUNK 2048
+
+void bdrv_set_dirty_tracking(BlockDriverState *bs, int enable);
 int bdrv_get_dirty(BlockDriverState *bs, int64_t sector);
-void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors);
-void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors);
-void bdrv_dirty_iter_init(BlockDriverState *bs, struct HBitmapIter *hbi);
+void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector,
+                      int nr_sectors);
 int64_t bdrv_get_dirty_count(BlockDriverState *bs);
 
 void bdrv_enable_copy_on_read(BlockDriverState *bs);
@@ -369,15 +340,6 @@ void bdrv_disable_copy_on_read(BlockDriverState *bs);
 void bdrv_set_in_use(BlockDriverState *bs, int in_use);
 int bdrv_in_use(BlockDriverState *bs);
 
-#ifdef CONFIG_LINUX_AIO
-int raw_get_aio_fd(BlockDriverState *bs);
-#else
-static inline int raw_get_aio_fd(BlockDriverState *bs)
-{
-    return -ENOTSUP;
-}
-#endif
-
 enum BlockAcctType {
     BDRV_ACCT_READ,
     BDRV_ACCT_WRITE,
@@ -444,9 +406,4 @@ typedef enum {
 #define BLKDBG_EVENT(bs, evt) bdrv_debug_event(bs, evt)
 void bdrv_debug_event(BlockDriverState *bs, BlkDebugEvent event);
 
-int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event,
-                           const char *tag);
-int bdrv_debug_resume(BlockDriverState *bs, const char *tag);
-bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag);
-
 #endif

block/Makefile.objs

@@ -2,21 +2,10 @@ block-obj-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat
 block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
 block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-obj-y += qed-check.o
-block-obj-y += parallels.o blkdebug.o blkverify.o
-block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
+block-obj-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
+block-obj-y += stream.o
+block-obj-$(CONFIG_WIN32) += raw-win32.o
 block-obj-$(CONFIG_POSIX) += raw-posix.o
-block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
-
-ifeq ($(CONFIG_POSIX),y)
-block-obj-y += nbd.o sheepdog.o
 block-obj-$(CONFIG_LIBISCSI) += iscsi.o
 block-obj-$(CONFIG_CURL) += curl.o
 block-obj-$(CONFIG_RBD) += rbd.o
-block-obj-$(CONFIG_GLUSTERFS) += gluster.o
-endif
-
-common-obj-y += stream.o
-common-obj-y += commit.o
-common-obj-y += mirror.o
-
-$(obj)/curl.o: QEMU_CFLAGS+=$(CURL_CFLAGS)

block/blkdebug.c

@@ -23,17 +23,13 @@
  */
 
 #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 BDRVBlkdebugState {
     int state;
-    int new_state;
-
     QLIST_HEAD(, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
     QSIMPLEQ_HEAD(, BlkdebugRule) active_rules;
-    QLIST_HEAD(, BlkdebugSuspendedReq) suspended_reqs;
 } BDRVBlkdebugState;
 
 typedef struct BlkdebugAIOCB {
@@ -42,15 +38,9 @@ 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 +48,6 @@ static const AIOCBInfo blkdebug_aiocb_info = {
 enum {
     ACTION_INJECT_ERROR,
     ACTION_SET_STATE,
-    ACTION_SUSPEND,
 };
 
 typedef struct BlkdebugRule {
@@ -75,9 +64,6 @@ typedef struct BlkdebugRule {
         struct {
             int new_state;
         } set_state;
-        struct {
-            char *tag;
-        } suspend;
     } options;
     QLIST_ENTRY(BlkdebugRule) next;
     QSIMPLEQ_ENTRY(BlkdebugRule) active_next;
@@ -239,11 +225,6 @@ static int add_rule(QemuOpts *opts, void *opaque)
         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 */
@@ -252,32 +233,12 @@ static int add_rule(QemuOpts *opts, void *opaque)
     return 0;
 }
 
-static void remove_rule(BlkdebugRule *rule)
-{
-    switch (rule->action) {
-    case ACTION_INJECT_ERROR:
-    case ACTION_SET_STATE:
-        break;
-    case ACTION_SUSPEND:
-        g_free(rule->options.suspend.tag);
-        break;
-    }
-
-    QLIST_REMOVE(rule, next);
-    g_free(rule);
-}
-
 static int read_config(BDRVBlkdebugState *s, const char *filename)
 {
     FILE *f;
     int ret;
     struct add_rule_data d;
 
-    /* Allow usage without config file */
-    if (!*filename) {
-        return 0;
-    }
-
     f = fopen(filename, "r");
     if (f == NULL) {
         return -errno;
@@ -373,7 +334,7 @@ static BlockDriverAIOCB *inject_error(BlockDriverState *bs,
         return NULL;
     }
 
-    acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&blkdebug_aio_pool, bs, cb, opaque);
     acb->ret = -error;
 
     bh = qemu_bh_new(error_callback_bh, acb);
@@ -427,7 +388,6 @@ static BlockDriverAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
     return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
 }
 
-
 static void blkdebug_close(BlockDriverState *bs)
 {
     BDRVBlkdebugState *s = bs->opaque;
@@ -436,39 +396,19 @@ static void blkdebug_close(BlockDriverState *bs)
 
     for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
         QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
-            remove_rule(rule);
+            QLIST_REMOVE(rule, next);
+            g_free(rule);
         }
     }
 }
 
-static void suspend_request(BlockDriverState *bs, BlkdebugRule *rule)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq r;
-
-    r = (BlkdebugSuspendedReq) {
-        .co         = qemu_coroutine_self(),
-        .tag        = g_strdup(rule->options.suspend.tag),
-    };
-
-    remove_rule(rule);
-    QLIST_INSERT_HEAD(&s->suspended_reqs, &r, next);
-
-    printf("blkdebug: Suspended request '%s'\n", r.tag);
-    qemu_coroutine_yield();
-    printf("blkdebug: Resuming request '%s'\n", r.tag);
-
-    QLIST_REMOVE(&r, next);
-    g_free(r.tag);
-}
-
 static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
-    bool injected)
+    int old_state, bool injected)
 {
     BDRVBlkdebugState *s = bs->opaque;
 
     /* Only process rules for the current state */
-    if (rule->state && rule->state != s->state) {
+    if (rule->state && rule->state != old_state) {
         return injected;
     }
 
@@ -483,11 +423,7 @@ static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
         break;
 
     case ACTION_SET_STATE:
-        s->new_state = rule->options.set_state.new_state;
-        break;
-
-    case ACTION_SUSPEND:
-        suspend_request(bs, rule);
+        s->state = rule->options.set_state.new_state;
         break;
     }
     return injected;
@@ -496,70 +432,16 @@ static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
 static void blkdebug_debug_event(BlockDriverState *bs, BlkDebugEvent event)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    struct BlkdebugRule *rule, *next;
+    struct BlkdebugRule *rule;
+    int old_state = s->state;
     bool injected;
 
     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) {
+        injected = process_rule(bs, rule, old_state, injected);
     }
-    s->state = s->new_state;
-}
-
-static int blkdebug_debug_breakpoint(BlockDriverState *bs, const char *event,
-                                     const char *tag)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    struct BlkdebugRule *rule;
-    BlkDebugEvent blkdebug_event;
-
-    if (get_event_by_name(event, &blkdebug_event) < 0) {
-        return -ENOENT;
-    }
-
-
-    rule = g_malloc(sizeof(*rule));
-    *rule = (struct BlkdebugRule) {
-        .event  = blkdebug_event,
-        .action = ACTION_SUSPEND,
-        .state  = 0,
-        .options.suspend.tag = g_strdup(tag),
-    };
-
-    QLIST_INSERT_HEAD(&s->rules[blkdebug_event], rule, next);
-
-    return 0;
-}
-
-static int blkdebug_debug_resume(BlockDriverState *bs, const char *tag)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq *r;
-
-    QLIST_FOREACH(r, &s->suspended_reqs, next) {
-        if (!strcmp(r->tag, tag)) {
-            qemu_coroutine_enter(r->co, NULL);
-            return 0;
-        }
-    }
-    return -ENOENT;
-}
-
-
-static bool blkdebug_debug_is_suspended(BlockDriverState *bs, const char *tag)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugSuspendedReq *r;
-
-    QLIST_FOREACH(r, &s->suspended_reqs, next) {
-        if (!strcmp(r->tag, tag)) {
-            return true;
-        }
-    }
-    return false;
 }
 
 static int64_t blkdebug_getlength(BlockDriverState *bs)
@@ -580,10 +462,7 @@ static BlockDriver bdrv_blkdebug = {
     .bdrv_aio_readv     = blkdebug_aio_readv,
     .bdrv_aio_writev    = blkdebug_aio_writev,
 
-    .bdrv_debug_event           = blkdebug_debug_event,
-    .bdrv_debug_breakpoint      = blkdebug_debug_breakpoint,
-    .bdrv_debug_resume          = blkdebug_debug_resume,
-    .bdrv_debug_is_suspended    = blkdebug_debug_is_suspended,
+    .bdrv_debug_event   = blkdebug_debug_event,
 };
 
 static void bdrv_blkdebug_init(void)

block/blkverify.c

@@ -8,8 +8,8 @@
  */
 
 #include <stdarg.h>
-#include "qemu/sockets.h" /* for EINPROGRESS on Windows */
-#include "block/block_int.h"
+#include "qemu_socket.h" /* for EINPROGRESS on Windows */
+#include "block_int.h"
 
 typedef struct {
     BlockDriverState *test_file;
@@ -48,7 +48,7 @@ static void blkverify_aio_cancel(BlockDriverAIOCB *blockacb)
     }
 }
 
-static const AIOCBInfo blkverify_aiocb_info = {
+static AIOPool blkverify_aio_pool = {
     .aiocb_size         = sizeof(BlkverifyAIOCB),
     .cancel             = blkverify_aio_cancel,
 };
@@ -233,7 +233,7 @@ static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
                                          BlockDriverCompletionFunc *cb,
                                          void *opaque)
 {
-    BlkverifyAIOCB *acb = qemu_aio_get(&blkverify_aiocb_info, bs, cb, opaque);
+    BlkverifyAIOCB *acb = qemu_aio_get(&blkverify_aio_pool, bs, cb, opaque);
 
     acb->bh = NULL;
     acb->is_write = is_write;

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"
 
 /**************************************************************/
 
@@ -114,13 +114,11 @@ static int bochs_open(BlockDriverState *bs, int flags)
     int i;
     struct bochs_header bochs;
     struct bochs_header_v1 header_v1;
-    int ret;
 
     bs->read_only = 1; // no write support yet
 
-    ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));
-    if (ret < 0) {
-        return ret;
+    if (bdrv_pread(bs->file, 0, &bochs, sizeof(bochs)) != sizeof(bochs)) {
+        goto fail;
     }
 
     if (strcmp(bochs.magic, HEADER_MAGIC) ||
@@ -128,7 +126,7 @@ static int bochs_open(BlockDriverState *bs, int flags)
         strcmp(bochs.subtype, GROWING_TYPE) ||
 	((le32_to_cpu(bochs.version) != HEADER_VERSION) &&
 	(le32_to_cpu(bochs.version) != HEADER_V1))) {
-        return -EMEDIUMTYPE;
+        goto fail;
     }
 
     if (le32_to_cpu(bochs.version) == HEADER_V1) {
@@ -140,13 +138,9 @@ static int bochs_open(BlockDriverState *bs, int flags)
 
     s->catalog_size = le32_to_cpu(bochs.extra.redolog.catalog);
     s->catalog_bitmap = g_malloc(s->catalog_size * 4);
-
-    ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
-                     s->catalog_size * 4);
-    if (ret < 0) {
-        goto fail;
-    }
-
+    if (bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
+                   s->catalog_size * 4) != s->catalog_size * 4)
+	goto fail;
     for (i = 0; i < s->catalog_size; i++)
 	le32_to_cpus(&s->catalog_bitmap[i]);
 
@@ -159,10 +153,8 @@ static int bochs_open(BlockDriverState *bs, int flags)
 
     qemu_co_mutex_init(&s->lock);
     return 0;
-
-fail:
-    g_free(s->catalog_bitmap);
-    return ret;
+ fail:
+    return -1;
 }
 
 static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)

block/cloop.c

@@ -22,8 +22,8 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 #include <zlib.h>
 
 typedef struct BDRVCloopState {
@@ -57,32 +57,27 @@ static int cloop_open(BlockDriverState *bs, int flags)
 {
     BDRVCloopState *s = bs->opaque;
     uint32_t offsets_size, max_compressed_block_size = 1, i;
-    int ret;
 
     bs->read_only = 1;
 
     /* read header */
-    ret = bdrv_pread(bs->file, 128, &s->block_size, 4);
-    if (ret < 0) {
-        return ret;
+    if (bdrv_pread(bs->file, 128, &s->block_size, 4) < 4) {
+        goto cloop_close;
     }
     s->block_size = be32_to_cpu(s->block_size);
 
-    ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4);
-    if (ret < 0) {
-        return ret;
+    if (bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4) < 4) {
+        goto cloop_close;
     }
     s->n_blocks = be32_to_cpu(s->n_blocks);
 
     /* read offsets */
     offsets_size = s->n_blocks * sizeof(uint64_t);
     s->offsets = g_malloc(offsets_size);
-
-    ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size);
-    if (ret < 0) {
-        goto fail;
+    if (bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size) <
+            offsets_size) {
+        goto cloop_close;
     }
-
     for(i=0;i<s->n_blocks;i++) {
         s->offsets[i] = be64_to_cpu(s->offsets[i]);
         if (i > 0) {
@@ -97,8 +92,7 @@ static int cloop_open(BlockDriverState *bs, int flags)
     s->compressed_block = g_malloc(max_compressed_block_size + 1);
     s->uncompressed_block = g_malloc(s->block_size);
     if (inflateInit(&s->zstream) != Z_OK) {
-        ret = -EINVAL;
-        goto fail;
+        goto cloop_close;
     }
     s->current_block = s->n_blocks;
 
@@ -107,11 +101,8 @@ static int cloop_open(BlockDriverState *bs, int flags)
     qemu_co_mutex_init(&s->lock);
     return 0;
 
-fail:
-    g_free(s->offsets);
-    g_free(s->compressed_block);
-    g_free(s->uncompressed_block);
-    return ret;
+cloop_close:
+    return -1;
 }
 
 static inline int cloop_read_block(BlockDriverState *bs, int block_num)

block/commit.c

@@ -1,258 +0,0 @@
-/*
- * Live block commit
- *
- * Copyright Red Hat, Inc. 2012
- *
- * Authors:
- *  Jeff Cody   <jcody@redhat.com>
- *  Based on stream.c by Stefan Hajnoczi
- *
- * This work is licensed under the terms of the GNU LGPL, version 2 or later.
- * See the COPYING.LIB file in the top-level directory.
- *
- */
-
-#include "trace.h"
-#include "block/block_int.h"
-#include "block/blockjob.h"
-#include "qemu/ratelimit.h"
-
-enum {
-    /*
-     * Size of data buffer for populating the image file.  This should be large
-     * enough to process multiple clusters in a single call, so that populating
-     * contiguous regions of the image is efficient.
-     */
-    COMMIT_BUFFER_SIZE = 512 * 1024, /* in bytes */
-};
-
-#define SLICE_TIME 100000000ULL /* ns */
-
-typedef struct CommitBlockJob {
-    BlockJob common;
-    RateLimit limit;
-    BlockDriverState *active;
-    BlockDriverState *top;
-    BlockDriverState *base;
-    BlockdevOnError on_error;
-    int base_flags;
-    int orig_overlay_flags;
-} CommitBlockJob;
-
-static int coroutine_fn commit_populate(BlockDriverState *bs,
-                                        BlockDriverState *base,
-                                        int64_t sector_num, int nb_sectors,
-                                        void *buf)
-{
-    int ret = 0;
-
-    ret = bdrv_read(bs, sector_num, buf, nb_sectors);
-    if (ret) {
-        return ret;
-    }
-
-    ret = bdrv_write(base, sector_num, buf, nb_sectors);
-    if (ret) {
-        return ret;
-    }
-
-    return 0;
-}
-
-static void coroutine_fn commit_run(void *opaque)
-{
-    CommitBlockJob *s = opaque;
-    BlockDriverState *active = s->active;
-    BlockDriverState *top = s->top;
-    BlockDriverState *base = s->base;
-    BlockDriverState *overlay_bs;
-    int64_t sector_num, end;
-    int ret = 0;
-    int n = 0;
-    void *buf;
-    int bytes_written = 0;
-    int64_t base_len;
-
-    ret = s->common.len = bdrv_getlength(top);
-
-
-    if (s->common.len < 0) {
-        goto exit_restore_reopen;
-    }
-
-    ret = base_len = bdrv_getlength(base);
-    if (base_len < 0) {
-        goto exit_restore_reopen;
-    }
-
-    if (base_len < s->common.len) {
-        ret = bdrv_truncate(base, s->common.len);
-        if (ret) {
-            goto exit_restore_reopen;
-        }
-    }
-
-    end = s->common.len >> BDRV_SECTOR_BITS;
-    buf = qemu_blockalign(top, COMMIT_BUFFER_SIZE);
-
-    for (sector_num = 0; sector_num < end; sector_num += n) {
-        uint64_t delay_ns = 0;
-        bool copy;
-
-wait:
-        /* Note that even when no rate limit is applied we need to yield
-         * with no pending I/O here so that bdrv_drain_all() returns.
-         */
-        block_job_sleep_ns(&s->common, rt_clock, delay_ns);
-        if (block_job_is_cancelled(&s->common)) {
-            break;
-        }
-        /* Copy if allocated above the base */
-        ret = bdrv_co_is_allocated_above(top, base, sector_num,
-                                         COMMIT_BUFFER_SIZE / BDRV_SECTOR_SIZE,
-                                         &n);
-        copy = (ret == 1);
-        trace_commit_one_iteration(s, sector_num, n, ret);
-        if (copy) {
-            if (s->common.speed) {
-                delay_ns = ratelimit_calculate_delay(&s->limit, n);
-                if (delay_ns > 0) {
-                    goto wait;
-                }
-            }
-            ret = commit_populate(top, base, sector_num, n, buf);
-            bytes_written += n * BDRV_SECTOR_SIZE;
-        }
-        if (ret < 0) {
-            if (s->on_error == BLOCKDEV_ON_ERROR_STOP ||
-                s->on_error == BLOCKDEV_ON_ERROR_REPORT||
-                (s->on_error == BLOCKDEV_ON_ERROR_ENOSPC && ret == -ENOSPC)) {
-                goto exit_free_buf;
-            } else {
-                n = 0;
-                continue;
-            }
-        }
-        /* Publish progress */
-        s->common.offset += n * BDRV_SECTOR_SIZE;
-    }
-
-    ret = 0;
-
-    if (!block_job_is_cancelled(&s->common) && sector_num == end) {
-        /* success */
-        ret = bdrv_drop_intermediate(active, top, base);
-    }
-
-exit_free_buf:
-    qemu_vfree(buf);
-
-exit_restore_reopen:
-    /* restore base open flags here if appropriate (e.g., change the base back
-     * to r/o). These reopens do not need to be atomic, since we won't abort
-     * even on failure here */
-    if (s->base_flags != bdrv_get_flags(base)) {
-        bdrv_reopen(base, s->base_flags, NULL);
-    }
-    overlay_bs = bdrv_find_overlay(active, top);
-    if (overlay_bs && s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
-        bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
-    }
-
-    block_job_completed(&s->common, ret);
-}
-
-static void commit_set_speed(BlockJob *job, int64_t speed, Error **errp)
-{
-    CommitBlockJob *s = container_of(job, CommitBlockJob, common);
-
-    if (speed < 0) {
-        error_set(errp, QERR_INVALID_PARAMETER, "speed");
-        return;
-    }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
-}
-
-static BlockJobType commit_job_type = {
-    .instance_size = sizeof(CommitBlockJob),
-    .job_type      = "commit",
-    .set_speed     = commit_set_speed,
-};
-
-void commit_start(BlockDriverState *bs, BlockDriverState *base,
-                  BlockDriverState *top, int64_t speed,
-                  BlockdevOnError on_error, BlockDriverCompletionFunc *cb,
-                  void *opaque, Error **errp)
-{
-    CommitBlockJob *s;
-    BlockReopenQueue *reopen_queue = NULL;
-    int orig_overlay_flags;
-    int orig_base_flags;
-    BlockDriverState *overlay_bs;
-    Error *local_err = NULL;
-
-    if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
-         on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
-        error_set(errp, QERR_INVALID_PARAMETER_COMBINATION);
-        return;
-    }
-
-    /* Once we support top == active layer, remove this check */
-    if (top == bs) {
-        error_setg(errp,
-                   "Top image as the active layer is currently unsupported");
-        return;
-    }
-
-    if (top == base) {
-        error_setg(errp, "Invalid files for merge: top and base are the same");
-        return;
-    }
-
-    overlay_bs = bdrv_find_overlay(bs, top);
-
-    if (overlay_bs == NULL) {
-        error_setg(errp, "Could not find overlay image for %s:", top->filename);
-        return;
-    }
-
-    orig_base_flags    = bdrv_get_flags(base);
-    orig_overlay_flags = bdrv_get_flags(overlay_bs);
-
-    /* convert base & overlay_bs to r/w, if necessary */
-    if (!(orig_base_flags & BDRV_O_RDWR)) {
-        reopen_queue = bdrv_reopen_queue(reopen_queue, base,
-                                         orig_base_flags | BDRV_O_RDWR);
-    }
-    if (!(orig_overlay_flags & BDRV_O_RDWR)) {
-        reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs,
-                                         orig_overlay_flags | BDRV_O_RDWR);
-    }
-    if (reopen_queue) {
-        bdrv_reopen_multiple(reopen_queue, &local_err);
-        if (local_err != NULL) {
-            error_propagate(errp, local_err);
-            return;
-        }
-    }
-
-
-    s = block_job_create(&commit_job_type, bs, speed, cb, opaque, errp);
-    if (!s) {
-        return;
-    }
-
-    s->base   = base;
-    s->top    = top;
-    s->active = bs;
-
-    s->base_flags          = orig_base_flags;
-    s->orig_overlay_flags  = orig_overlay_flags;
-
-    s->on_error = on_error;
-    s->common.co = qemu_coroutine_create(commit_run);
-
-    trace_commit_start(bs, base, top, s, s->common.co, opaque);
-    qemu_coroutine_enter(s->common.co, s);
-}

block/cow.c

@@ -22,8 +22,8 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 
 /**************************************************************/
 /* COW block driver using file system holes */
@@ -73,7 +73,7 @@ static int cow_open(BlockDriverState *bs, int flags)
     }
 
     if (be32_to_cpu(cow_header.magic) != COW_MAGIC) {
-        ret = -EMEDIUMTYPE;
+        ret = -EINVAL;
         goto fail;
     }
 

block/curl.c

@@ -22,7 +22,7 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include <curl/curl.h>
 
 // #define DEBUG
@@ -34,10 +34,6 @@
 #define DPRINTF(fmt, ...) do { } while (0)
 #endif
 
-#define PROTOCOLS (CURLPROTO_HTTP | CURLPROTO_HTTPS | \
-                   CURLPROTO_FTP | CURLPROTO_FTPS | \
-                   CURLPROTO_TFTP)
-
 #define CURL_NUM_STATES 8
 #define CURL_NUM_ACB    8
 #define SECTOR_SIZE     512
@@ -306,17 +302,6 @@ static CURLState *curl_init_state(BDRVCURLState *s)
     curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
     curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
 
-    /* Restrict supported protocols to avoid security issues in the more
-     * obscure protocols.  For example, do not allow POP3/SMTP/IMAP see
-     * CVE-2013-0249.
-     *
-     * Restricting protocols is only supported from 7.19.4 upwards.
-     */
-#if LIBCURL_VERSION_NUM >= 0x071304
-    curl_easy_setopt(state->curl, CURLOPT_PROTOCOLS, PROTOCOLS);
-    curl_easy_setopt(state->curl, CURLOPT_REDIR_PROTOCOLS, PROTOCOLS);
-#endif
-
 #ifdef DEBUG_VERBOSE
     curl_easy_setopt(state->curl, CURLOPT_VERBOSE, 1);
 #endif
@@ -453,7 +438,7 @@ static void curl_aio_cancel(BlockDriverAIOCB *blockacb)
     // Do we have to implement canceling? Seems to work without...
 }
 
-static const AIOCBInfo curl_aiocb_info = {
+static AIOPool curl_aio_pool = {
     .aiocb_size         = sizeof(CURLAIOCB),
     .cancel             = curl_aio_cancel,
 };
@@ -520,7 +505,7 @@ static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
 {
     CURLAIOCB *acb;
 
-    acb = qemu_aio_get(&curl_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&curl_aio_pool, bs, cb, opaque);
 
     acb->qiov = qiov;
     acb->sector_num = sector_num;

block/dmg.c

@@ -22,9 +22,9 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/bswap.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "bswap.h"
+#include "module.h"
 #include <zlib.h>
 
 typedef struct BDRVDMGState {
@@ -57,42 +57,29 @@ static int dmg_probe(const uint8_t *buf, int buf_size, const char *filename)
     return 0;
 }
 
-static int read_uint64(BlockDriverState *bs, int64_t offset, uint64_t *result)
+static off_t read_off(BlockDriverState *bs, int64_t offset)
 {
-    uint64_t buffer;
-    int ret;
-
-    ret = bdrv_pread(bs->file, offset, &buffer, 8);
-    if (ret < 0) {
-        return ret;
-    }
-
-    *result = be64_to_cpu(buffer);
-    return 0;
+	uint64_t buffer;
+	if (bdrv_pread(bs->file, offset, &buffer, 8) < 8)
+		return 0;
+	return be64_to_cpu(buffer);
 }
 
-static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result)
+static off_t read_uint32(BlockDriverState *bs, int64_t offset)
 {
-    uint32_t buffer;
-    int ret;
-
-    ret = bdrv_pread(bs->file, offset, &buffer, 4);
-    if (ret < 0) {
-        return ret;
-    }
-
-    *result = be32_to_cpu(buffer);
-    return 0;
+	uint32_t buffer;
+	if (bdrv_pread(bs->file, offset, &buffer, 4) < 4)
+		return 0;
+	return be32_to_cpu(buffer);
 }
 
 static int dmg_open(BlockDriverState *bs, int flags)
 {
     BDRVDMGState *s = bs->opaque;
-    uint64_t info_begin,info_end,last_in_offset,last_out_offset;
-    uint32_t count, tmp;
+    off_t info_begin,info_end,last_in_offset,last_out_offset;
+    uint32_t count;
     uint32_t max_compressed_size=1,max_sectors_per_chunk=1,i;
     int64_t offset;
-    int ret;
 
     bs->read_only = 1;
     s->n_chunks = 0;
@@ -101,32 +88,21 @@ static int dmg_open(BlockDriverState *bs, 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;
@@ -138,20 +114,12 @@ static int dmg_open(BlockDriverState *bs, int flags)
     while (offset < info_end) {
         uint32_t type;
 
-        ret = read_uint32(bs, offset, &count);
-        if (ret < 0) {
-            goto fail;
-        } else if (count == 0) {
-            ret = -EINVAL;
-            goto fail;
-        }
+	count = read_uint32(bs, offset);
+	if(count==0)
+	    goto fail;
         offset += 4;
 
-        ret = read_uint32(bs, offset, &type);
-        if (ret < 0) {
-            goto fail;
-        }
-
+	type = read_uint32(bs, offset);
 	if (type == 0x6d697368 && count >= 244) {
 	    int new_size, chunk_count;
 
@@ -166,11 +134,8 @@ static int dmg_open(BlockDriverState *bs, int flags)
 	    s->sectors = g_realloc(s->sectors, new_size);
 	    s->sectorcounts = g_realloc(s->sectorcounts, new_size);
 
-            for (i = s->n_chunks; i < s->n_chunks + chunk_count; i++) {
-                ret = read_uint32(bs, offset, &s->types[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
+	    for(i=s->n_chunks;i<s->n_chunks+chunk_count;i++) {
+		s->types[i] = read_uint32(bs, offset);
 		offset += 4;
 		if(s->types[i]!=0x80000005 && s->types[i]!=1 && s->types[i]!=2) {
 		    if(s->types[i]==0xffffffff) {
@@ -184,31 +149,17 @@ static int dmg_open(BlockDriverState *bs, int flags)
 		}
 		offset += 4;
 
-                ret = read_uint64(bs, offset, &s->sectors[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                s->sectors[i] += last_out_offset;
-                offset += 8;
+		s->sectors[i] = last_out_offset+read_off(bs, offset);
+		offset += 8;
 
-                ret = read_uint64(bs, offset, &s->sectorcounts[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                offset += 8;
+		s->sectorcounts[i] = read_off(bs, offset);
+		offset += 8;
 
-                ret = read_uint64(bs, offset, &s->offsets[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                s->offsets[i] += last_in_offset;
-                offset += 8;
+		s->offsets[i] = last_in_offset+read_off(bs, offset);
+		offset += 8;
 
-                ret = read_uint64(bs, offset, &s->lengths[i]);
-                if (ret < 0) {
-                    goto fail;
-                }
-                offset += 8;
+		s->lengths[i] = read_off(bs, offset);
+		offset += 8;
 
 		if(s->lengths[i]>max_compressed_size)
 		    max_compressed_size = s->lengths[i];
@@ -222,25 +173,15 @@ static int dmg_open(BlockDriverState *bs, int flags)
     /* initialize zlib engine */
     s->compressed_chunk = g_malloc(max_compressed_size+1);
     s->uncompressed_chunk = g_malloc(512*max_sectors_per_chunk);
-    if(inflateInit(&s->zstream) != Z_OK) {
-        ret = -EINVAL;
-        goto fail;
-    }
+    if(inflateInit(&s->zstream) != Z_OK)
+	goto fail;
 
     s->current_chunk = s->n_chunks;
 
     qemu_co_mutex_init(&s->lock);
     return 0;
-
 fail:
-    g_free(s->types);
-    g_free(s->offsets);
-    g_free(s->lengths);
-    g_free(s->sectors);
-    g_free(s->sectorcounts);
-    g_free(s->compressed_chunk);
-    g_free(s->uncompressed_chunk);
-    return ret;
+    return -1;
 }
 
 static inline int is_sector_in_chunk(BDRVDMGState* s,
@@ -355,15 +296,15 @@ static coroutine_fn int dmg_co_read(BlockDriverState *bs, int64_t sector_num,
 static void dmg_close(BlockDriverState *bs)
 {
     BDRVDMGState *s = bs->opaque;
-
-    g_free(s->types);
-    g_free(s->offsets);
-    g_free(s->lengths);
-    g_free(s->sectors);
-    g_free(s->sectorcounts);
-    g_free(s->compressed_chunk);
-    g_free(s->uncompressed_chunk);
-
+    if(s->n_chunks>0) {
+	free(s->types);
+	free(s->offsets);
+	free(s->lengths);
+	free(s->sectors);
+	free(s->sectorcounts);
+    }
+    free(s->compressed_chunk);
+    free(s->uncompressed_chunk);
     inflateEnd(&s->zstream);
 }
 

block/gluster.c

@@ -1,624 +0,0 @@
-/*
- * GlusterFS backend for QEMU
- *
- * Copyright (C) 2012 Bharata B Rao <bharata@linux.vnet.ibm.com>
- *
- * Pipe handling mechanism in AIO implementation is derived from
- * block/rbd.c. Hence,
- *
- * Copyright (C) 2010-2011 Christian Brunner <chb@muc.de>,
- *                         Josh Durgin <josh.durgin@dreamhost.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
- * Contributions after 2012-01-13 are licensed under the terms of the
- * GNU GPL, version 2 or (at your option) any later version.
- */
-#include <glusterfs/api/glfs.h>
-#include "block/block_int.h"
-#include "qemu/sockets.h"
-#include "qemu/uri.h"
-
-typedef struct GlusterAIOCB {
-    BlockDriverAIOCB common;
-    int64_t size;
-    int ret;
-    bool *finished;
-    QEMUBH *bh;
-} GlusterAIOCB;
-
-typedef struct BDRVGlusterState {
-    struct glfs *glfs;
-    int fds[2];
-    struct glfs_fd *fd;
-    int qemu_aio_count;
-    int event_reader_pos;
-    GlusterAIOCB *event_acb;
-} BDRVGlusterState;
-
-#define GLUSTER_FD_READ  0
-#define GLUSTER_FD_WRITE 1
-
-typedef struct GlusterConf {
-    char *server;
-    int port;
-    char *volname;
-    char *image;
-    char *transport;
-} GlusterConf;
-
-static void qemu_gluster_gconf_free(GlusterConf *gconf)
-{
-    g_free(gconf->server);
-    g_free(gconf->volname);
-    g_free(gconf->image);
-    g_free(gconf->transport);
-    g_free(gconf);
-}
-
-static int parse_volume_options(GlusterConf *gconf, char *path)
-{
-    char *p, *q;
-
-    if (!path) {
-        return -EINVAL;
-    }
-
-    /* volume */
-    p = q = path + strspn(path, "/");
-    p += strcspn(p, "/");
-    if (*p == '\0') {
-        return -EINVAL;
-    }
-    gconf->volname = g_strndup(q, p - q);
-
-    /* image */
-    p += strspn(p, "/");
-    if (*p == '\0') {
-        return -EINVAL;
-    }
-    gconf->image = g_strdup(p);
-    return 0;
-}
-
-/*
- * file=gluster[+transport]://[server[:port]]/volname/image[?socket=...]
- *
- * 'gluster' is the protocol.
- *
- * 'transport' specifies the transport type used to connect to gluster
- * management daemon (glusterd). Valid transport types are
- * tcp, unix and rdma. If a transport type isn't specified, then tcp
- * type is assumed.
- *
- * 'server' specifies the server where the volume file specification for
- * the given volume resides. This can be either hostname, ipv4 address
- * or ipv6 address. ipv6 address needs to be within square brackets [ ].
- * If transport type is 'unix', then 'server' field should not be specifed.
- * The 'socket' field needs to be populated with the path to unix domain
- * socket.
- *
- * 'port' is the port number on which glusterd is listening. This is optional
- * and if not specified, QEMU will send 0 which will make gluster to use the
- * default port. If the transport type is unix, then 'port' should not be
- * specified.
- *
- * 'volname' is the name of the gluster volume which contains the VM image.
- *
- * 'image' is the path to the actual VM image that resides on gluster volume.
- *
- * Examples:
- *
- * file=gluster://1.2.3.4/testvol/a.img
- * file=gluster+tcp://1.2.3.4/testvol/a.img
- * file=gluster+tcp://1.2.3.4:24007/testvol/dir/a.img
- * file=gluster+tcp://[1:2:3:4:5:6:7:8]/testvol/dir/a.img
- * file=gluster+tcp://[1:2:3:4:5:6:7:8]:24007/testvol/dir/a.img
- * file=gluster+tcp://server.domain.com:24007/testvol/dir/a.img
- * file=gluster+unix:///testvol/dir/a.img?socket=/tmp/glusterd.socket
- * file=gluster+rdma://1.2.3.4:24007/testvol/a.img
- */
-static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename)
-{
-    URI *uri;
-    QueryParams *qp = NULL;
-    bool is_unix = false;
-    int ret = 0;
-
-    uri = uri_parse(filename);
-    if (!uri) {
-        return -EINVAL;
-    }
-
-    /* transport */
-    if (!strcmp(uri->scheme, "gluster")) {
-        gconf->transport = g_strdup("tcp");
-    } else if (!strcmp(uri->scheme, "gluster+tcp")) {
-        gconf->transport = g_strdup("tcp");
-    } else if (!strcmp(uri->scheme, "gluster+unix")) {
-        gconf->transport = g_strdup("unix");
-        is_unix = true;
-    } else if (!strcmp(uri->scheme, "gluster+rdma")) {
-        gconf->transport = g_strdup("rdma");
-    } else {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    ret = parse_volume_options(gconf, uri->path);
-    if (ret < 0) {
-        goto out;
-    }
-
-    qp = query_params_parse(uri->query);
-    if (qp->n > 1 || (is_unix && !qp->n) || (!is_unix && qp->n)) {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    if (is_unix) {
-        if (uri->server || uri->port) {
-            ret = -EINVAL;
-            goto out;
-        }
-        if (strcmp(qp->p[0].name, "socket")) {
-            ret = -EINVAL;
-            goto out;
-        }
-        gconf->server = g_strdup(qp->p[0].value);
-    } else {
-        gconf->server = g_strdup(uri->server);
-        gconf->port = uri->port;
-    }
-
-out:
-    if (qp) {
-        query_params_free(qp);
-    }
-    uri_free(uri);
-    return ret;
-}
-
-static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename)
-{
-    struct glfs *glfs = NULL;
-    int ret;
-    int old_errno;
-
-    ret = qemu_gluster_parseuri(gconf, filename);
-    if (ret < 0) {
-        error_report("Usage: file=gluster[+transport]://[server[:port]]/"
-            "volname/image[?socket=...]");
-        errno = -ret;
-        goto out;
-    }
-
-    glfs = glfs_new(gconf->volname);
-    if (!glfs) {
-        goto out;
-    }
-
-    ret = glfs_set_volfile_server(glfs, gconf->transport, gconf->server,
-            gconf->port);
-    if (ret < 0) {
-        goto out;
-    }
-
-    /*
-     * TODO: Use GF_LOG_ERROR instead of hard code value of 4 here when
-     * GlusterFS makes GF_LOG_* macros available to libgfapi users.
-     */
-    ret = glfs_set_logging(glfs, "-", 4);
-    if (ret < 0) {
-        goto out;
-    }
-
-    ret = glfs_init(glfs);
-    if (ret) {
-        error_report("Gluster connection failed for server=%s port=%d "
-             "volume=%s image=%s transport=%s", gconf->server, gconf->port,
-             gconf->volname, gconf->image, gconf->transport);
-        goto out;
-    }
-    return glfs;
-
-out:
-    if (glfs) {
-        old_errno = errno;
-        glfs_fini(glfs);
-        errno = old_errno;
-    }
-    return NULL;
-}
-
-static void qemu_gluster_complete_aio(GlusterAIOCB *acb, BDRVGlusterState *s)
-{
-    int ret;
-    bool *finished = acb->finished;
-    BlockDriverCompletionFunc *cb = acb->common.cb;
-    void *opaque = acb->common.opaque;
-
-    if (!acb->ret || acb->ret == acb->size) {
-        ret = 0; /* Success */
-    } else if (acb->ret < 0) {
-        ret = acb->ret; /* Read/Write failed */
-    } else {
-        ret = -EIO; /* Partial read/write - fail it */
-    }
-
-    s->qemu_aio_count--;
-    qemu_aio_release(acb);
-    cb(opaque, ret);
-    if (finished) {
-        *finished = true;
-    }
-}
-
-static void qemu_gluster_aio_event_reader(void *opaque)
-{
-    BDRVGlusterState *s = opaque;
-    ssize_t ret;
-
-    do {
-        char *p = (char *)&s->event_acb;
-
-        ret = read(s->fds[GLUSTER_FD_READ], p + s->event_reader_pos,
-                   sizeof(s->event_acb) - s->event_reader_pos);
-        if (ret > 0) {
-            s->event_reader_pos += ret;
-            if (s->event_reader_pos == sizeof(s->event_acb)) {
-                s->event_reader_pos = 0;
-                qemu_gluster_complete_aio(s->event_acb, s);
-            }
-        }
-    } while (ret < 0 && errno == EINTR);
-}
-
-static int qemu_gluster_aio_flush_cb(void *opaque)
-{
-    BDRVGlusterState *s = opaque;
-
-    return (s->qemu_aio_count > 0);
-}
-
-static int qemu_gluster_open(BlockDriverState *bs, const char *filename,
-    int bdrv_flags)
-{
-    BDRVGlusterState *s = bs->opaque;
-    int open_flags = O_BINARY;
-    int ret = 0;
-    GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
-
-    s->glfs = qemu_gluster_init(gconf, filename);
-    if (!s->glfs) {
-        ret = -errno;
-        goto out;
-    }
-
-    if (bdrv_flags & BDRV_O_RDWR) {
-        open_flags |= O_RDWR;
-    } else {
-        open_flags |= O_RDONLY;
-    }
-
-    if ((bdrv_flags & BDRV_O_NOCACHE)) {
-        open_flags |= O_DIRECT;
-    }
-
-    s->fd = glfs_open(s->glfs, gconf->image, open_flags);
-    if (!s->fd) {
-        ret = -errno;
-        goto out;
-    }
-
-    ret = qemu_pipe(s->fds);
-    if (ret < 0) {
-        ret = -errno;
-        goto out;
-    }
-    fcntl(s->fds[GLUSTER_FD_READ], F_SETFL, O_NONBLOCK);
-    qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ],
-        qemu_gluster_aio_event_reader, NULL, qemu_gluster_aio_flush_cb, s);
-
-out:
-    qemu_gluster_gconf_free(gconf);
-    if (!ret) {
-        return ret;
-    }
-    if (s->fd) {
-        glfs_close(s->fd);
-    }
-    if (s->glfs) {
-        glfs_fini(s->glfs);
-    }
-    return ret;
-}
-
-static int qemu_gluster_create(const char *filename,
-        QEMUOptionParameter *options)
-{
-    struct glfs *glfs;
-    struct glfs_fd *fd;
-    int ret = 0;
-    int64_t total_size = 0;
-    GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
-
-    glfs = qemu_gluster_init(gconf, filename);
-    if (!glfs) {
-        ret = -errno;
-        goto out;
-    }
-
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            total_size = options->value.n / BDRV_SECTOR_SIZE;
-        }
-        options++;
-    }
-
-    fd = glfs_creat(glfs, gconf->image,
-        O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, S_IRUSR | S_IWUSR);
-    if (!fd) {
-        ret = -errno;
-    } else {
-        if (glfs_ftruncate(fd, total_size * BDRV_SECTOR_SIZE) != 0) {
-            ret = -errno;
-        }
-        if (glfs_close(fd) != 0) {
-            ret = -errno;
-        }
-    }
-out:
-    qemu_gluster_gconf_free(gconf);
-    if (glfs) {
-        glfs_fini(glfs);
-    }
-    return ret;
-}
-
-static void qemu_gluster_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    GlusterAIOCB *acb = (GlusterAIOCB *)blockacb;
-    bool finished = false;
-
-    acb->finished = &finished;
-    while (!finished) {
-        qemu_aio_wait();
-    }
-}
-
-static const AIOCBInfo gluster_aiocb_info = {
-    .aiocb_size = sizeof(GlusterAIOCB),
-    .cancel = qemu_gluster_aio_cancel,
-};
-
-static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
-{
-    GlusterAIOCB *acb = (GlusterAIOCB *)arg;
-    BlockDriverState *bs = acb->common.bs;
-    BDRVGlusterState *s = bs->opaque;
-    int retval;
-
-    acb->ret = ret;
-    retval = qemu_write_full(s->fds[GLUSTER_FD_WRITE], &acb, sizeof(acb));
-    if (retval != sizeof(acb)) {
-        /*
-         * Gluster AIO callback thread failed to notify the waiting
-         * QEMU thread about IO completion.
-         *
-         * Complete this IO request and make the disk inaccessible for
-         * subsequent reads and writes.
-         */
-        error_report("Gluster failed to notify QEMU about IO completion");
-
-        qemu_mutex_lock_iothread(); /* We are in gluster thread context */
-        acb->common.cb(acb->common.opaque, -EIO);
-        qemu_aio_release(acb);
-        s->qemu_aio_count--;
-        close(s->fds[GLUSTER_FD_READ]);
-        close(s->fds[GLUSTER_FD_WRITE]);
-        qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ], NULL, NULL, NULL,
-            NULL);
-        bs->drv = NULL; /* Make the disk inaccessible */
-        qemu_mutex_unlock_iothread();
-    }
-}
-
-static BlockDriverAIOCB *qemu_gluster_aio_rw(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque, int write)
-{
-    int ret;
-    GlusterAIOCB *acb;
-    BDRVGlusterState *s = bs->opaque;
-    size_t size;
-    off_t offset;
-
-    offset = sector_num * BDRV_SECTOR_SIZE;
-    size = nb_sectors * BDRV_SECTOR_SIZE;
-    s->qemu_aio_count++;
-
-    acb = qemu_aio_get(&gluster_aiocb_info, bs, cb, opaque);
-    acb->size = size;
-    acb->ret = 0;
-    acb->finished = NULL;
-
-    if (write) {
-        ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
-            &gluster_finish_aiocb, acb);
-    } else {
-        ret = glfs_preadv_async(s->fd, qiov->iov, qiov->niov, offset, 0,
-            &gluster_finish_aiocb, acb);
-    }
-
-    if (ret < 0) {
-        goto out;
-    }
-    return &acb->common;
-
-out:
-    s->qemu_aio_count--;
-    qemu_aio_release(acb);
-    return NULL;
-}
-
-static BlockDriverAIOCB *qemu_gluster_aio_readv(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    return qemu_gluster_aio_rw(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
-}
-
-static BlockDriverAIOCB *qemu_gluster_aio_writev(BlockDriverState *bs,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    return qemu_gluster_aio_rw(bs, sector_num, qiov, nb_sectors, cb, opaque, 1);
-}
-
-static BlockDriverAIOCB *qemu_gluster_aio_flush(BlockDriverState *bs,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    int ret;
-    GlusterAIOCB *acb;
-    BDRVGlusterState *s = bs->opaque;
-
-    acb = qemu_aio_get(&gluster_aiocb_info, bs, cb, opaque);
-    acb->size = 0;
-    acb->ret = 0;
-    acb->finished = NULL;
-    s->qemu_aio_count++;
-
-    ret = glfs_fsync_async(s->fd, &gluster_finish_aiocb, acb);
-    if (ret < 0) {
-        goto out;
-    }
-    return &acb->common;
-
-out:
-    s->qemu_aio_count--;
-    qemu_aio_release(acb);
-    return NULL;
-}
-
-static int64_t qemu_gluster_getlength(BlockDriverState *bs)
-{
-    BDRVGlusterState *s = bs->opaque;
-    int64_t ret;
-
-    ret = glfs_lseek(s->fd, 0, SEEK_END);
-    if (ret < 0) {
-        return -errno;
-    } else {
-        return ret;
-    }
-}
-
-static int64_t qemu_gluster_allocated_file_size(BlockDriverState *bs)
-{
-    BDRVGlusterState *s = bs->opaque;
-    struct stat st;
-    int ret;
-
-    ret = glfs_fstat(s->fd, &st);
-    if (ret < 0) {
-        return -errno;
-    } else {
-        return st.st_blocks * 512;
-    }
-}
-
-static void qemu_gluster_close(BlockDriverState *bs)
-{
-    BDRVGlusterState *s = bs->opaque;
-
-    close(s->fds[GLUSTER_FD_READ]);
-    close(s->fds[GLUSTER_FD_WRITE]);
-    qemu_aio_set_fd_handler(s->fds[GLUSTER_FD_READ], NULL, NULL, NULL, NULL);
-
-    if (s->fd) {
-        glfs_close(s->fd);
-        s->fd = NULL;
-    }
-    glfs_fini(s->glfs);
-}
-
-static QEMUOptionParameter qemu_gluster_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    { NULL }
-};
-
-static BlockDriver bdrv_gluster = {
-    .format_name                  = "gluster",
-    .protocol_name                = "gluster",
-    .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
-    .bdrv_getlength               = qemu_gluster_getlength,
-    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
-    .create_options               = qemu_gluster_create_options,
-};
-
-static BlockDriver bdrv_gluster_tcp = {
-    .format_name                  = "gluster",
-    .protocol_name                = "gluster+tcp",
-    .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
-    .bdrv_getlength               = qemu_gluster_getlength,
-    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
-    .create_options               = qemu_gluster_create_options,
-};
-
-static BlockDriver bdrv_gluster_unix = {
-    .format_name                  = "gluster",
-    .protocol_name                = "gluster+unix",
-    .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
-    .bdrv_getlength               = qemu_gluster_getlength,
-    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
-    .create_options               = qemu_gluster_create_options,
-};
-
-static BlockDriver bdrv_gluster_rdma = {
-    .format_name                  = "gluster",
-    .protocol_name                = "gluster+rdma",
-    .instance_size                = sizeof(BDRVGlusterState),
-    .bdrv_file_open               = qemu_gluster_open,
-    .bdrv_close                   = qemu_gluster_close,
-    .bdrv_create                  = qemu_gluster_create,
-    .bdrv_getlength               = qemu_gluster_getlength,
-    .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_aio_readv               = qemu_gluster_aio_readv,
-    .bdrv_aio_writev              = qemu_gluster_aio_writev,
-    .bdrv_aio_flush               = qemu_gluster_aio_flush,
-    .create_options               = qemu_gluster_create_options,
-};
-
-static void bdrv_gluster_init(void)
-{
-    bdrv_register(&bdrv_gluster_rdma);
-    bdrv_register(&bdrv_gluster_unix);
-    bdrv_register(&bdrv_gluster_tcp);
-    bdrv_register(&bdrv_gluster);
-}
-
-block_init(bdrv_gluster_init);

block/iscsi.c

@@ -27,9 +27,8 @@
 #include <poll.h>
 #include <arpa/inet.h>
 #include "qemu-common.h"
-#include "qemu/config-file.h"
-#include "qemu/error-report.h"
-#include "block/block_int.h"
+#include "qemu-error.h"
+#include "block_int.h"
 #include "trace.h"
 #include "hw/scsi-defs.h"
 
@@ -48,7 +47,6 @@ typedef struct IscsiLun {
     int block_size;
     uint64_t num_blocks;
     int events;
-    QEMUTimer *nop_timer;
 } IscsiLun;
 
 typedef struct IscsiAIOCB {
@@ -67,9 +65,6 @@ typedef struct IscsiAIOCB {
 #endif
 } IscsiAIOCB;
 
-#define NOP_INTERVAL 5000
-#define MAX_NOP_FAILURES 3
-
 static void
 iscsi_bh_cb(void *p)
 {
@@ -77,9 +72,6 @@ iscsi_bh_cb(void *p)
 
     qemu_bh_delete(acb->bh);
 
-    g_free(acb->buf);
-    acb->buf = NULL;
-
     if (acb->canceled == 0) {
         acb->common.cb(acb->common.opaque, acb->status);
     }
@@ -134,7 +126,7 @@ iscsi_aio_cancel(BlockDriverAIOCB *blockacb)
     }
 }
 
-static const AIOCBInfo iscsi_aiocb_info = {
+static AIOPool iscsi_aio_pool = {
     .aiocb_size         = sizeof(IscsiAIOCB),
     .cancel             = iscsi_aio_cancel,
 };
@@ -201,7 +193,6 @@ iscsi_aio_write16_cb(struct iscsi_context *iscsi, int status,
     trace_iscsi_aio_write16_cb(iscsi, status, acb, acb->canceled);
 
     g_free(acb->buf);
-    acb->buf = NULL;
 
     if (acb->canceled != 0) {
         return;
@@ -234,12 +225,9 @@ iscsi_aio_writev(BlockDriverState *bs, int64_t sector_num,
     size_t size;
     uint32_t num_sectors;
     uint64_t lba;
-#if !defined(LIBISCSI_FEATURE_IOVECTOR)
     struct iscsi_data data;
-#endif
-    int ret;
 
-    acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
     trace_iscsi_aio_writev(iscsi, sector_num, nb_sectors, opaque, acb);
 
     acb->iscsilun = iscsilun;
@@ -248,23 +236,12 @@ iscsi_aio_writev(BlockDriverState *bs, int64_t sector_num,
     acb->canceled   = 0;
     acb->bh         = NULL;
     acb->status     = -EINPROGRESS;
-    acb->buf        = NULL;
 
+    /* XXX we should pass the iovec to write16 to avoid the extra copy */
     /* this will allow us to get rid of 'buf' completely */
     size = nb_sectors * BDRV_SECTOR_SIZE;
-
-#if !defined(LIBISCSI_FEATURE_IOVECTOR)
-    data.size = MIN(size, acb->qiov->size);
-
-    /* if the iovec only contains one buffer we can pass it directly */
-    if (acb->qiov->niov == 1) {
-        data.data = acb->qiov->iov[0].iov_base;
-    } else {
-        acb->buf = g_malloc(data.size);
-        qemu_iovec_to_buf(acb->qiov, 0, acb->buf, data.size);
-        data.data = acb->buf;
-    }
-#endif
+    acb->buf = g_malloc(size);
+    qemu_iovec_to_buf(acb->qiov, 0, acb->buf, size);
 
     acb->task = malloc(sizeof(struct scsi_task));
     if (acb->task == NULL) {
@@ -278,6 +255,10 @@ iscsi_aio_writev(BlockDriverState *bs, int64_t sector_num,
     acb->task->xfer_dir = SCSI_XFER_WRITE;
     acb->task->cdb_size = 16;
     acb->task->cdb[0] = 0x8a;
+    if (!(bs->open_flags & BDRV_O_CACHE_WB)) {
+        /* set FUA on writes when cache mode is write through */
+        acb->task->cdb[1] |= 0x04;
+    }
     lba = sector_qemu2lun(sector_num, iscsilun);
     *(uint32_t *)&acb->task->cdb[2]  = htonl(lba >> 32);
     *(uint32_t *)&acb->task->cdb[6]  = htonl(lba & 0xffffffff);
@@ -285,28 +266,19 @@ iscsi_aio_writev(BlockDriverState *bs, int64_t sector_num,
     *(uint32_t *)&acb->task->cdb[10] = htonl(num_sectors);
     acb->task->expxferlen = size;
 
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
-    ret = iscsi_scsi_command_async(iscsi, iscsilun->lun, acb->task,
-                                   iscsi_aio_write16_cb,
-                                   NULL,
-                                   acb);
-#else
-    ret = iscsi_scsi_command_async(iscsi, iscsilun->lun, acb->task,
-                                   iscsi_aio_write16_cb,
-                                   &data,
-                                   acb);
-#endif
-    if (ret != 0) {
+    data.data = acb->buf;
+    data.size = size;
+
+    if (iscsi_scsi_command_async(iscsi, iscsilun->lun, acb->task,
+                                 iscsi_aio_write16_cb,
+                                 &data,
+                                 acb) != 0) {
         scsi_free_scsi_task(acb->task);
         g_free(acb->buf);
         qemu_aio_release(acb);
         return NULL;
     }
 
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
-    scsi_task_set_iov_out(acb->task, (struct scsi_iovec*) acb->qiov->iov, acb->qiov->niov);
-#endif
-
     iscsi_set_events(iscsilun);
 
     return &acb->common;
@@ -344,16 +316,13 @@ iscsi_aio_readv(BlockDriverState *bs, int64_t sector_num,
     struct iscsi_context *iscsi = iscsilun->iscsi;
     IscsiAIOCB *acb;
     size_t qemu_read_size;
-#if !defined(LIBISCSI_FEATURE_IOVECTOR)
     int i;
-#endif
-    int ret;
     uint64_t lba;
     uint32_t num_sectors;
 
     qemu_read_size = BDRV_SECTOR_SIZE * (size_t)nb_sectors;
 
-    acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
     trace_iscsi_aio_readv(iscsi, sector_num, nb_sectors, opaque, acb);
 
     acb->iscsilun = iscsilun;
@@ -409,25 +378,20 @@ iscsi_aio_readv(BlockDriverState *bs, int64_t sector_num,
         break;
     }
 
-    ret = iscsi_scsi_command_async(iscsi, iscsilun->lun, acb->task,
-                                   iscsi_aio_read16_cb,
-                                   NULL,
-                                   acb);
-    if (ret != 0) {
+    if (iscsi_scsi_command_async(iscsi, iscsilun->lun, acb->task,
+                                 iscsi_aio_read16_cb,
+                                 NULL,
+                                 acb) != 0) {
         scsi_free_scsi_task(acb->task);
         qemu_aio_release(acb);
         return NULL;
     }
 
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
-    scsi_task_set_iov_in(acb->task, (struct scsi_iovec*) acb->qiov->iov, acb->qiov->niov);
-#else
     for (i = 0; i < acb->qiov->niov; i++) {
         scsi_task_add_data_in_buffer(acb->task,
                 acb->qiov->iov[i].iov_len,
                 acb->qiov->iov[i].iov_base);
     }
-#endif
 
     iscsi_set_events(iscsilun);
 
@@ -463,13 +427,12 @@ iscsi_aio_flush(BlockDriverState *bs,
     struct iscsi_context *iscsi = iscsilun->iscsi;
     IscsiAIOCB *acb;
 
-    acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
 
     acb->iscsilun = iscsilun;
     acb->canceled   = 0;
     acb->bh         = NULL;
     acb->status     = -EINPROGRESS;
-    acb->buf        = NULL;
 
     acb->task = iscsi_synchronizecache10_task(iscsi, iscsilun->lun,
                                          0, 0, 0, 0,
@@ -517,13 +480,12 @@ iscsi_aio_discard(BlockDriverState *bs,
     IscsiAIOCB *acb;
     struct unmap_list list[1];
 
-    acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
 
     acb->iscsilun = iscsilun;
     acb->canceled   = 0;
     acb->bh         = NULL;
     acb->status     = -EINPROGRESS;
-    acb->buf        = NULL;
 
     list[0].lba = sector_qemu2lun(sector_num, iscsilun);
     list[0].num = nb_sectors * BDRV_SECTOR_SIZE / iscsilun->block_size;
@@ -593,7 +555,7 @@ static BlockDriverAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
 
     assert(req == SG_IO);
 
-    acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
 
     acb->iscsilun = iscsilun;
     acb->canceled    = 0;
@@ -803,26 +765,6 @@ static char *parse_initiator_name(const char *target)
     }
 }
 
-#if defined(LIBISCSI_FEATURE_NOP_COUNTER)
-static void iscsi_nop_timed_event(void *opaque)
-{
-    IscsiLun *iscsilun = opaque;
-
-    if (iscsi_get_nops_in_flight(iscsilun->iscsi) > MAX_NOP_FAILURES) {
-        error_report("iSCSI: NOP timeout. Reconnecting...");
-        iscsi_reconnect(iscsilun->iscsi);
-    }
-
-    if (iscsi_nop_out_async(iscsilun->iscsi, NULL, NULL, 0, NULL) != 0) {
-        error_report("iSCSI: failed to sent NOP-Out. Disabling NOP messages.");
-        return;
-    }
-
-    qemu_mod_timer(iscsilun->nop_timer, qemu_get_clock_ms(rt_clock) + NOP_INTERVAL);
-    iscsi_set_events(iscsilun);
-}
-#endif
-
 /*
  * We support iscsi url's on the form
  * iscsi://[<username>%<password>@]<host>[:<port>]/<targetname>/<lun>
@@ -983,12 +925,6 @@ static int iscsi_open(BlockDriverState *bs, const char *filename, int flags)
 
     ret = 0;
 
-#if defined(LIBISCSI_FEATURE_NOP_COUNTER)
-    /* Set up a timer for sending out iSCSI NOPs */
-    iscsilun->nop_timer = qemu_new_timer_ms(rt_clock, iscsi_nop_timed_event, iscsilun);
-    qemu_mod_timer(iscsilun->nop_timer, qemu_get_clock_ms(rt_clock) + NOP_INTERVAL);
-#endif
-
 out:
     if (initiator_name != NULL) {
         g_free(initiator_name);
@@ -1014,10 +950,6 @@ static void iscsi_close(BlockDriverState *bs)
     IscsiLun *iscsilun = bs->opaque;
     struct iscsi_context *iscsi = iscsilun->iscsi;
 
-    if (iscsilun->nop_timer) {
-        qemu_del_timer(iscsilun->nop_timer);
-        qemu_free_timer(iscsilun->nop_timer);
-    }
     qemu_aio_set_fd_handler(iscsi_get_fd(iscsi), NULL, NULL, NULL, NULL);
     iscsi_destroy_context(iscsi);
     memset(iscsilun, 0, sizeof(IscsiLun));
@@ -1028,60 +960,6 @@ static int iscsi_has_zero_init(BlockDriverState *bs)
     return 0;
 }
 
-static int iscsi_create(const char *filename, QEMUOptionParameter *options)
-{
-    int ret = 0;
-    int64_t total_size = 0;
-    BlockDriverState bs;
-    IscsiLun *iscsilun = NULL;
-
-    memset(&bs, 0, sizeof(BlockDriverState));
-
-    /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, "size")) {
-            total_size = options->value.n / BDRV_SECTOR_SIZE;
-        }
-        options++;
-    }
-
-    bs.opaque = g_malloc0(sizeof(struct IscsiLun));
-    iscsilun = bs.opaque;
-
-    ret = iscsi_open(&bs, filename, 0);
-    if (ret != 0) {
-        goto out;
-    }
-    if (iscsilun->nop_timer) {
-        qemu_del_timer(iscsilun->nop_timer);
-        qemu_free_timer(iscsilun->nop_timer);
-    }
-    if (iscsilun->type != TYPE_DISK) {
-        ret = -ENODEV;
-        goto out;
-    }
-    if (bs.total_sectors < total_size) {
-        ret = -ENOSPC;
-    }
-
-    ret = 0;
-out:
-    if (iscsilun->iscsi != NULL) {
-        iscsi_destroy_context(iscsilun->iscsi);
-    }
-    g_free(bs.opaque);
-    return ret;
-}
-
-static QEMUOptionParameter iscsi_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    { NULL }
-};
-
 static BlockDriver bdrv_iscsi = {
     .format_name     = "iscsi",
     .protocol_name   = "iscsi",
@@ -1089,8 +967,6 @@ static BlockDriver bdrv_iscsi = {
     .instance_size   = sizeof(IscsiLun),
     .bdrv_file_open  = iscsi_open,
     .bdrv_close      = iscsi_close,
-    .bdrv_create     = iscsi_create,
-    .create_options  = iscsi_create_options,
 
     .bdrv_getlength  = iscsi_getlength,
 
@@ -1107,36 +983,9 @@ static BlockDriver bdrv_iscsi = {
 #endif
 };
 
-static QemuOptsList qemu_iscsi_opts = {
-    .name = "iscsi",
-    .head = QTAILQ_HEAD_INITIALIZER(qemu_iscsi_opts.head),
-    .desc = {
-        {
-            .name = "user",
-            .type = QEMU_OPT_STRING,
-            .help = "username for CHAP authentication to target",
-        },{
-            .name = "password",
-            .type = QEMU_OPT_STRING,
-            .help = "password for CHAP authentication to target",
-        },{
-            .name = "header-digest",
-            .type = QEMU_OPT_STRING,
-            .help = "HeaderDigest setting. "
-                    "{CRC32C|CRC32C-NONE|NONE-CRC32C|NONE}",
-        },{
-            .name = "initiator-name",
-            .type = QEMU_OPT_STRING,
-            .help = "Initiator iqn name to use when connecting",
-        },
-        { /* end of list */ }
-    },
-};
-
 static void iscsi_block_init(void)
 {
     bdrv_register(&bdrv_iscsi);
-    qemu_add_opts(&qemu_iscsi_opts);
 }
 
 block_init(iscsi_block_init);

block/mirror.c

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

block/nbd.c

@@ -27,11 +27,10 @@
  */
 
 #include "qemu-common.h"
-#include "block/nbd.h"
-#include "qemu/uri.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "qemu/sockets.h"
+#include "nbd.h"
+#include "block_int.h"
+#include "module.h"
+#include "qemu_socket.h"
 
 #include <sys/types.h>
 #include <unistd.h>
@@ -56,6 +55,7 @@ typedef struct BDRVNBDState {
     uint32_t nbdflags;
     off_t size;
     size_t blocksize;
+    char *export_name; /* An NBD server may export several devices */
 
     CoMutex send_mutex;
     CoMutex free_sema;
@@ -65,75 +65,13 @@ typedef struct BDRVNBDState {
     Coroutine *recv_coroutine[MAX_NBD_REQUESTS];
     struct nbd_reply reply;
 
-    int is_unix;
+    /* 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;
-    char *export_name; /* An NBD server may export several devices */
 } BDRVNBDState;
 
-static int nbd_parse_uri(BDRVNBDState *s, const char *filename)
-{
-    URI *uri;
-    const char *p;
-    QueryParams *qp = NULL;
-    int ret = 0;
-
-    uri = uri_parse(filename);
-    if (!uri) {
-        return -EINVAL;
-    }
-
-    /* transport */
-    if (!strcmp(uri->scheme, "nbd")) {
-        s->is_unix = false;
-    } else if (!strcmp(uri->scheme, "nbd+tcp")) {
-        s->is_unix = false;
-    } else if (!strcmp(uri->scheme, "nbd+unix")) {
-        s->is_unix = true;
-    } else {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    p = uri->path ? uri->path : "/";
-    p += strspn(p, "/");
-    if (p[0]) {
-        s->export_name = g_strdup(p);
-    }
-
-    qp = query_params_parse(uri->query);
-    if (qp->n > 1 || (s->is_unix && !qp->n) || (!s->is_unix && qp->n)) {
-        ret = -EINVAL;
-        goto out;
-    }
-
-    if (s->is_unix) {
-        /* nbd+unix:///export?socket=path */
-        if (uri->server || uri->port || strcmp(qp->p[0].name, "socket")) {
-            ret = -EINVAL;
-            goto out;
-        }
-        s->host_spec = g_strdup(qp->p[0].value);
-    } else {
-        /* nbd[+tcp]://host:port/export */
-        if (!uri->server) {
-            ret = -EINVAL;
-            goto out;
-        }
-        if (!uri->port) {
-            uri->port = NBD_DEFAULT_PORT;
-        }
-        s->host_spec = g_strdup_printf("%s:%d", uri->server, uri->port);
-    }
-
-out:
-    if (qp) {
-        query_params_free(qp);
-    }
-    uri_free(uri);
-    return ret;
-}
-
-static int nbd_config(BDRVNBDState *s, const char *filename)
+static int nbd_config(BDRVNBDState *s, const char *filename, int flags)
 {
     char *file;
     char *export_name;
@@ -141,10 +79,6 @@ static int nbd_config(BDRVNBDState *s, const char *filename)
     const char *unixpath;
     int err = -EINVAL;
 
-    if (strstr(filename, "://")) {
-        return nbd_parse_uri(s, filename);
-    }
-
     file = g_strdup(filename);
 
     export_name = strstr(file, EN_OPTSTR);
@@ -164,10 +98,11 @@ static int nbd_config(BDRVNBDState *s, const char *filename)
 
     /* are we a UNIX or TCP socket? */
     if (strstart(host_spec, "unix:", &unixpath)) {
-        s->is_unix = true;
+        if (unixpath[0] != '/') { /* We demand  an absolute path*/
+            goto out;
+        }
         s->host_spec = g_strdup(unixpath);
     } else {
-        s->is_unix = false;
         s->host_spec = g_strdup(host_spec);
     }
 
@@ -327,7 +262,7 @@ static int nbd_establish_connection(BlockDriverState *bs)
     off_t size;
     size_t blocksize;
 
-    if (s->is_unix) {
+    if (s->host_spec[0] == '/') {
         sock = unix_socket_outgoing(s->host_spec);
     } else {
         sock = tcp_socket_outgoing_spec(s->host_spec);
@@ -350,7 +285,7 @@ static int nbd_establish_connection(BlockDriverState *bs)
 
     /* Now that we're connected, set the socket to be non-blocking and
      * kick the reply mechanism.  */
-    qemu_set_nonblock(sock);
+    socket_set_nonblock(sock);
     qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL,
                             nbd_have_request, s);
 
@@ -385,7 +320,7 @@ static int nbd_open(BlockDriverState *bs, const char* filename, int flags)
     qemu_co_mutex_init(&s->free_sema);
 
     /* Pop the config into our state object. Exit if invalid. */
-    result = nbd_config(s, filename);
+    result = nbd_config(s, filename, flags);
     if (result != 0) {
         return result;
     }
@@ -563,48 +498,20 @@ static int64_t nbd_getlength(BlockDriverState *bs)
 
 static BlockDriver bdrv_nbd = {
     .format_name         = "nbd",
+    .instance_size       = sizeof(BDRVNBDState),
+    .bdrv_file_open      = nbd_open,
+    .bdrv_co_readv       = nbd_co_readv,
+    .bdrv_co_writev      = nbd_co_writev,
+    .bdrv_close          = nbd_close,
+    .bdrv_co_flush_to_os = nbd_co_flush,
+    .bdrv_co_discard     = nbd_co_discard,
+    .bdrv_getlength      = nbd_getlength,
     .protocol_name       = "nbd",
-    .instance_size       = sizeof(BDRVNBDState),
-    .bdrv_file_open      = nbd_open,
-    .bdrv_co_readv       = nbd_co_readv,
-    .bdrv_co_writev      = nbd_co_writev,
-    .bdrv_close          = nbd_close,
-    .bdrv_co_flush_to_os = nbd_co_flush,
-    .bdrv_co_discard     = nbd_co_discard,
-    .bdrv_getlength      = nbd_getlength,
-};
-
-static BlockDriver bdrv_nbd_tcp = {
-    .format_name         = "nbd",
-    .protocol_name       = "nbd+tcp",
-    .instance_size       = sizeof(BDRVNBDState),
-    .bdrv_file_open      = nbd_open,
-    .bdrv_co_readv       = nbd_co_readv,
-    .bdrv_co_writev      = nbd_co_writev,
-    .bdrv_close          = nbd_close,
-    .bdrv_co_flush_to_os = nbd_co_flush,
-    .bdrv_co_discard     = nbd_co_discard,
-    .bdrv_getlength      = nbd_getlength,
-};
-
-static BlockDriver bdrv_nbd_unix = {
-    .format_name         = "nbd",
-    .protocol_name       = "nbd+unix",
-    .instance_size       = sizeof(BDRVNBDState),
-    .bdrv_file_open      = nbd_open,
-    .bdrv_co_readv       = nbd_co_readv,
-    .bdrv_co_writev      = nbd_co_writev,
-    .bdrv_close          = nbd_close,
-    .bdrv_co_flush_to_os = nbd_co_flush,
-    .bdrv_co_discard     = nbd_co_discard,
-    .bdrv_getlength      = nbd_getlength,
 };
 
 static void bdrv_nbd_init(void)
 {
     bdrv_register(&bdrv_nbd);
-    bdrv_register(&bdrv_nbd_tcp);
-    bdrv_register(&bdrv_nbd_unix);
 }
 
 block_init(bdrv_nbd_init);

block/parallels.c

@@ -24,8 +24,8 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 
 /**************************************************************/
 
@@ -73,18 +73,14 @@ static int parallels_open(BlockDriverState *bs, int flags)
     BDRVParallelsState *s = bs->opaque;
     int i;
     struct parallels_header ph;
-    int ret;
 
     bs->read_only = 1; // no write support yet
 
-    ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph));
-    if (ret < 0) {
+    if (bdrv_pread(bs->file, 0, &ph, sizeof(ph)) != sizeof(ph))
         goto fail;
-    }
 
     if (memcmp(ph.magic, HEADER_MAGIC, 16) ||
-        (le32_to_cpu(ph.version) != HEADER_VERSION)) {
-        ret = -EMEDIUMTYPE;
+	(le32_to_cpu(ph.version) != HEADER_VERSION)) {
         goto fail;
     }
 
@@ -94,21 +90,18 @@ static int parallels_open(BlockDriverState *bs, int flags)
 
     s->catalog_size = le32_to_cpu(ph.catalog_entries);
     s->catalog_bitmap = g_malloc(s->catalog_size * 4);
-
-    ret = bdrv_pread(bs->file, 64, s->catalog_bitmap, s->catalog_size * 4);
-    if (ret < 0) {
-        goto fail;
-    }
-
+    if (bdrv_pread(bs->file, 64, s->catalog_bitmap, s->catalog_size * 4) !=
+	s->catalog_size * 4)
+	goto fail;
     for (i = 0; i < s->catalog_size; i++)
 	le32_to_cpus(&s->catalog_bitmap[i]);
 
     qemu_co_mutex_init(&s->lock);
     return 0;
-
 fail:
-    g_free(s->catalog_bitmap);
-    return ret;
+    if (s->catalog_bitmap)
+	g_free(s->catalog_bitmap);
+    return -1;
 }
 
 static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)

block/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 "block/aes.h"
-#include "migration/migration.h"
+#include "aes.h"
+#include "migration.h"
 
 /**************************************************************/
 /* QEMU COW block driver with compression and encryption support */
@@ -112,7 +112,7 @@ static int qcow_open(BlockDriverState *bs, int flags)
     be64_to_cpus(&header.l1_table_offset);
 
     if (header.magic != QCOW_MAGIC) {
-        ret = -EMEDIUMTYPE;
+        ret = -EINVAL;
         goto fail;
     }
     if (header.version != QCOW_VERSION) {
@@ -197,15 +197,6 @@ static int qcow_open(BlockDriverState *bs, int flags)
     return ret;
 }
 
-
-/* We have nothing to do for QCOW reopen, stubs just return
- * success */
-static int qcow_reopen_prepare(BDRVReopenState *state,
-                               BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 static int qcow_set_key(BlockDriverState *bs, const char *key)
 {
     BDRVQcowState *s = bs->opaque;
@@ -877,7 +868,6 @@ static BlockDriver bdrv_qcow = {
     .bdrv_probe		= qcow_probe,
     .bdrv_open		= qcow_open,
     .bdrv_close		= qcow_close,
-    .bdrv_reopen_prepare = qcow_reopen_prepare,
     .bdrv_create	= qcow_create,
 
     .bdrv_co_readv          = qcow_co_readv,

block/qcow2-cache.c

@@ -22,7 +22,7 @@
  * THE SOFTWARE.
  */
 
-#include "block/block_int.h"
+#include "block_int.h"
 #include "qemu-common.h"
 #include "qcow2.h"
 #include "trace.h"

block/qcow2-cluster.c

@@ -25,7 +25,7 @@
 #include <zlib.h>
 
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include "block/qcow2.h"
 #include "trace.h"
 
@@ -454,9 +454,6 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
         *cluster_offset &= L2E_COMPRESSED_OFFSET_SIZE_MASK;
         break;
     case QCOW2_CLUSTER_ZERO:
-        if (s->qcow_version < 3) {
-            return -EIO;
-        }
         c = count_contiguous_clusters(nb_clusters, s->cluster_size,
                 &l2_table[l2_index], 0,
                 QCOW_OFLAG_COMPRESSED | QCOW_OFLAG_ZERO);
@@ -618,67 +615,57 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
     return cluster_offset;
 }
 
-static int perform_cow(BlockDriverState *bs, QCowL2Meta *m, Qcow2COWRegion *r)
-{
-    BDRVQcowState *s = bs->opaque;
-    int ret;
-
-    if (r->nb_sectors == 0) {
-        return 0;
-    }
-
-    qemu_co_mutex_unlock(&s->lock);
-    ret = copy_sectors(bs, m->offset / BDRV_SECTOR_SIZE, m->alloc_offset,
-                       r->offset / BDRV_SECTOR_SIZE,
-                       r->offset / BDRV_SECTOR_SIZE + r->nb_sectors);
-    qemu_co_mutex_lock(&s->lock);
-
-    if (ret < 0) {
-        return ret;
-    }
-
-    /*
-     * Before we update the L2 table to actually point to the new cluster, we
-     * need to be sure that the refcounts have been increased and COW was
-     * handled.
-     */
-    qcow2_cache_depends_on_flush(s->l2_table_cache);
-
-    return 0;
-}
-
 int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
 {
     BDRVQcowState *s = bs->opaque;
     int i, j = 0, l2_index, ret;
-    uint64_t *old_cluster, *l2_table;
+    uint64_t *old_cluster, start_sect, *l2_table;
     uint64_t cluster_offset = m->alloc_offset;
+    bool cow = false;
 
     trace_qcow2_cluster_link_l2(qemu_coroutine_self(), m->nb_clusters);
-    assert(m->nb_clusters > 0);
+
+    if (m->nb_clusters == 0)
+        return 0;
 
     old_cluster = g_malloc(m->nb_clusters * sizeof(uint64_t));
 
     /* copy content of unmodified sectors */
-    ret = perform_cow(bs, m, &m->cow_start);
-    if (ret < 0) {
-        goto err;
+    start_sect = (m->offset & ~(s->cluster_size - 1)) >> 9;
+    if (m->n_start) {
+        cow = true;
+        qemu_co_mutex_unlock(&s->lock);
+        ret = copy_sectors(bs, start_sect, cluster_offset, 0, m->n_start);
+        qemu_co_mutex_lock(&s->lock);
+        if (ret < 0)
+            goto err;
     }
 
-    ret = perform_cow(bs, m, &m->cow_end);
-    if (ret < 0) {
-        goto err;
+    if (m->nb_available & (s->cluster_sectors - 1)) {
+        cow = true;
+        qemu_co_mutex_unlock(&s->lock);
+        ret = copy_sectors(bs, start_sect, cluster_offset, m->nb_available,
+                           align_offset(m->nb_available, s->cluster_sectors));
+        qemu_co_mutex_lock(&s->lock);
+        if (ret < 0)
+            goto err;
     }
 
-    /* Update L2 table. */
-    if (s->compatible_features & QCOW2_COMPAT_LAZY_REFCOUNTS) {
-        qcow2_mark_dirty(bs);
+    /*
+     * Update L2 table.
+     *
+     * Before we update the L2 table to actually point to the new cluster, we
+     * need to be sure that the refcounts have been increased and COW was
+     * handled.
+     */
+    if (cow) {
+        qcow2_cache_depends_on_flush(s->l2_table_cache);
     }
+
     if (qcow2_need_accurate_refcounts(s)) {
         qcow2_cache_set_dependency(bs, s->l2_table_cache,
                                    s->refcount_block_cache);
     }
-
     ret = get_cluster_table(bs, m->offset, &l2_table, &l2_index);
     if (ret < 0) {
         goto err;
@@ -756,16 +743,38 @@ out:
 }
 
 /*
- * Check if there already is an AIO write request in flight which allocates
- * the same cluster. In this case we need to wait until the previous
- * request has completed and updated the L2 table accordingly.
+ * Allocates new clusters for the given guest_offset.
+ *
+ * At most *nb_clusters are allocated, and on return *nb_clusters is updated to
+ * contain the number of clusters that have been allocated and are contiguous
+ * in the image file.
+ *
+ * If *host_offset is non-zero, it specifies the offset in the image file at
+ * which the new clusters must start. *nb_clusters can be 0 on return in this
+ * case if the cluster at host_offset is already in use. If *host_offset is
+ * zero, the clusters can be allocated anywhere in the image file.
+ *
+ * *host_offset is updated to contain the offset into the image file at which
+ * the first allocated cluster starts.
+ *
+ * Return 0 on success and -errno in error cases. -EAGAIN means that the
+ * function has been waiting for another request and the allocation must be
+ * restarted, but the whole request should not be failed.
  */
-static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset,
-    unsigned int *nb_clusters)
+static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
+    uint64_t *host_offset, unsigned int *nb_clusters)
 {
     BDRVQcowState *s = bs->opaque;
     QCowL2Meta *old_alloc;
 
+    trace_qcow2_do_alloc_clusters_offset(qemu_coroutine_self(), guest_offset,
+                                         *host_offset, *nb_clusters);
+
+    /*
+     * Check if there already is an AIO write request in flight which allocates
+     * the same cluster. In this case we need to wait until the previous
+     * request has completed and updated the L2 table accordingly.
+     */
     QLIST_FOREACH(old_alloc, &s->cluster_allocs, next_in_flight) {
 
         uint64_t start = guest_offset >> s->cluster_bits;
@@ -798,42 +807,6 @@ static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset,
         abort();
     }
 
-    return 0;
-}
-
-/*
- * Allocates new clusters for the given guest_offset.
- *
- * At most *nb_clusters are allocated, and on return *nb_clusters is updated to
- * contain the number of clusters that have been allocated and are contiguous
- * in the image file.
- *
- * If *host_offset is non-zero, it specifies the offset in the image file at
- * which the new clusters must start. *nb_clusters can be 0 on return in this
- * case if the cluster at host_offset is already in use. If *host_offset is
- * zero, the clusters can be allocated anywhere in the image file.
- *
- * *host_offset is updated to contain the offset into the image file at which
- * the first allocated cluster starts.
- *
- * Return 0 on success and -errno in error cases. -EAGAIN means that the
- * function has been waiting for another request and the allocation must be
- * restarted, but the whole request should not be failed.
- */
-static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
-    uint64_t *host_offset, unsigned int *nb_clusters)
-{
-    BDRVQcowState *s = bs->opaque;
-    int ret;
-
-    trace_qcow2_do_alloc_clusters_offset(qemu_coroutine_self(), guest_offset,
-                                         *host_offset, *nb_clusters);
-
-    ret = handle_dependencies(bs, guest_offset, nb_clusters);
-    if (ret < 0) {
-        return ret;
-    }
-
     /* Allocate new clusters */
     trace_qcow2_cluster_alloc_phys(qemu_coroutine_self());
     if (*host_offset == 0) {
@@ -845,7 +818,7 @@ static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
         *host_offset = cluster_offset;
         return 0;
     } else {
-        ret = qcow2_alloc_clusters_at(bs, *host_offset, *nb_clusters);
+        int ret = qcow2_alloc_clusters_at(bs, *host_offset, *nb_clusters);
         if (ret < 0) {
             return ret;
         }
@@ -874,7 +847,7 @@ static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
  * Return 0 on success and -errno in error cases
  */
 int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
-    int n_start, int n_end, int *num, uint64_t *host_offset, QCowL2Meta **m)
+    int n_start, int n_end, int *num, QCowL2Meta *m)
 {
     BDRVQcowState *s = bs->opaque;
     int l2_index, ret, sectors;
@@ -946,6 +919,12 @@ again:
     }
 
     /* If there is something left to allocate, do that now */
+    *m = (QCowL2Meta) {
+        .cluster_offset     = cluster_offset,
+        .nb_clusters        = 0,
+    };
+    qemu_co_queue_init(&m->dependent_requests);
+
     if (nb_clusters > 0) {
         uint64_t alloc_offset;
         uint64_t alloc_cluster_offset;
@@ -978,40 +957,22 @@ again:
              *
              * avail_sectors: Number of sectors from the start of the first
              * newly allocated to the end of the last newly allocated cluster.
-             *
-             * nb_sectors: The number of sectors from the start of the first
-             * newly allocated cluster to the end of the aread that the write
-             * request actually writes to (excluding COW at the end)
              */
             int requested_sectors = n_end - keep_clusters * s->cluster_sectors;
             int avail_sectors = nb_clusters
                                 << (s->cluster_bits - BDRV_SECTOR_BITS);
-            int alloc_n_start = keep_clusters == 0 ? n_start : 0;
-            int nb_sectors = MIN(requested_sectors, avail_sectors);
 
-            if (keep_clusters == 0) {
-                cluster_offset = alloc_cluster_offset;
-            }
-
-            *m = g_malloc0(sizeof(**m));
-
-            **m = (QCowL2Meta) {
+            *m = (QCowL2Meta) {
+                .cluster_offset = keep_clusters == 0 ?
+                                  alloc_cluster_offset : cluster_offset,
                 .alloc_offset   = alloc_cluster_offset,
-                .offset         = alloc_offset & ~(s->cluster_size - 1),
+                .offset         = alloc_offset,
+                .n_start        = keep_clusters == 0 ? n_start : 0,
                 .nb_clusters    = nb_clusters,
-                .nb_available   = nb_sectors,
-
-                .cow_start = {
-                    .offset     = 0,
-                    .nb_sectors = alloc_n_start,
-                },
-                .cow_end = {
-                    .offset     = nb_sectors * BDRV_SECTOR_SIZE,
-                    .nb_sectors = avail_sectors - nb_sectors,
-                },
+                .nb_available   = MIN(requested_sectors, avail_sectors),
             };
-            qemu_co_queue_init(&(*m)->dependent_requests);
-            QLIST_INSERT_HEAD(&s->cluster_allocs, *m, next_in_flight);
+            qemu_co_queue_init(&m->dependent_requests);
+            QLIST_INSERT_HEAD(&s->cluster_allocs, m, next_in_flight);
         }
     }
 
@@ -1023,13 +984,12 @@ again:
 
     assert(sectors > n_start);
     *num = sectors - n_start;
-    *host_offset = cluster_offset;
 
     return 0;
 
 fail:
-    if (*m && (*m)->nb_clusters > 0) {
-        QLIST_REMOVE(*m, next_in_flight);
+    if (m->nb_clusters > 0) {
+        QLIST_REMOVE(m, next_in_flight);
     }
     return ret;
 }

block/qcow2-refcount.c

@@ -23,7 +23,7 @@
  */
 
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include "block/qcow2.h"
 
 static int64_t alloc_clusters_noref(BlockDriverState *bs, int64_t size);
@@ -201,10 +201,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
     *refcount_block = NULL;
 
     /* We write to the refcount table, so we might depend on L2 tables */
-    ret = qcow2_cache_flush(bs, s->l2_table_cache);
-    if (ret < 0) {
-        return ret;
-    }
+    qcow2_cache_flush(bs, s->l2_table_cache);
 
     /* Allocate the refcount block itself and mark it as used */
     int64_t new_block = alloc_clusters_noref(bs, s->cluster_size);
@@ -240,10 +237,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
             goto fail_block;
         }
 
-        ret = qcow2_cache_flush(bs, s->refcount_block_cache);
-        if (ret < 0) {
-            goto fail_block;
-        }
+        bdrv_flush(bs->file);
 
         /* Initialize the new refcount block only after updating its refcount,
          * update_refcount uses the refcount cache itself */
@@ -743,7 +737,11 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
      * l1_table_offset when it is the current s->l1_table_offset! Be careful
      * when changing this! */
     if (l1_table_offset != s->l1_table_offset) {
-        l1_table = g_malloc0(align_offset(l1_size2, 512));
+        if (l1_size2 != 0) {
+            l1_table = g_malloc0(align_offset(l1_size2, 512));
+        } else {
+            l1_table = NULL;
+        }
         l1_allocated = 1;
         if (bdrv_pread(bs->file, l1_table_offset,
                        l1_table, l1_size2) != l1_size2)

block/qcow2-snapshot.c

@@ -23,7 +23,7 @@
  */
 
 #include "qemu-common.h"
-#include "block/block_int.h"
+#include "block_int.h"
 #include "block/qcow2.h"
 
 typedef struct QEMU_PACKED QCowSnapshotHeader {
@@ -180,14 +180,11 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
 
     /* Allocate space for the new snapshot list */
     snapshots_offset = qcow2_alloc_clusters(bs, snapshots_size);
+    bdrv_flush(bs->file);
     offset = snapshots_offset;
     if (offset < 0) {
         return offset;
     }
-    ret = bdrv_flush(bs);
-    if (ret < 0) {
-        return ret;
-    }
 
     /* Write all snapshots to the new list */
     for(i = 0; i < s->nb_snapshots; i++) {

block/qcow2.c

@@ -22,13 +22,13 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 #include <zlib.h>
-#include "block/aes.h"
+#include "aes.h"
 #include "block/qcow2.h"
-#include "qemu/error-report.h"
-#include "qapi/qmp/qerror.h"
+#include "qemu-error.h"
+#include "qerror.h"
 #include "trace.h"
 
 /*
@@ -52,7 +52,6 @@ typedef struct {
     uint32_t magic;
     uint32_t len;
 } QCowExtension;
-
 #define  QCOW2_EXT_MAGIC_END 0
 #define  QCOW2_EXT_MAGIC_BACKING_FORMAT 0xE2792ACA
 #define  QCOW2_EXT_MAGIC_FEATURE_TABLE 0x6803f857
@@ -222,7 +221,7 @@ static void report_unsupported_feature(BlockDriverState *bs,
  * updated successfully.  Therefore it is not required to check the return
  * value of this function.
  */
-int qcow2_mark_dirty(BlockDriverState *bs)
+static int qcow2_mark_dirty(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t val;
@@ -311,7 +310,7 @@ static int qcow2_open(BlockDriverState *bs, int flags)
     be32_to_cpus(&header.nb_snapshots);
 
     if (header.magic != QCOW_MAGIC) {
-        ret = -EMEDIUMTYPE;
+        ret = -EINVAL;
         goto fail;
     }
     if (header.version < 2 || header.version > 3) {
@@ -559,14 +558,6 @@ static int qcow2_set_key(BlockDriverState *bs, const char *key)
     return 0;
 }
 
-/* We have nothing to do for QCOW2 reopen, stubs just return
- * success */
-static int qcow2_reopen_prepare(BDRVReopenState *state,
-                                BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 static int coroutine_fn qcow2_co_is_allocated(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *pnum)
 {
@@ -584,7 +575,7 @@ static int coroutine_fn qcow2_co_is_allocated(BlockDriverState *bs,
         *pnum = 0;
     }
 
-    return (cluster_offset != 0) || (ret == QCOW2_CLUSTER_ZERO);
+    return (cluster_offset != 0);
 }
 
 /* handle reading after the end of the backing file */
@@ -665,6 +656,10 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
             break;
 
         case QCOW2_CLUSTER_ZERO:
+            if (s->qcow_version < 3) {
+                ret = -EIO;
+                goto fail;
+            }
             qemu_iovec_memset(&hd_qiov, 0, 0, 512 * cur_nr_sectors);
             break;
 
@@ -741,6 +736,21 @@ fail:
     return ret;
 }
 
+static void run_dependent_requests(BDRVQcowState *s, QCowL2Meta *m)
+{
+    /* Take the request off the list of running requests */
+    if (m->nb_clusters != 0) {
+        QLIST_REMOVE(m, next_in_flight);
+    }
+
+    /* Restart all dependent requests */
+    if (!qemu_co_queue_empty(&m->dependent_requests)) {
+        qemu_co_mutex_unlock(&s->lock);
+        qemu_co_queue_restart_all(&m->dependent_requests);
+        qemu_co_mutex_lock(&s->lock);
+    }
+}
+
 static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
                            int64_t sector_num,
                            int remaining_sectors,
@@ -755,11 +765,15 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
     QEMUIOVector hd_qiov;
     uint64_t bytes_done = 0;
     uint8_t *cluster_data = NULL;
-    QCowL2Meta *l2meta = NULL;
+    QCowL2Meta l2meta = {
+        .nb_clusters = 0,
+    };
 
     trace_qcow2_writev_start_req(qemu_coroutine_self(), sector_num,
                                  remaining_sectors);
 
+    qemu_co_queue_init(&l2meta.dependent_requests);
+
     qemu_iovec_init(&hd_qiov, qiov->niov);
 
     s->cluster_cache_offset = -1; /* disable compressed cache */
@@ -768,8 +782,6 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
 
     while (remaining_sectors != 0) {
 
-        l2meta = NULL;
-
         trace_qcow2_writev_start_part(qemu_coroutine_self());
         index_in_cluster = sector_num & (s->cluster_sectors - 1);
         n_end = index_in_cluster + remaining_sectors;
@@ -779,11 +791,17 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
         }
 
         ret = qcow2_alloc_cluster_offset(bs, sector_num << 9,
-            index_in_cluster, n_end, &cur_nr_sectors, &cluster_offset, &l2meta);
+            index_in_cluster, n_end, &cur_nr_sectors, &l2meta);
         if (ret < 0) {
             goto fail;
         }
 
+        if (l2meta.nb_clusters > 0 &&
+            (s->compatible_features & QCOW2_COMPAT_LAZY_REFCOUNTS)) {
+            qcow2_mark_dirty(bs);
+        }
+
+        cluster_offset = l2meta.cluster_offset;
         assert((cluster_offset & 511) == 0);
 
         qemu_iovec_reset(&hd_qiov);
@@ -808,8 +826,8 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
                 cur_nr_sectors * 512);
         }
 
-        qemu_co_mutex_unlock(&s->lock);
         BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
+        qemu_co_mutex_unlock(&s->lock);
         trace_qcow2_writev_data(qemu_coroutine_self(),
                                 (cluster_offset >> 9) + index_in_cluster);
         ret = bdrv_co_writev(bs->file,
@@ -820,25 +838,13 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
             goto fail;
         }
 
-        if (l2meta != NULL) {
-            ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
-            if (ret < 0) {
-                goto fail;
-            }
-
-            /* Take the request off the list of running requests */
-            if (l2meta->nb_clusters != 0) {
-                QLIST_REMOVE(l2meta, next_in_flight);
-            }
-
-            qemu_co_mutex_unlock(&s->lock);
-            qemu_co_queue_restart_all(&l2meta->dependent_requests);
-            qemu_co_mutex_lock(&s->lock);
-
-            g_free(l2meta);
-            l2meta = NULL;
+        ret = qcow2_alloc_cluster_link_l2(bs, &l2meta);
+        if (ret < 0) {
+            goto fail;
         }
 
+        run_dependent_requests(s, &l2meta);
+
         remaining_sectors -= cur_nr_sectors;
         sector_num += cur_nr_sectors;
         bytes_done += cur_nr_sectors * 512;
@@ -847,15 +853,9 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
     ret = 0;
 
 fail:
-    qemu_co_mutex_unlock(&s->lock);
+    run_dependent_requests(s, &l2meta);
 
-    if (l2meta != NULL) {
-        if (l2meta->nb_clusters != 0) {
-            QLIST_REMOVE(l2meta, next_in_flight);
-        }
-        qemu_co_queue_restart_all(&l2meta->dependent_requests);
-        g_free(l2meta);
-    }
+    qemu_co_mutex_unlock(&s->lock);
 
     qemu_iovec_destroy(&hd_qiov);
     qemu_vfree(cluster_data);
@@ -1087,7 +1087,6 @@ int qcow2_update_header(BlockDriverState *bs)
             goto fail;
         }
 
-        /* Using strncpy is ok here, since buf is not NUL-terminated. */
         strncpy(buf, bs->backing_file, buflen);
 
         header->backing_file_offset = cpu_to_be64(buf - ((char*) header));
@@ -1119,33 +1118,31 @@ static int preallocate(BlockDriverState *bs)
 {
     uint64_t nb_sectors;
     uint64_t offset;
-    uint64_t host_offset = 0;
     int num;
     int ret;
-    QCowL2Meta *meta;
+    QCowL2Meta meta;
 
     nb_sectors = bdrv_getlength(bs) >> 9;
     offset = 0;
+    qemu_co_queue_init(&meta.dependent_requests);
+    meta.cluster_offset = 0;
 
     while (nb_sectors) {
         num = MIN(nb_sectors, INT_MAX >> 9);
-        ret = qcow2_alloc_cluster_offset(bs, offset, 0, num, &num,
-                                         &host_offset, &meta);
+        ret = qcow2_alloc_cluster_offset(bs, offset, 0, num, &num, &meta);
         if (ret < 0) {
             return ret;
         }
 
-        ret = qcow2_alloc_cluster_link_l2(bs, meta);
+        ret = qcow2_alloc_cluster_link_l2(bs, &meta);
         if (ret < 0) {
-            qcow2_free_any_clusters(bs, meta->alloc_offset, meta->nb_clusters);
+            qcow2_free_any_clusters(bs, meta.cluster_offset, meta.nb_clusters);
             return ret;
         }
 
         /* There are no dependent requests, but we need to remove our request
          * from the list of in-flight requests */
-        if (meta != NULL) {
-            QLIST_REMOVE(meta, next_in_flight);
-        }
+        run_dependent_requests(bs->opaque, &meta);
 
         /* TODO Preallocate data if requested */
 
@@ -1158,10 +1155,10 @@ static int preallocate(BlockDriverState *bs)
      * all of the allocated clusters (otherwise we get failing reads after
      * EOF). Extend the image to the last allocated sector.
      */
-    if (host_offset != 0) {
+    if (meta.cluster_offset != 0) {
         uint8_t buf[512];
         memset(buf, 0, 512);
-        ret = bdrv_write(bs->file, (host_offset >> 9) + num - 1, buf, 1);
+        ret = bdrv_write(bs->file, (meta.cluster_offset >> 9) + num - 1, buf, 1);
         if (ret < 0) {
             return ret;
         }
@@ -1682,7 +1679,6 @@ static BlockDriver bdrv_qcow2 = {
     .bdrv_probe         = qcow2_probe,
     .bdrv_open          = qcow2_open,
     .bdrv_close         = qcow2_close,
-    .bdrv_reopen_prepare  = qcow2_reopen_prepare,
     .bdrv_create        = qcow2_create,
     .bdrv_co_is_allocated = qcow2_co_is_allocated,
     .bdrv_set_key       = qcow2_set_key,

block/qcow2.h

@@ -25,8 +25,8 @@
 #ifndef BLOCK_QCOW2_H
 #define BLOCK_QCOW2_H
 
-#include "block/aes.h"
-#include "block/coroutine.h"
+#include "aes.h"
+#include "qemu-coroutine.h"
 
 //#define DEBUG_ALLOC
 //#define DEBUG_ALLOC2
@@ -196,56 +196,17 @@ typedef struct QCowCreateState {
 
 struct QCowAIOCB;
 
-typedef struct Qcow2COWRegion {
-    /**
-     * Offset of the COW region in bytes from the start of the first cluster
-     * touched by the request.
-     */
-    uint64_t    offset;
-
-    /** Number of sectors to copy */
-    int         nb_sectors;
-} Qcow2COWRegion;
-
-/**
- * Describes an in-flight (part of a) write request that writes to clusters
- * that are not referenced in their L2 table yet.
- */
+/* XXX This could be private for qcow2-cluster.c */
 typedef struct QCowL2Meta
 {
-    /** Guest offset of the first newly allocated cluster */
     uint64_t offset;
-
-    /** Host offset of the first newly allocated cluster */
+    uint64_t cluster_offset;
     uint64_t alloc_offset;
-
-    /**
-     * Number of sectors from the start of the first allocated cluster to
-     * the end of the (possibly shortened) request
-     */
+    int n_start;
     int nb_available;
-
-    /** Number of newly allocated clusters */
     int nb_clusters;
-
-    /**
-     * Requests that overlap with this allocation and wait to be restarted
-     * when the allocating request has completed.
-     */
     CoQueue dependent_requests;
 
-    /**
-     * The COW Region between the start of the first allocated cluster and the
-     * area the guest actually writes to.
-     */
-    Qcow2COWRegion cow_start;
-
-    /**
-     * The COW Region between the area the guest actually writes to and the
-     * end of the last allocated cluster.
-     */
-    Qcow2COWRegion cow_end;
-
     QLIST_ENTRY(QCowL2Meta) next_in_flight;
 } QCowL2Meta;
 
@@ -303,8 +264,6 @@ static inline bool qcow2_need_accurate_refcounts(BDRVQcowState *s)
 /* qcow2.c functions */
 int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov,
                   int64_t sector_num, int nb_sectors);
-
-int qcow2_mark_dirty(BlockDriverState *bs);
 int qcow2_update_header(BlockDriverState *bs);
 
 /* qcow2-refcount.c functions */
@@ -338,7 +297,7 @@ void qcow2_encrypt_sectors(BDRVQcowState *s, int64_t sector_num,
 int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
     int *num, uint64_t *cluster_offset);
 int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
-    int n_start, int n_end, int *num, uint64_t *host_offset, QCowL2Meta **m);
+    int n_start, int n_end, int *num, QCowL2Meta *m);
 uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
                                          uint64_t offset,
                                          int compressed_size);

block/qed-table.c

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

block/qed.c

@@ -12,11 +12,11 @@
  *
  */
 
-#include "qemu/timer.h"
+#include "qemu-timer.h"
 #include "trace.h"
 #include "qed.h"
-#include "qapi/qmp/qerror.h"
-#include "migration/migration.h"
+#include "qerror.h"
+#include "migration.h"
 
 static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
 {
@@ -30,7 +30,7 @@ static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
     }
 }
 
-static const AIOCBInfo qed_aiocb_info = {
+static AIOPool qed_aio_pool = {
     .aiocb_size         = sizeof(QEDAIOCB),
     .cancel             = qed_aio_cancel,
 };
@@ -390,7 +390,7 @@ static int bdrv_qed_open(BlockDriverState *bs, int flags)
     qed_header_le_to_cpu(&le_header, &s->header);
 
     if (s->header.magic != QED_MAGIC) {
-        return -EMEDIUMTYPE;
+        return -EINVAL;
     }
     if (s->header.features & ~QED_FEATURE_MASK) {
         /* image uses unsupported feature bits */
@@ -505,14 +505,6 @@ out:
     return ret;
 }
 
-/* We have nothing to do for QED reopen, stubs just return
- * success */
-static int bdrv_qed_reopen_prepare(BDRVReopenState *state,
-                                   BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 static void bdrv_qed_close(BlockDriverState *bs)
 {
     BDRVQEDState *s = bs->opaque;
@@ -1311,7 +1303,7 @@ static BlockDriverAIOCB *qed_aio_setup(BlockDriverState *bs,
                                        BlockDriverCompletionFunc *cb,
                                        void *opaque, int flags)
 {
-    QEDAIOCB *acb = qemu_aio_get(&qed_aiocb_info, bs, cb, opaque);
+    QEDAIOCB *acb = qemu_aio_get(&qed_aio_pool, bs, cb, opaque);
 
     trace_qed_aio_setup(bs->opaque, acb, sector_num, nb_sectors,
                         opaque, flags);
@@ -1572,7 +1564,6 @@ static BlockDriver bdrv_qed = {
     .bdrv_rebind              = bdrv_qed_rebind,
     .bdrv_open                = bdrv_qed_open,
     .bdrv_close               = bdrv_qed_close,
-    .bdrv_reopen_prepare      = bdrv_qed_reopen_prepare,
     .bdrv_create              = bdrv_qed_create,
     .bdrv_co_is_allocated     = bdrv_qed_co_is_allocated,
     .bdrv_make_empty          = bdrv_qed_make_empty,

block/qed.h

@@ -15,7 +15,7 @@
 #ifndef BLOCK_QED_H
 #define BLOCK_QED_H
 
-#include "block/block_int.h"
+#include "block_int.h"
 
 /* The layout of a QED file is as follows:
  *

block/raw-posix-aio.h

@@ -1,5 +1,5 @@
 /*
- * Declarations for AIO in the raw protocol
+ * QEMU Posix block I/O backend AIO support
  *
  * Copyright IBM, Corp. 2008
  *
@@ -12,40 +12,34 @@
  * Contributions after 2012-01-13 are licensed under the terms of the
  * GNU GPL, version 2 or (at your option) any later version.
  */
-#ifndef QEMU_RAW_AIO_H
-#define QEMU_RAW_AIO_H
+#ifndef QEMU_RAW_POSIX_AIO_H
+#define QEMU_RAW_POSIX_AIO_H
 
 /* AIO request types */
 #define QEMU_AIO_READ         0x0001
 #define QEMU_AIO_WRITE        0x0002
 #define QEMU_AIO_IOCTL        0x0004
 #define QEMU_AIO_FLUSH        0x0008
-#define QEMU_AIO_DISCARD      0x0010
 #define QEMU_AIO_TYPE_MASK \
-        (QEMU_AIO_READ|QEMU_AIO_WRITE|QEMU_AIO_IOCTL|QEMU_AIO_FLUSH| \
-         QEMU_AIO_DISCARD)
+	(QEMU_AIO_READ|QEMU_AIO_WRITE|QEMU_AIO_IOCTL|QEMU_AIO_FLUSH)
 
 /* AIO flags */
 #define QEMU_AIO_MISALIGNED   0x1000
-#define QEMU_AIO_BLKDEV       0x2000
 
 
+/* posix-aio-compat.c - thread pool based implementation */
+int paio_init(void);
+BlockDriverAIOCB *paio_submit(BlockDriverState *bs, int fd,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque, int type);
+BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd,
+        unsigned long int req, void *buf,
+        BlockDriverCompletionFunc *cb, void *opaque);
+
 /* linux-aio.c - Linux native implementation */
-#ifdef CONFIG_LINUX_AIO
 void *laio_init(void);
 BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
         BlockDriverCompletionFunc *cb, void *opaque, int type);
-#endif
 
-#ifdef _WIN32
-typedef struct QEMUWin32AIOState QEMUWin32AIOState;
-QEMUWin32AIOState *win32_aio_init(void);
-int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile);
-BlockDriverAIOCB *win32_aio_submit(BlockDriverState *bs,
-        QEMUWin32AIOState *aio, HANDLE hfile,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque, int type);
-#endif
-
-#endif /* QEMU_RAW_AIO_H */
+#endif /* QEMU_RAW_POSIX_AIO_H */

block/raw-posix.c

@@ -22,14 +22,12 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "qemu/timer.h"
-#include "qemu/log.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "trace.h"
-#include "block/thread-pool.h"
-#include "qemu/iov.h"
-#include "raw-aio.h"
+#include "qemu-timer.h"
+#include "qemu-char.h"
+#include "qemu-log.h"
+#include "block_int.h"
+#include "module.h"
+#include "block/raw-posix-aio.h"
 
 #if defined(__APPLE__) && (__MACH__)
 #include <paths.h>
@@ -59,9 +57,6 @@
 #ifdef CONFIG_FIEMAP
 #include <linux/fiemap.h>
 #endif
-#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
-#include <linux/falloc.h>
-#endif
 #if defined (__FreeBSD__) || defined(__FreeBSD_kernel__)
 #include <sys/disk.h>
 #include <sys/cdio.h>
@@ -138,37 +133,16 @@ typedef struct BDRVRawState {
     int use_aio;
     void *aio_ctx;
 #endif
+    uint8_t *aligned_buf;
+    unsigned aligned_buf_size;
 #ifdef CONFIG_XFS
     bool is_xfs : 1;
 #endif
-    bool has_discard : 1;
 } BDRVRawState;
 
-typedef struct BDRVRawReopenState {
-    int fd;
-    int open_flags;
-#ifdef CONFIG_LINUX_AIO
-    int use_aio;
-#endif
-} BDRVRawReopenState;
-
 static int fd_open(BlockDriverState *bs);
 static int64_t raw_getlength(BlockDriverState *bs);
 
-typedef struct RawPosixAIOData {
-    BlockDriverState *bs;
-    int aio_fildes;
-    union {
-        struct iovec *aio_iov;
-        void *aio_ioctl_buf;
-    };
-    int aio_niov;
-    uint64_t aio_nbytes;
-#define aio_ioctl_cmd   aio_nbytes /* for QEMU_AIO_IOCTL */
-    off_t aio_offset;
-    int aio_type;
-} RawPosixAIOData;
-
 #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
 static int cdrom_reopen(BlockDriverState *bs);
 #endif
@@ -211,57 +185,6 @@ static int raw_normalize_devicepath(const char **filename)
 }
 #endif
 
-static void raw_parse_flags(int bdrv_flags, int *open_flags)
-{
-    assert(open_flags != NULL);
-
-    *open_flags |= O_BINARY;
-    *open_flags &= ~O_ACCMODE;
-    if (bdrv_flags & BDRV_O_RDWR) {
-        *open_flags |= O_RDWR;
-    } else {
-        *open_flags |= O_RDONLY;
-    }
-
-    /* Use O_DSYNC for write-through caching, no flags for write-back caching,
-     * and O_DIRECT for no caching. */
-    if ((bdrv_flags & BDRV_O_NOCACHE)) {
-        *open_flags |= O_DIRECT;
-    }
-}
-
-#ifdef CONFIG_LINUX_AIO
-static int raw_set_aio(void **aio_ctx, int *use_aio, int bdrv_flags)
-{
-    int ret = -1;
-    assert(aio_ctx != NULL);
-    assert(use_aio != NULL);
-    /*
-     * Currently Linux do AIO only for files opened with O_DIRECT
-     * specified so check NOCACHE flag too
-     */
-    if ((bdrv_flags & (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) ==
-                      (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) {
-
-        /* if non-NULL, laio_init() has already been run */
-        if (*aio_ctx == NULL) {
-            *aio_ctx = laio_init();
-            if (!*aio_ctx) {
-                goto error;
-            }
-        }
-        *use_aio = 1;
-    } else {
-        *use_aio = 0;
-    }
-
-    ret = 0;
-
-error:
-    return ret;
-}
-#endif
-
 static int raw_open_common(BlockDriverState *bs, const char *filename,
                            int bdrv_flags, int open_flags)
 {
@@ -273,8 +196,20 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
         return ret;
     }
 
-    s->open_flags = open_flags;
-    raw_parse_flags(bdrv_flags, &s->open_flags);
+    s->open_flags = open_flags | O_BINARY;
+    s->open_flags &= ~O_ACCMODE;
+    if (bdrv_flags & BDRV_O_RDWR) {
+        s->open_flags |= O_RDWR;
+    } else {
+        s->open_flags |= O_RDONLY;
+    }
+
+    /* Use O_DSYNC for write-through caching, no flags for write-back caching,
+     * and O_DIRECT for no caching. */
+    if ((bdrv_flags & BDRV_O_NOCACHE))
+        s->open_flags |= O_DIRECT;
+    if (!(bdrv_flags & BDRV_O_CACHE_WB))
+        s->open_flags |= O_DSYNC;
 
     s->fd = -1;
     fd = qemu_open(filename, s->open_flags, 0644);
@@ -285,15 +220,46 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
         return ret;
     }
     s->fd = fd;
+    s->aligned_buf = NULL;
+
+    if ((bdrv_flags & BDRV_O_NOCACHE)) {
+        /*
+         * Allocate a buffer for read/modify/write cycles.  Chose the size
+         * pessimistically as we don't know the block size yet.
+         */
+        s->aligned_buf_size = 32 * MAX_BLOCKSIZE;
+        s->aligned_buf = qemu_memalign(MAX_BLOCKSIZE, s->aligned_buf_size);
+        if (s->aligned_buf == NULL) {
+            goto out_close;
+        }
+    }
+
+    /* We're falling back to POSIX AIO in some cases so init always */
+    if (paio_init() < 0) {
+        goto out_free_buf;
+    }
 
 #ifdef CONFIG_LINUX_AIO
-    if (raw_set_aio(&s->aio_ctx, &s->use_aio, bdrv_flags)) {
-        qemu_close(fd);
-        return -errno;
-    }
-#endif
+    /*
+     * Currently Linux do AIO only for files opened with O_DIRECT
+     * specified so check NOCACHE flag too
+     */
+    if ((bdrv_flags & (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) ==
+                      (BDRV_O_NOCACHE|BDRV_O_NATIVE_AIO)) {
+
+        s->aio_ctx = laio_init();
+        if (!s->aio_ctx) {
+            goto out_free_buf;
+        }
+        s->use_aio = 1;
+    } else
+#endif
+    {
+#ifdef CONFIG_LINUX_AIO
+        s->use_aio = 0;
+#endif
+    }
 
-    s->has_discard = 1;
 #ifdef CONFIG_XFS
     if (platform_test_xfs_fd(s->fd)) {
         s->is_xfs = 1;
@@ -301,6 +267,12 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
 #endif
 
     return 0;
+
+out_free_buf:
+    qemu_vfree(s->aligned_buf);
+out_close:
+    qemu_close(fd);
+    return -errno;
 }
 
 static int raw_open(BlockDriverState *bs, const char *filename, int flags)
@@ -311,122 +283,6 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags)
     return raw_open_common(bs, filename, flags, 0);
 }
 
-static int raw_reopen_prepare(BDRVReopenState *state,
-                              BlockReopenQueue *queue, Error **errp)
-{
-    BDRVRawState *s;
-    BDRVRawReopenState *raw_s;
-    int ret = 0;
-
-    assert(state != NULL);
-    assert(state->bs != NULL);
-
-    s = state->bs->opaque;
-
-    state->opaque = g_malloc0(sizeof(BDRVRawReopenState));
-    raw_s = state->opaque;
-
-#ifdef CONFIG_LINUX_AIO
-    raw_s->use_aio = s->use_aio;
-
-    /* we can use s->aio_ctx instead of a copy, because the use_aio flag is
-     * valid in the 'false' condition even if aio_ctx is set, and raw_set_aio()
-     * won't override aio_ctx if aio_ctx is non-NULL */
-    if (raw_set_aio(&s->aio_ctx, &raw_s->use_aio, state->flags)) {
-        return -1;
-    }
-#endif
-
-    if (s->type == FTYPE_FD || s->type == FTYPE_CD) {
-        raw_s->open_flags |= O_NONBLOCK;
-    }
-
-    raw_parse_flags(state->flags, &raw_s->open_flags);
-
-    raw_s->fd = -1;
-
-    int fcntl_flags = O_APPEND | O_NONBLOCK;
-#ifdef O_NOATIME
-    fcntl_flags |= O_NOATIME;
-#endif
-
-#ifdef O_ASYNC
-    /* Not all operating systems have O_ASYNC, and those that don't
-     * will not let us track the state into raw_s->open_flags (typically
-     * you achieve the same effect with an ioctl, for example I_SETSIG
-     * on Solaris). But we do not use O_ASYNC, so that's fine.
-     */
-    assert((s->open_flags & O_ASYNC) == 0);
-#endif
-
-    if ((raw_s->open_flags & ~fcntl_flags) == (s->open_flags & ~fcntl_flags)) {
-        /* dup the original fd */
-        /* TODO: use qemu fcntl wrapper */
-#ifdef F_DUPFD_CLOEXEC
-        raw_s->fd = fcntl(s->fd, F_DUPFD_CLOEXEC, 0);
-#else
-        raw_s->fd = dup(s->fd);
-        if (raw_s->fd != -1) {
-            qemu_set_cloexec(raw_s->fd);
-        }
-#endif
-        if (raw_s->fd >= 0) {
-            ret = fcntl_setfl(raw_s->fd, raw_s->open_flags);
-            if (ret) {
-                qemu_close(raw_s->fd);
-                raw_s->fd = -1;
-            }
-        }
-    }
-
-    /* If we cannot use fcntl, or fcntl failed, fall back to qemu_open() */
-    if (raw_s->fd == -1) {
-        assert(!(raw_s->open_flags & O_CREAT));
-        raw_s->fd = qemu_open(state->bs->filename, raw_s->open_flags);
-        if (raw_s->fd == -1) {
-            ret = -1;
-        }
-    }
-    return ret;
-}
-
-
-static void raw_reopen_commit(BDRVReopenState *state)
-{
-    BDRVRawReopenState *raw_s = state->opaque;
-    BDRVRawState *s = state->bs->opaque;
-
-    s->open_flags = raw_s->open_flags;
-
-    qemu_close(s->fd);
-    s->fd = raw_s->fd;
-#ifdef CONFIG_LINUX_AIO
-    s->use_aio = raw_s->use_aio;
-#endif
-
-    g_free(state->opaque);
-    state->opaque = NULL;
-}
-
-
-static void raw_reopen_abort(BDRVReopenState *state)
-{
-    BDRVRawReopenState *raw_s = state->opaque;
-
-     /* nothing to do if NULL, we didn't get far enough */
-    if (raw_s == NULL) {
-        return;
-    }
-
-    if (raw_s->fd >= 0) {
-        qemu_close(raw_s->fd);
-        raw_s->fd = -1;
-    }
-    g_free(state->opaque);
-    state->opaque = NULL;
-}
-
-
 /* XXX: use host sector size if necessary with:
 #ifdef DIOCGSECTORSIZE
         {
@@ -444,326 +300,20 @@ static void raw_reopen_abort(BDRVReopenState *state)
 #endif
 */
 
-static ssize_t handle_aiocb_ioctl(RawPosixAIOData *aiocb)
-{
-    int ret;
-
-    ret = ioctl(aiocb->aio_fildes, aiocb->aio_ioctl_cmd, aiocb->aio_ioctl_buf);
-    if (ret == -1) {
-        return -errno;
-    }
-
-    return 0;
-}
-
-static ssize_t handle_aiocb_flush(RawPosixAIOData *aiocb)
-{
-    int ret;
-
-    ret = qemu_fdatasync(aiocb->aio_fildes);
-    if (ret == -1) {
-        return -errno;
-    }
-    return 0;
-}
-
-#ifdef CONFIG_PREADV
-
-static bool preadv_present = true;
-
-static ssize_t
-qemu_preadv(int fd, const struct iovec *iov, int nr_iov, off_t offset)
-{
-    return preadv(fd, iov, nr_iov, offset);
-}
-
-static ssize_t
-qemu_pwritev(int fd, const struct iovec *iov, int nr_iov, off_t offset)
-{
-    return pwritev(fd, iov, nr_iov, offset);
-}
-
-#else
-
-static bool preadv_present = false;
-
-static ssize_t
-qemu_preadv(int fd, const struct iovec *iov, int nr_iov, off_t offset)
-{
-    return -ENOSYS;
-}
-
-static ssize_t
-qemu_pwritev(int fd, const struct iovec *iov, int nr_iov, off_t offset)
-{
-    return -ENOSYS;
-}
-
-#endif
-
-static ssize_t handle_aiocb_rw_vector(RawPosixAIOData *aiocb)
-{
-    ssize_t len;
-
-    do {
-        if (aiocb->aio_type & QEMU_AIO_WRITE)
-            len = qemu_pwritev(aiocb->aio_fildes,
-                               aiocb->aio_iov,
-                               aiocb->aio_niov,
-                               aiocb->aio_offset);
-         else
-            len = qemu_preadv(aiocb->aio_fildes,
-                              aiocb->aio_iov,
-                              aiocb->aio_niov,
-                              aiocb->aio_offset);
-    } while (len == -1 && errno == EINTR);
-
-    if (len == -1) {
-        return -errno;
-    }
-    return len;
-}
-
 /*
- * Read/writes the data to/from a given linear buffer.
- *
- * Returns the number of bytes handles or -errno in case of an error. Short
- * reads are only returned if the end of the file is reached.
+ * Check if all memory in this vector is sector aligned.
  */
-static ssize_t handle_aiocb_rw_linear(RawPosixAIOData *aiocb, char *buf)
+static int qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
 {
-    ssize_t offset = 0;
-    ssize_t len;
+    int i;
 
-    while (offset < aiocb->aio_nbytes) {
-        if (aiocb->aio_type & QEMU_AIO_WRITE) {
-            len = pwrite(aiocb->aio_fildes,
-                         (const char *)buf + offset,
-                         aiocb->aio_nbytes - offset,
-                         aiocb->aio_offset + offset);
-        } else {
-            len = pread(aiocb->aio_fildes,
-                        buf + offset,
-                        aiocb->aio_nbytes - offset,
-                        aiocb->aio_offset + offset);
-        }
-        if (len == -1 && errno == EINTR) {
-            continue;
-        } else if (len == -1) {
-            offset = -errno;
-            break;
-        } else if (len == 0) {
-            break;
-        }
-        offset += len;
-    }
-
-    return offset;
-}
-
-static ssize_t handle_aiocb_rw(RawPosixAIOData *aiocb)
-{
-    ssize_t nbytes;
-    char *buf;
-
-    if (!(aiocb->aio_type & QEMU_AIO_MISALIGNED)) {
-        /*
-         * If there is just a single buffer, and it is properly aligned
-         * we can just use plain pread/pwrite without any problems.
-         */
-        if (aiocb->aio_niov == 1) {
-             return handle_aiocb_rw_linear(aiocb, aiocb->aio_iov->iov_base);
-        }
-        /*
-         * We have more than one iovec, and all are properly aligned.
-         *
-         * Try preadv/pwritev first and fall back to linearizing the
-         * buffer if it's not supported.
-         */
-        if (preadv_present) {
-            nbytes = handle_aiocb_rw_vector(aiocb);
-            if (nbytes == aiocb->aio_nbytes ||
-                (nbytes < 0 && nbytes != -ENOSYS)) {
-                return nbytes;
-            }
-            preadv_present = false;
-        }
-
-        /*
-         * XXX(hch): short read/write.  no easy way to handle the reminder
-         * using these interfaces.  For now retry using plain
-         * pread/pwrite?
-         */
-    }
-
-    /*
-     * Ok, we have to do it the hard way, copy all segments into
-     * a single aligned buffer.
-     */
-    buf = qemu_blockalign(aiocb->bs, aiocb->aio_nbytes);
-    if (aiocb->aio_type & QEMU_AIO_WRITE) {
-        char *p = buf;
-        int i;
-
-        for (i = 0; i < aiocb->aio_niov; ++i) {
-            memcpy(p, aiocb->aio_iov[i].iov_base, aiocb->aio_iov[i].iov_len);
-            p += aiocb->aio_iov[i].iov_len;
+    for (i = 0; i < qiov->niov; i++) {
+        if ((uintptr_t) qiov->iov[i].iov_base % bs->buffer_alignment) {
+            return 0;
         }
     }
 
-    nbytes = handle_aiocb_rw_linear(aiocb, buf);
-    if (!(aiocb->aio_type & QEMU_AIO_WRITE)) {
-        char *p = buf;
-        size_t count = aiocb->aio_nbytes, copy;
-        int i;
-
-        for (i = 0; i < aiocb->aio_niov && count; ++i) {
-            copy = count;
-            if (copy > aiocb->aio_iov[i].iov_len) {
-                copy = aiocb->aio_iov[i].iov_len;
-            }
-            memcpy(aiocb->aio_iov[i].iov_base, p, copy);
-            p     += copy;
-            count -= copy;
-        }
-    }
-    qemu_vfree(buf);
-
-    return nbytes;
-}
-
-#ifdef CONFIG_XFS
-static int xfs_discard(BDRVRawState *s, int64_t offset, uint64_t bytes)
-{
-    struct xfs_flock64 fl;
-
-    memset(&fl, 0, sizeof(fl));
-    fl.l_whence = SEEK_SET;
-    fl.l_start = offset;
-    fl.l_len = bytes;
-
-    if (xfsctl(NULL, s->fd, XFS_IOC_UNRESVSP64, &fl) < 0) {
-        DEBUG_BLOCK_PRINT("cannot punch hole (%s)\n", strerror(errno));
-        return -errno;
-    }
-
-    return 0;
-}
-#endif
-
-static ssize_t handle_aiocb_discard(RawPosixAIOData *aiocb)
-{
-    int ret = -EOPNOTSUPP;
-    BDRVRawState *s = aiocb->bs->opaque;
-
-    if (s->has_discard == 0) {
-        return 0;
-    }
-
-    if (aiocb->aio_type & QEMU_AIO_BLKDEV) {
-#ifdef BLKDISCARD
-        do {
-            uint64_t range[2] = { aiocb->aio_offset, aiocb->aio_nbytes };
-            if (ioctl(aiocb->aio_fildes, BLKDISCARD, range) == 0) {
-                return 0;
-            }
-        } while (errno == EINTR);
-
-        ret = -errno;
-#endif
-    } else {
-#ifdef CONFIG_XFS
-        if (s->is_xfs) {
-            return xfs_discard(s, aiocb->aio_offset, aiocb->aio_nbytes);
-        }
-#endif
-
-#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
-        do {
-            if (fallocate(s->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
-                          aiocb->aio_offset, aiocb->aio_nbytes) == 0) {
-                return 0;
-            }
-        } while (errno == EINTR);
-
-        ret = -errno;
-#endif
-    }
-
-    if (ret == -ENODEV || ret == -ENOSYS || ret == -EOPNOTSUPP ||
-        ret == -ENOTTY) {
-        s->has_discard = 0;
-        ret = 0;
-    }
-    return ret;
-}
-
-static int aio_worker(void *arg)
-{
-    RawPosixAIOData *aiocb = arg;
-    ssize_t ret = 0;
-
-    switch (aiocb->aio_type & QEMU_AIO_TYPE_MASK) {
-    case QEMU_AIO_READ:
-        ret = handle_aiocb_rw(aiocb);
-        if (ret >= 0 && ret < aiocb->aio_nbytes && aiocb->bs->growable) {
-            iov_memset(aiocb->aio_iov, aiocb->aio_niov, ret,
-                      0, aiocb->aio_nbytes - ret);
-
-            ret = aiocb->aio_nbytes;
-        }
-        if (ret == aiocb->aio_nbytes) {
-            ret = 0;
-        } else if (ret >= 0 && ret < aiocb->aio_nbytes) {
-            ret = -EINVAL;
-        }
-        break;
-    case QEMU_AIO_WRITE:
-        ret = handle_aiocb_rw(aiocb);
-        if (ret == aiocb->aio_nbytes) {
-            ret = 0;
-        } else if (ret >= 0 && ret < aiocb->aio_nbytes) {
-            ret = -EINVAL;
-        }
-        break;
-    case QEMU_AIO_FLUSH:
-        ret = handle_aiocb_flush(aiocb);
-        break;
-    case QEMU_AIO_IOCTL:
-        ret = handle_aiocb_ioctl(aiocb);
-        break;
-    case QEMU_AIO_DISCARD:
-        ret = handle_aiocb_discard(aiocb);
-        break;
-    default:
-        fprintf(stderr, "invalid aio request (0x%x)\n", aiocb->aio_type);
-        ret = -EINVAL;
-        break;
-    }
-
-    g_slice_free(RawPosixAIOData, aiocb);
-    return ret;
-}
-
-static BlockDriverAIOCB *paio_submit(BlockDriverState *bs, int fd,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque, int type)
-{
-    RawPosixAIOData *acb = g_slice_new(RawPosixAIOData);
-
-    acb->bs = bs;
-    acb->aio_type = type;
-    acb->aio_fildes = fd;
-
-    if (qiov) {
-        acb->aio_iov = qiov->iov;
-        acb->aio_niov = qiov->niov;
-    }
-    acb->aio_nbytes = nb_sectors * 512;
-    acb->aio_offset = sector_num * 512;
-
-    trace_paio_submit(acb, opaque, sector_num, nb_sectors, type);
-    return thread_pool_submit_aio(aio_worker, acb, cb, opaque);
+    return 1;
 }
 
 static BlockDriverAIOCB *raw_aio_submit(BlockDriverState *bs,
@@ -780,8 +330,8 @@ static BlockDriverAIOCB *raw_aio_submit(BlockDriverState *bs,
      * boundary.  Check if this is the case or tell the low-level
      * driver that it needs to copy the buffer.
      */
-    if ((bs->open_flags & BDRV_O_NOCACHE)) {
-        if (!bdrv_qiov_is_aligned(bs, qiov)) {
+    if (s->aligned_buf) {
+        if (!qiov_is_aligned(bs, qiov)) {
             type |= QEMU_AIO_MISALIGNED;
 #ifdef CONFIG_LINUX_AIO
         } else if (s->use_aio) {
@@ -828,6 +378,8 @@ static void raw_close(BlockDriverState *bs)
     if (s->fd >= 0) {
         qemu_close(s->fd);
         s->fd = -1;
+        if (s->aligned_buf != NULL)
+            qemu_vfree(s->aligned_buf);
     }
 }
 
@@ -1135,14 +687,37 @@ static int coroutine_fn raw_co_is_allocated(BlockDriverState *bs,
     }
 }
 
-static coroutine_fn BlockDriverAIOCB *raw_aio_discard(BlockDriverState *bs,
-    int64_t sector_num, int nb_sectors,
-    BlockDriverCompletionFunc *cb, void *opaque)
+#ifdef CONFIG_XFS
+static int xfs_discard(BDRVRawState *s, int64_t sector_num, int nb_sectors)
 {
+    struct xfs_flock64 fl;
+
+    memset(&fl, 0, sizeof(fl));
+    fl.l_whence = SEEK_SET;
+    fl.l_start = sector_num << 9;
+    fl.l_len = (int64_t)nb_sectors << 9;
+
+    if (xfsctl(NULL, s->fd, XFS_IOC_UNRESVSP64, &fl) < 0) {
+        DEBUG_BLOCK_PRINT("cannot punch hole (%s)\n", strerror(errno));
+        return -errno;
+    }
+
+    return 0;
+}
+#endif
+
+static coroutine_fn int raw_co_discard(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors)
+{
+#ifdef CONFIG_XFS
     BDRVRawState *s = bs->opaque;
 
-    return paio_submit(bs, s->fd, sector_num, NULL, nb_sectors,
-                       cb, opaque, QEMU_AIO_DISCARD);
+    if (s->is_xfs) {
+        return xfs_discard(s, sector_num, nb_sectors);
+    }
+#endif
+
+    return 0;
 }
 
 static QEMUOptionParameter raw_create_options[] = {
@@ -1160,17 +735,14 @@ static BlockDriver bdrv_file = {
     .instance_size = sizeof(BDRVRawState),
     .bdrv_probe = NULL, /* no probe for protocols */
     .bdrv_file_open = raw_open,
-    .bdrv_reopen_prepare = raw_reopen_prepare,
-    .bdrv_reopen_commit = raw_reopen_commit,
-    .bdrv_reopen_abort = raw_reopen_abort,
     .bdrv_close = raw_close,
     .bdrv_create = raw_create,
+    .bdrv_co_discard = raw_co_discard,
     .bdrv_co_is_allocated = raw_co_is_allocated,
 
     .bdrv_aio_readv = raw_aio_readv,
     .bdrv_aio_writev = raw_aio_writev,
     .bdrv_aio_flush = raw_aio_flush,
-    .bdrv_aio_discard = raw_aio_discard,
 
     .bdrv_truncate = raw_truncate,
     .bdrv_getlength = raw_getlength,
@@ -1257,43 +829,9 @@ static int hdev_probe_device(const char *filename)
     return 0;
 }
 
-static int check_hdev_writable(BDRVRawState *s)
-{
-#if defined(BLKROGET)
-    /* Linux block devices can be configured "read-only" using blockdev(8).
-     * This is independent of device node permissions and therefore open(2)
-     * with O_RDWR succeeds.  Actual writes fail with EPERM.
-     *
-     * bdrv_open() is supposed to fail if the disk is read-only.  Explicitly
-     * check for read-only block devices so that Linux block devices behave
-     * properly.
-     */
-    struct stat st;
-    int readonly = 0;
-
-    if (fstat(s->fd, &st)) {
-        return -errno;
-    }
-
-    if (!S_ISBLK(st.st_mode)) {
-        return 0;
-    }
-
-    if (ioctl(s->fd, BLKROGET, &readonly) < 0) {
-        return -errno;
-    }
-
-    if (readonly) {
-        return -EACCES;
-    }
-#endif /* defined(BLKROGET) */
-    return 0;
-}
-
 static int hdev_open(BlockDriverState *bs, const char *filename, int flags)
 {
     BDRVRawState *s = bs->opaque;
-    int ret;
 
 #if defined(__APPLE__) && defined(__MACH__)
     if (strstart(filename, "/dev/cdrom", NULL)) {
@@ -1334,20 +872,7 @@ static int hdev_open(BlockDriverState *bs, const char *filename, int flags)
     }
 #endif
 
-    ret = raw_open_common(bs, filename, flags, 0);
-    if (ret < 0) {
-        return ret;
-    }
-
-    if (flags & BDRV_O_RDWR) {
-        ret = check_hdev_writable(s);
-        if (ret < 0) {
-            raw_close(bs);
-            return ret;
-        }
-    }
-
-    return ret;
+    return raw_open_common(bs, filename, flags, 0);
 }
 
 #if defined(__linux__)
@@ -1412,19 +937,10 @@ static BlockDriverAIOCB *hdev_aio_ioctl(BlockDriverState *bs,
         BlockDriverCompletionFunc *cb, void *opaque)
 {
     BDRVRawState *s = bs->opaque;
-    RawPosixAIOData *acb;
 
     if (fd_open(bs) < 0)
         return NULL;
-
-    acb = g_slice_new(RawPosixAIOData);
-    acb->bs = bs;
-    acb->aio_type = QEMU_AIO_IOCTL;
-    acb->aio_fildes = s->fd;
-    acb->aio_offset = 0;
-    acb->aio_ioctl_buf = buf;
-    acb->aio_ioctl_cmd = req;
-    return thread_pool_submit_aio(aio_worker, acb, cb, opaque);
+    return paio_ioctl(bs, s->fd, req, buf, cb, opaque);
 }
 
 #elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
@@ -1446,19 +962,6 @@ static int fd_open(BlockDriverState *bs)
 
 #endif /* !linux && !FreeBSD */
 
-static coroutine_fn BlockDriverAIOCB *hdev_aio_discard(BlockDriverState *bs,
-    int64_t sector_num, int nb_sectors,
-    BlockDriverCompletionFunc *cb, void *opaque)
-{
-    BDRVRawState *s = bs->opaque;
-
-    if (fd_open(bs) < 0) {
-        return NULL;
-    }
-    return paio_submit(bs, s->fd, sector_num, NULL, nb_sectors,
-                       cb, opaque, QEMU_AIO_DISCARD|QEMU_AIO_BLKDEV);
-}
-
 static int hdev_create(const char *filename, QEMUOptionParameter *options)
 {
     int fd;
@@ -1501,9 +1004,6 @@ static BlockDriver bdrv_host_device = {
     .bdrv_probe_device  = hdev_probe_device,
     .bdrv_file_open     = hdev_open,
     .bdrv_close         = raw_close,
-    .bdrv_reopen_prepare = raw_reopen_prepare,
-    .bdrv_reopen_commit  = raw_reopen_commit,
-    .bdrv_reopen_abort   = raw_reopen_abort,
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
     .bdrv_has_zero_init = hdev_has_zero_init,
@@ -1511,7 +1011,6 @@ static BlockDriver bdrv_host_device = {
     .bdrv_aio_readv	= raw_aio_readv,
     .bdrv_aio_writev	= raw_aio_writev,
     .bdrv_aio_flush	= raw_aio_flush,
-    .bdrv_aio_discard   = hdev_aio_discard,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength	= raw_getlength,
@@ -1626,9 +1125,6 @@ static BlockDriver bdrv_host_floppy = {
     .bdrv_probe_device	= floppy_probe_device,
     .bdrv_file_open     = floppy_open,
     .bdrv_close         = raw_close,
-    .bdrv_reopen_prepare = raw_reopen_prepare,
-    .bdrv_reopen_commit  = raw_reopen_commit,
-    .bdrv_reopen_abort   = raw_reopen_abort,
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
     .bdrv_has_zero_init = hdev_has_zero_init,
@@ -1728,9 +1224,6 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_probe_device	= cdrom_probe_device,
     .bdrv_file_open     = cdrom_open,
     .bdrv_close         = raw_close,
-    .bdrv_reopen_prepare = raw_reopen_prepare,
-    .bdrv_reopen_commit  = raw_reopen_commit,
-    .bdrv_reopen_abort   = raw_reopen_abort,
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
     .bdrv_has_zero_init = hdev_has_zero_init,
@@ -1850,9 +1343,6 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_probe_device	= cdrom_probe_device,
     .bdrv_file_open     = cdrom_open,
     .bdrv_close         = raw_close,
-    .bdrv_reopen_prepare = raw_reopen_prepare,
-    .bdrv_reopen_commit  = raw_reopen_commit,
-    .bdrv_reopen_abort   = raw_reopen_abort,
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
     .bdrv_has_zero_init = hdev_has_zero_init,
@@ -1873,40 +1363,6 @@ static BlockDriver bdrv_host_cdrom = {
 };
 #endif /* __FreeBSD__ */
 
-#ifdef CONFIG_LINUX_AIO
-/**
- * Return the file descriptor for Linux AIO
- *
- * This function is a layering violation and should be removed when it becomes
- * possible to call the block layer outside the global mutex.  It allows the
- * caller to hijack the file descriptor so I/O can be performed outside the
- * block layer.
- */
-int raw_get_aio_fd(BlockDriverState *bs)
-{
-    BDRVRawState *s;
-
-    if (!bs->drv) {
-        return -ENOMEDIUM;
-    }
-
-    if (bs->drv == bdrv_find_format("raw")) {
-        bs = bs->file;
-    }
-
-    /* raw-posix has several protocols so just check for raw_aio_readv */
-    if (bs->drv->bdrv_aio_readv != raw_aio_readv) {
-        return -ENOTSUP;
-    }
-
-    s = bs->opaque;
-    if (!s->use_aio) {
-        return -ENOTSUP;
-    }
-    return s->fd;
-}
-#endif /* CONFIG_LINUX_AIO */
-
 static void bdrv_file_init(void)
 {
     /*

block/raw-win32.c

@@ -22,13 +22,9 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "qemu/timer.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "raw-aio.h"
-#include "trace.h"
-#include "block/thread-pool.h"
-#include "qemu/iov.h"
+#include "qemu-timer.h"
+#include "block_int.h"
+#include "module.h"
 #include <windows.h>
 #include <winioctl.h>
 
@@ -36,130 +32,12 @@
 #define FTYPE_CD     1
 #define FTYPE_HARDDISK 2
 
-static QEMUWin32AIOState *aio;
-
-typedef struct RawWin32AIOData {
-    BlockDriverState *bs;
-    HANDLE hfile;
-    struct iovec *aio_iov;
-    int aio_niov;
-    size_t aio_nbytes;
-    off64_t aio_offset;
-    int aio_type;
-} RawWin32AIOData;
-
 typedef struct BDRVRawState {
     HANDLE hfile;
     int type;
     char drive_path[16]; /* format: "d:\" */
-    QEMUWin32AIOState *aio;
 } BDRVRawState;
 
-/*
- * Read/writes the data to/from a given linear buffer.
- *
- * Returns the number of bytes handles or -errno in case of an error. Short
- * reads are only returned if the end of the file is reached.
- */
-static size_t handle_aiocb_rw(RawWin32AIOData *aiocb)
-{
-    size_t offset = 0;
-    int i;
-
-    for (i = 0; i < aiocb->aio_niov; i++) {
-        OVERLAPPED ov;
-        DWORD ret, ret_count, len;
-
-        memset(&ov, 0, sizeof(ov));
-        ov.Offset = (aiocb->aio_offset + offset);
-        ov.OffsetHigh = (aiocb->aio_offset + offset) >> 32;
-        len = aiocb->aio_iov[i].iov_len;
-        if (aiocb->aio_type & QEMU_AIO_WRITE) {
-            ret = WriteFile(aiocb->hfile, aiocb->aio_iov[i].iov_base,
-                            len, &ret_count, &ov);
-        } else {
-            ret = ReadFile(aiocb->hfile, aiocb->aio_iov[i].iov_base,
-                           len, &ret_count, &ov);
-        }
-        if (!ret) {
-            ret_count = 0;
-        }
-        if (ret_count != len) {
-            break;
-        }
-        offset += len;
-    }
-
-    return offset;
-}
-
-static int aio_worker(void *arg)
-{
-    RawWin32AIOData *aiocb = arg;
-    ssize_t ret = 0;
-    size_t count;
-
-    switch (aiocb->aio_type & QEMU_AIO_TYPE_MASK) {
-    case QEMU_AIO_READ:
-        count = handle_aiocb_rw(aiocb);
-        if (count < aiocb->aio_nbytes && aiocb->bs->growable) {
-            /* A short read means that we have reached EOF. Pad the buffer
-             * with zeros for bytes after EOF. */
-            iov_memset(aiocb->aio_iov, aiocb->aio_niov, count,
-                      0, aiocb->aio_nbytes - count);
-
-            count = aiocb->aio_nbytes;
-        }
-        if (count == aiocb->aio_nbytes) {
-            ret = 0;
-        } else {
-            ret = -EINVAL;
-        }
-        break;
-    case QEMU_AIO_WRITE:
-        count = handle_aiocb_rw(aiocb);
-        if (count == aiocb->aio_nbytes) {
-            count = 0;
-        } else {
-            count = -EINVAL;
-        }
-        break;
-    case QEMU_AIO_FLUSH:
-        if (!FlushFileBuffers(aiocb->hfile)) {
-            return -EIO;
-        }
-        break;
-    default:
-        fprintf(stderr, "invalid aio request (0x%x)\n", aiocb->aio_type);
-        ret = -EINVAL;
-        break;
-    }
-
-    g_slice_free(RawWin32AIOData, aiocb);
-    return ret;
-}
-
-static BlockDriverAIOCB *paio_submit(BlockDriverState *bs, HANDLE hfile,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque, int type)
-{
-    RawWin32AIOData *acb = g_slice_new(RawWin32AIOData);
-
-    acb->bs = bs;
-    acb->hfile = hfile;
-    acb->aio_type = type;
-
-    if (qiov) {
-        acb->aio_iov = qiov->iov;
-        acb->aio_niov = qiov->niov;
-    }
-    acb->aio_nbytes = nb_sectors * 512;
-    acb->aio_offset = sector_num * 512;
-
-    trace_paio_submit(acb, opaque, sector_num, nb_sectors, type);
-    return thread_pool_submit_aio(aio_worker, acb, cb, opaque);
-}
-
 int qemu_ftruncate64(int fd, int64_t length)
 {
     LARGE_INTEGER li;
@@ -199,26 +77,6 @@ static int set_sparse(int fd)
 				 NULL, 0, NULL, 0, &returned, NULL);
 }
 
-static void raw_parse_flags(int flags, int *access_flags, DWORD *overlapped)
-{
-    assert(access_flags != NULL);
-    assert(overlapped != NULL);
-
-    if (flags & BDRV_O_RDWR) {
-        *access_flags = GENERIC_READ | GENERIC_WRITE;
-    } else {
-        *access_flags = GENERIC_READ;
-    }
-
-    *overlapped = FILE_ATTRIBUTE_NORMAL;
-    if (flags & BDRV_O_NATIVE_AIO) {
-        *overlapped |= FILE_FLAG_OVERLAPPED;
-    }
-    if (flags & BDRV_O_NOCACHE) {
-        *overlapped |= FILE_FLAG_NO_BUFFERING;
-    }
-}
-
 static int raw_open(BlockDriverState *bs, const char *filename, int flags)
 {
     BDRVRawState *s = bs->opaque;
@@ -227,15 +85,17 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags)
 
     s->type = FTYPE_FILE;
 
-    raw_parse_flags(flags, &access_flags, &overlapped);
-    
-    if ((flags & BDRV_O_NATIVE_AIO) && aio == NULL) {
-        aio = win32_aio_init();
-        if (aio == NULL) {
-            return -EINVAL;
-        }
+    if (flags & BDRV_O_RDWR) {
+        access_flags = GENERIC_READ | GENERIC_WRITE;
+    } else {
+        access_flags = GENERIC_READ;
     }
 
+    overlapped = FILE_ATTRIBUTE_NORMAL;
+    if (flags & BDRV_O_NOCACHE)
+        overlapped |= FILE_FLAG_NO_BUFFERING;
+    if (!(flags & BDRV_O_CACHE_WB))
+        overlapped |= FILE_FLAG_WRITE_THROUGH;
     s->hfile = CreateFile(filename, access_flags,
                           FILE_SHARE_READ, NULL,
                           OPEN_EXISTING, overlapped, NULL);
@@ -244,53 +104,64 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags)
 
         if (err == ERROR_ACCESS_DENIED)
             return -EACCES;
-        return -EINVAL;
-    }
-
-    if (flags & BDRV_O_NATIVE_AIO) {
-        int ret = win32_aio_attach(aio, s->hfile);
-        if (ret < 0) {
-            CloseHandle(s->hfile);
-            return ret;
-        }
-        s->aio = aio;
+        return -1;
     }
     return 0;
 }
 
-static BlockDriverAIOCB *raw_aio_readv(BlockDriverState *bs,
-                         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-                         BlockDriverCompletionFunc *cb, void *opaque)
+static int raw_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
 {
     BDRVRawState *s = bs->opaque;
-    if (s->aio) {
-        return win32_aio_submit(bs, s->aio, s->hfile, sector_num, qiov,
-                                nb_sectors, cb, opaque, QEMU_AIO_READ); 
-    } else {
-        return paio_submit(bs, s->hfile, sector_num, qiov, nb_sectors,
-                           cb, opaque, QEMU_AIO_READ);
-    }
+    OVERLAPPED ov;
+    DWORD ret_count;
+    int ret;
+    int64_t offset = sector_num * 512;
+    int count = nb_sectors * 512;
+
+    memset(&ov, 0, sizeof(ov));
+    ov.Offset = offset;
+    ov.OffsetHigh = offset >> 32;
+    ret = ReadFile(s->hfile, buf, count, &ret_count, &ov);
+    if (!ret)
+        return ret_count;
+    if (ret_count == count)
+        ret_count = 0;
+    return ret_count;
 }
 
-static BlockDriverAIOCB *raw_aio_writev(BlockDriverState *bs,
-                          int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-                          BlockDriverCompletionFunc *cb, void *opaque)
+static int raw_write(BlockDriverState *bs, int64_t sector_num,
+                     const uint8_t *buf, int nb_sectors)
 {
     BDRVRawState *s = bs->opaque;
-    if (s->aio) {
-        return win32_aio_submit(bs, s->aio, s->hfile, sector_num, qiov,
-                                nb_sectors, cb, opaque, QEMU_AIO_WRITE); 
-    } else {
-        return paio_submit(bs, s->hfile, sector_num, qiov, nb_sectors,
-                           cb, opaque, QEMU_AIO_WRITE);
-    }
+    OVERLAPPED ov;
+    DWORD ret_count;
+    int ret;
+    int64_t offset = sector_num * 512;
+    int count = nb_sectors * 512;
+
+    memset(&ov, 0, sizeof(ov));
+    ov.Offset = offset;
+    ov.OffsetHigh = offset >> 32;
+    ret = WriteFile(s->hfile, buf, count, &ret_count, &ov);
+    if (!ret)
+        return ret_count;
+    if (ret_count == count)
+        ret_count = 0;
+    return ret_count;
 }
 
-static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs,
-                         BlockDriverCompletionFunc *cb, void *opaque)
+static int raw_flush(BlockDriverState *bs)
 {
     BDRVRawState *s = bs->opaque;
-    return paio_submit(bs, s->hfile, 0, NULL, 0, cb, opaque, QEMU_AIO_FLUSH);
+    int ret;
+
+    ret = FlushFileBuffers(s->hfile);
+    if (ret == 0) {
+        return -EIO;
+    }
+
+    return 0;
 }
 
 static void raw_close(BlockDriverState *bs)
@@ -303,24 +174,13 @@ static int raw_truncate(BlockDriverState *bs, int64_t offset)
 {
     BDRVRawState *s = bs->opaque;
     LONG low, high;
-    DWORD dwPtrLow;
 
     low = offset;
     high = offset >> 32;
-
-    /*
-     * An error has occurred if the return value is INVALID_SET_FILE_POINTER
-     * and GetLastError doesn't return NO_ERROR.
-     */
-    dwPtrLow = SetFilePointer(s->hfile, low, &high, FILE_BEGIN);
-    if (dwPtrLow == INVALID_SET_FILE_POINTER && GetLastError() != NO_ERROR) {
-        fprintf(stderr, "SetFilePointer error: %lu\n", GetLastError());
+    if (!SetFilePointer(s->hfile, low, &high, FILE_BEGIN))
+	return -EIO;
+    if (!SetEndOfFile(s->hfile))
         return -EIO;
-    }
-    if (SetEndOfFile(s->hfile) == 0) {
-        fprintf(stderr, "SetEndOfFile error: %lu\n", GetLastError());
-        return -EIO;
-    }
     return 0;
 }
 
@@ -422,9 +282,9 @@ static BlockDriver bdrv_file = {
     .bdrv_close		= raw_close,
     .bdrv_create	= raw_create,
 
-    .bdrv_aio_readv     = raw_aio_readv,
-    .bdrv_aio_writev    = raw_aio_writev,
-    .bdrv_aio_flush     = raw_aio_flush,
+    .bdrv_read              = raw_read,
+    .bdrv_write             = raw_write,
+    .bdrv_co_flush_to_disk  = raw_flush,
 
     .bdrv_truncate	= raw_truncate,
     .bdrv_getlength	= raw_getlength,
@@ -514,10 +374,18 @@ static int hdev_open(BlockDriverState *bs, const char *filename, int flags)
     }
     s->type = find_device_type(bs, filename);
 
-    raw_parse_flags(flags, &access_flags, &overlapped);
-
+    if (flags & BDRV_O_RDWR) {
+        access_flags = GENERIC_READ | GENERIC_WRITE;
+    } else {
+        access_flags = GENERIC_READ;
+    }
     create_flags = OPEN_EXISTING;
 
+    overlapped = FILE_ATTRIBUTE_NORMAL;
+    if (flags & BDRV_O_NOCACHE)
+        overlapped |= FILE_FLAG_NO_BUFFERING;
+    if (!(flags & BDRV_O_CACHE_WB))
+        overlapped |= FILE_FLAG_WRITE_THROUGH;
     s->hfile = CreateFile(filename, access_flags,
                           FILE_SHARE_READ, NULL,
                           create_flags, overlapped, NULL);
@@ -545,9 +413,9 @@ static BlockDriver bdrv_host_device = {
     .bdrv_close		= raw_close,
     .bdrv_has_zero_init = hdev_has_zero_init,
 
-    .bdrv_aio_readv     = raw_aio_readv,
-    .bdrv_aio_writev    = raw_aio_writev,
-    .bdrv_aio_flush     = raw_aio_flush,
+    .bdrv_read              = raw_read,
+    .bdrv_write             = raw_write,
+    .bdrv_co_flush_to_disk  = raw_flush,
 
     .bdrv_getlength	= raw_getlength,
     .bdrv_get_allocated_file_size

block/raw.c

@@ -1,7 +1,7 @@
 
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
+#include "block_int.h"
+#include "module.h"
 
 static int raw_open(BlockDriverState *bs, int flags)
 {
@@ -9,14 +9,6 @@ static int raw_open(BlockDriverState *bs, int flags)
     return 0;
 }
 
-/* We have nothing to do for raw reopen, stubs just return
- * success */
-static int raw_reopen_prepare(BDRVReopenState *state,
-                              BlockReopenQueue *queue,  Error **errp)
-{
-    return 0;
-}
-
 static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num,
                                      int nb_sectors, QEMUIOVector *qiov)
 {
@@ -123,8 +115,6 @@ static BlockDriver bdrv_raw = {
     .bdrv_open          = raw_open,
     .bdrv_close         = raw_close,
 
-    .bdrv_reopen_prepare  = raw_reopen_prepare,
-
     .bdrv_co_readv          = raw_co_readv,
     .bdrv_co_writev         = raw_co_writev,
     .bdrv_co_is_allocated   = raw_co_is_allocated,

block/rbd.c

@@ -14,8 +14,8 @@
 #include <inttypes.h>
 
 #include "qemu-common.h"
-#include "qemu/error-report.h"
-#include "block/block_int.h"
+#include "qemu-error.h"
+#include "block_int.h"
 
 #include <rbd/librbd.h>
 
@@ -69,7 +69,7 @@ typedef enum {
 typedef struct RBDAIOCB {
     BlockDriverAIOCB common;
     QEMUBH *bh;
-    int64_t ret;
+    int ret;
     QEMUIOVector *qiov;
     char *bounce;
     RBDAIOCmd cmd;
@@ -77,7 +77,6 @@ typedef struct RBDAIOCB {
     int error;
     struct BDRVRBDState *s;
     int cancelled;
-    int status;
 } RBDAIOCB;
 
 typedef struct RADOSCB {
@@ -87,7 +86,7 @@ typedef struct RADOSCB {
     int done;
     int64_t size;
     char *buf;
-    int64_t ret;
+    int ret;
 } RADOSCB;
 
 #define RBD_FD_READ 0
@@ -377,6 +376,12 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
     RBDAIOCB *acb = rcb->acb;
     int64_t r;
 
+    if (acb->cancelled) {
+        qemu_vfree(acb->bounce);
+        qemu_aio_release(acb);
+        goto done;
+    }
+
     r = rcb->ret;
 
     if (acb->cmd == RBD_AIO_WRITE ||
@@ -404,6 +409,7 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
     /* Note that acb->bh can be NULL in case where the aio was cancelled */
     acb->bh = qemu_bh_new(rbd_aio_bh_cb, acb);
     qemu_bh_schedule(acb->bh);
+done:
     g_free(rcb);
 }
 
@@ -481,6 +487,12 @@ static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags)
         rados_conf_set(s->cluster, "rbd_cache", "false");
     } else {
         rados_conf_set(s->cluster, "rbd_cache", "true");
+        if (!(flags & BDRV_O_CACHE_WB)) {
+            r = rados_conf_set(s->cluster, "rbd_cache_max_dirty", "0");
+            if (r < 0) {
+                rados_conf_set(s->cluster, "rbd_cache", "false");
+            }
+        }
     }
 
     if (strstr(conf, "conf=") == NULL) {
@@ -562,15 +574,9 @@ static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     RBDAIOCB *acb = (RBDAIOCB *) blockacb;
     acb->cancelled = 1;
-
-    while (acb->status == -EINPROGRESS) {
-        qemu_aio_wait();
-    }
-
-    qemu_aio_release(acb);
 }
 
-static const AIOCBInfo rbd_aiocb_info = {
+static AIOPool rbd_aio_pool = {
     .aiocb_size = sizeof(RBDAIOCB),
     .cancel = qemu_rbd_aio_cancel,
 };
@@ -639,11 +645,8 @@ static void rbd_aio_bh_cb(void *opaque)
     acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
     qemu_bh_delete(acb->bh);
     acb->bh = NULL;
-    acb->status = 0;
 
-    if (!acb->cancelled) {
-        qemu_aio_release(acb);
-    }
+    qemu_aio_release(acb);
 }
 
 static int rbd_aio_discard_wrapper(rbd_image_t image,
@@ -675,7 +678,7 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
 
     BDRVRBDState *s = bs->opaque;
 
-    acb = qemu_aio_get(&rbd_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&rbd_aio_pool, bs, cb, opaque);
     acb->cmd = cmd;
     acb->qiov = qiov;
     if (cmd == RBD_AIO_DISCARD) {
@@ -688,7 +691,6 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
     acb->s = s;
     acb->cancelled = 0;
     acb->bh = NULL;
-    acb->status = -EINPROGRESS;
 
     if (cmd == RBD_AIO_WRITE) {
         qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);

block/sheepdog.c

@@ -13,10 +13,10 @@
  */
 
 #include "qemu-common.h"
-#include "qemu/error-report.h"
-#include "qemu/sockets.h"
-#include "block/block_int.h"
-#include "qemu/bitops.h"
+#include "qemu-error.h"
+#include "qemu_socket.h"
+#include "block_int.h"
+#include "bitops.h"
 
 #define SD_PROTO_VER 0x01
 
@@ -36,8 +36,7 @@
 
 #define SD_FLAG_CMD_WRITE    0x01
 #define SD_FLAG_CMD_COW      0x02
-#define SD_FLAG_CMD_CACHE    0x04 /* Writeback mode for cache */
-#define SD_FLAG_CMD_DIRECT   0x08 /* Don't use cache */
+#define SD_FLAG_CMD_CACHE    0x04
 
 #define SD_RES_SUCCESS       0x00 /* Success */
 #define SD_RES_UNKNOWN       0x01 /* Unknown error */
@@ -145,7 +144,7 @@ typedef struct SheepdogVdiReq {
     uint32_t id;
     uint32_t data_length;
     uint64_t vdi_size;
-    uint32_t vdi_id;
+    uint32_t base_vdi_id;
     uint32_t copies;
     uint32_t snapid;
     uint32_t pad[3];
@@ -202,12 +201,12 @@ static inline uint64_t fnv_64a_buf(void *buf, size_t len, uint64_t hval)
     return hval;
 }
 
-static inline bool is_data_obj_writable(SheepdogInode *inode, unsigned int idx)
+static inline int is_data_obj_writable(SheepdogInode *inode, unsigned int idx)
 {
     return inode->vdi_id == inode->data_vdi_id[idx];
 }
 
-static inline bool is_data_obj(uint64_t oid)
+static inline int is_data_obj(uint64_t oid)
 {
     return !(VDI_BIT & oid);
 }
@@ -232,7 +231,7 @@ static inline uint64_t vid_to_data_oid(uint32_t vid, uint32_t idx)
     return ((uint64_t)vid << VDI_SPACE_SHIFT) | idx;
 }
 
-static inline bool is_snapshot(struct SheepdogInode *inode)
+static inline int is_snapshot(struct SheepdogInode *inode)
 {
     return !!inode->snap_ctime;
 }
@@ -266,7 +265,6 @@ typedef struct AIOReq {
 enum AIOCBState {
     AIOCB_WRITE_UDATA,
     AIOCB_READ_UDATA,
-    AIOCB_FLUSH_CACHE,
 };
 
 struct SheepdogAIOCB {
@@ -283,7 +281,7 @@ struct SheepdogAIOCB {
     Coroutine *coroutine;
     void (*aio_done_func)(SheepdogAIOCB *);
 
-    bool canceled;
+    int canceled;
     int nr_pending;
 };
 
@@ -294,12 +292,13 @@ typedef struct BDRVSheepdogState {
     uint32_t max_dirty_data_idx;
 
     char name[SD_MAX_VDI_LEN];
-    bool is_snapshot;
-    uint32_t cache_flags;
+    int is_snapshot;
+    uint8_t cache_enabled;
 
     char *addr;
     char *port;
     int fd;
+    int flush_fd;
 
     CoMutex lock;
     Coroutine *co_send;
@@ -418,20 +417,21 @@ static void sd_aio_cancel(BlockDriverAIOCB *blockacb)
      */
     acb->ret = -EIO;
     qemu_coroutine_enter(acb->coroutine, NULL);
-    acb->canceled = true;
+    acb->canceled = 1;
 }
 
-static const AIOCBInfo sd_aiocb_info = {
+static AIOPool sd_aio_pool = {
     .aiocb_size = sizeof(SheepdogAIOCB),
     .cancel = sd_aio_cancel,
 };
 
 static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
-                                   int64_t sector_num, int nb_sectors)
+                                   int64_t sector_num, int nb_sectors,
+                                   BlockDriverCompletionFunc *cb, void *opaque)
 {
     SheepdogAIOCB *acb;
 
-    acb = qemu_aio_get(&sd_aiocb_info, bs, NULL, NULL);
+    acb = qemu_aio_get(&sd_aio_pool, bs, cb, opaque);
 
     acb->qiov = qiov;
 
@@ -439,7 +439,7 @@ static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
     acb->nb_sectors = nb_sectors;
 
     acb->aio_done_func = NULL;
-    acb->canceled = false;
+    acb->canceled = 0;
     acb->coroutine = qemu_coroutine_self();
     acb->ret = 0;
     acb->nr_pending = 0;
@@ -549,7 +549,7 @@ static coroutine_fn void do_co_req(void *opaque)
     co = qemu_coroutine_self();
     qemu_aio_set_fd_handler(sockfd, NULL, restart_co_req, NULL, co);
 
-    qemu_set_block(sockfd);
+    socket_set_block(sockfd);
     ret = send_co_req(sockfd, hdr, data, wlen);
     if (ret < 0) {
         goto out;
@@ -579,7 +579,7 @@ static coroutine_fn void do_co_req(void *opaque)
     ret = 0;
 out:
     qemu_aio_set_fd_handler(sockfd, NULL, NULL, NULL, NULL);
-    qemu_set_nonblock(sockfd);
+    socket_set_nonblock(sockfd);
 
     srco->ret = ret;
     srco->finished = true;
@@ -613,7 +613,7 @@ static int do_req(int sockfd, SheepdogReq *hdr, void *data,
 }
 
 static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
-                           struct iovec *iov, int niov, bool create,
+                           struct iovec *iov, int niov, int create,
                            enum AIOCBState aiocb_type);
 
 
@@ -646,7 +646,7 @@ static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid)
         QLIST_REMOVE(aio_req, aio_siblings);
         QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
         ret = add_aio_request(s, aio_req, acb->qiov->iov,
-                              acb->qiov->niov, false, acb->aiocb_type);
+                              acb->qiov->niov, 0, acb->aiocb_type);
         if (ret < 0) {
             error_report("add_aio_request is failed");
             free_aio_req(s, aio_req);
@@ -714,17 +714,16 @@ static void coroutine_fn aio_read_response(void *opaque)
              * and max_dirty_data_idx are changed to include updated
              * index between them.
              */
-            if (rsp.result == SD_RES_SUCCESS) {
-                s->inode.data_vdi_id[idx] = s->inode.vdi_id;
-                s->max_dirty_data_idx = MAX(idx, s->max_dirty_data_idx);
-                s->min_dirty_data_idx = MIN(idx, s->min_dirty_data_idx);
-            }
+            s->inode.data_vdi_id[idx] = s->inode.vdi_id;
+            s->max_dirty_data_idx = MAX(idx, s->max_dirty_data_idx);
+            s->min_dirty_data_idx = MIN(idx, s->min_dirty_data_idx);
+
             /*
              * Some requests may be blocked because simultaneous
              * create requests are not allowed, so we search the
              * pending requests here.
              */
-            send_pending_req(s, aio_req->oid);
+            send_pending_req(s, vid_to_data_oid(s->inode.vdi_id, idx));
         }
         break;
     case AIOCB_READ_UDATA:
@@ -735,13 +734,6 @@ static void coroutine_fn aio_read_response(void *opaque)
             goto out;
         }
         break;
-    case AIOCB_FLUSH_CACHE:
-        if (rsp.result == SD_RES_INVALID_PARMS) {
-            dprintf("disable cache since the server doesn't support it\n");
-            s->cache_flags = SD_FLAG_CMD_DIRECT;
-            rsp.result = SD_RES_SUCCESS;
-        }
-        break;
     }
 
     if (rsp.result != SD_RES_SUCCESS) {
@@ -812,7 +804,7 @@ static int get_sheep_fd(BDRVSheepdogState *s)
         return fd;
     }
 
-    qemu_set_nonblock(fd);
+    socket_set_nonblock(fd);
 
     ret = set_nodelay(fd);
     if (ret) {
@@ -874,14 +866,14 @@ static int parse_vdiname(BDRVSheepdogState *s, const char *filename,
         s->port = 0;
     }
 
-    pstrcpy(vdi, SD_MAX_VDI_LEN, p);
+    strncpy(vdi, p, SD_MAX_VDI_LEN);
 
     p = strchr(vdi, ':');
     if (p) {
         *p++ = '\0';
         *snapid = strtoul(p, NULL, 10);
         if (*snapid == 0) {
-            pstrcpy(tag, SD_MAX_VDI_TAG_LEN, p);
+            strncpy(tag, p, SD_MAX_VDI_TAG_LEN);
         }
     } else {
         *snapid = CURRENT_VDI_ID; /* search current vdi */
@@ -908,10 +900,7 @@ static int find_vdi_name(BDRVSheepdogState *s, char *filename, uint32_t snapid,
         return fd;
     }
 
-    /* This pair of strncpy calls ensures that the buffer is zero-filled,
-     * which is desirable since we'll soon be sending those bytes, and
-     * don't want the send_req to read uninitialized data.
-     */
+    memset(buf, 0, sizeof(buf));
     strncpy(buf, filename, SD_MAX_VDI_LEN);
     strncpy(buf + SD_MAX_VDI_LEN, tag, SD_MAX_VDI_TAG_LEN);
 
@@ -951,12 +940,12 @@ out:
 }
 
 static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
-                           struct iovec *iov, int niov, bool create,
+                           struct iovec *iov, int niov, int create,
                            enum AIOCBState aiocb_type)
 {
     int nr_copies = s->inode.nr_copies;
     SheepdogObjReq hdr;
-    unsigned int wlen = 0;
+    unsigned int wlen;
     int ret;
     uint64_t oid = aio_req->oid;
     unsigned int datalen = aio_req->data_len;
@@ -970,27 +959,22 @@ static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
 
     memset(&hdr, 0, sizeof(hdr));
 
-    switch (aiocb_type) {
-    case AIOCB_FLUSH_CACHE:
-        hdr.opcode = SD_OP_FLUSH_VDI;
-        break;
-    case AIOCB_READ_UDATA:
+    if (aiocb_type == AIOCB_READ_UDATA) {
+        wlen = 0;
         hdr.opcode = SD_OP_READ_OBJ;
         hdr.flags = flags;
-        break;
-    case AIOCB_WRITE_UDATA:
-        if (create) {
-            hdr.opcode = SD_OP_CREATE_AND_WRITE_OBJ;
-        } else {
-            hdr.opcode = SD_OP_WRITE_OBJ;
-        }
+    } else if (create) {
         wlen = datalen;
+        hdr.opcode = SD_OP_CREATE_AND_WRITE_OBJ;
+        hdr.flags = SD_FLAG_CMD_WRITE | flags;
+    } else {
+        wlen = datalen;
+        hdr.opcode = SD_OP_WRITE_OBJ;
         hdr.flags = SD_FLAG_CMD_WRITE | flags;
-        break;
     }
 
-    if (s->cache_flags) {
-        hdr.flags |= s->cache_flags;
+    if (s->cache_enabled) {
+        hdr.flags |= SD_FLAG_CMD_CACHE;
     }
 
     hdr.oid = oid;
@@ -1035,7 +1019,7 @@ static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
 
 static int read_write_object(int fd, char *buf, uint64_t oid, int copies,
                              unsigned int datalen, uint64_t offset,
-                             bool write, bool create, uint32_t cache_flags)
+                             int write, int create, uint8_t cache)
 {
     SheepdogObjReq hdr;
     SheepdogObjRsp *rsp = (SheepdogObjRsp *)&hdr;
@@ -1059,7 +1043,9 @@ static int read_write_object(int fd, char *buf, uint64_t oid, int copies,
         hdr.opcode = SD_OP_READ_OBJ;
     }
 
-    hdr.flags |= cache_flags;
+    if (cache) {
+        hdr.flags |= SD_FLAG_CMD_CACHE;
+    }
 
     hdr.oid = oid;
     hdr.data_length = datalen;
@@ -1082,19 +1068,18 @@ static int read_write_object(int fd, char *buf, uint64_t oid, int copies,
 }
 
 static int read_object(int fd, char *buf, uint64_t oid, int copies,
-                       unsigned int datalen, uint64_t offset,
-                       uint32_t cache_flags)
+                       unsigned int datalen, uint64_t offset, uint8_t cache)
 {
-    return read_write_object(fd, buf, oid, copies, datalen, offset, false,
-                             false, cache_flags);
+    return read_write_object(fd, buf, oid, copies, datalen, offset, 0, 0,
+                             cache);
 }
 
 static int write_object(int fd, char *buf, uint64_t oid, int copies,
-                        unsigned int datalen, uint64_t offset, bool create,
-                        uint32_t cache_flags)
+                        unsigned int datalen, uint64_t offset, int create,
+                        uint8_t cache)
 {
-    return read_write_object(fd, buf, oid, copies, datalen, offset, true,
-                             create, cache_flags);
+    return read_write_object(fd, buf, oid, copies, datalen, offset, 1, create,
+                             cache);
 }
 
 static int sd_open(BlockDriverState *bs, const char *filename, int flags)
@@ -1129,18 +1114,19 @@ static int sd_open(BlockDriverState *bs, const char *filename, int flags)
         goto out;
     }
 
-    /*
-     * QEMU block layer emulates writethrough cache as 'writeback + flush', so
-     * we always set SD_FLAG_CMD_CACHE (writeback cache) as default.
-     */
-    s->cache_flags = SD_FLAG_CMD_CACHE;
-    if (flags & BDRV_O_NOCACHE) {
-        s->cache_flags = SD_FLAG_CMD_DIRECT;
+    if (flags & BDRV_O_CACHE_WB) {
+        s->cache_enabled = 1;
+        s->flush_fd = connect_to_sdog(s->addr, s->port);
+        if (s->flush_fd < 0) {
+            error_report("failed to connect");
+            ret = s->flush_fd;
+            goto out;
+        }
     }
 
     if (snapid || tag[0] != '\0') {
         dprintf("%" PRIx32 " snapshot inode was open.\n", vid);
-        s->is_snapshot = true;
+        s->is_snapshot = 1;
     }
 
     fd = connect_to_sdog(s->addr, s->port);
@@ -1152,7 +1138,7 @@ static int sd_open(BlockDriverState *bs, const char *filename, int flags)
 
     buf = g_malloc(SD_INODE_SIZE);
     ret = read_object(fd, buf, vid_to_vdi_oid(vid), 0, SD_INODE_SIZE, 0,
-                      s->cache_flags);
+                      s->cache_enabled);
 
     closesocket(fd);
 
@@ -1165,7 +1151,7 @@ static int sd_open(BlockDriverState *bs, const char *filename, int flags)
     s->max_dirty_data_idx = 0;
 
     bs->total_sectors = s->inode.vdi_size / SECTOR_SIZE;
-    pstrcpy(s->name, sizeof(s->name), vdi);
+    strncpy(s->name, vdi, sizeof(s->name));
     qemu_co_mutex_init(&s->lock);
     g_free(buf);
     return 0;
@@ -1193,15 +1179,12 @@ static int do_sd_create(char *filename, int64_t vdi_size,
         return fd;
     }
 
-    /* FIXME: would it be better to fail (e.g., return -EIO) when filename
-     * does not fit in buf?  For now, just truncate and avoid buffer overrun.
-     */
     memset(buf, 0, sizeof(buf));
-    pstrcpy(buf, sizeof(buf), filename);
+    strncpy(buf, filename, SD_MAX_VDI_LEN);
 
     memset(&hdr, 0, sizeof(hdr));
     hdr.opcode = SD_OP_NEW_VDI;
-    hdr.vdi_id = base_vid;
+    hdr.base_vdi_id = base_vid;
 
     wlen = SD_MAX_VDI_LEN;
 
@@ -1283,7 +1266,7 @@ static int sd_create(const char *filename, QEMUOptionParameter *options)
     BDRVSheepdogState *s;
     char vdi[SD_MAX_VDI_LEN], tag[SD_MAX_VDI_TAG_LEN];
     uint32_t snapid;
-    bool prealloc = false;
+    int prealloc = 0;
     const char *vdiname;
 
     s = g_malloc0(sizeof(BDRVSheepdogState));
@@ -1305,9 +1288,9 @@ static int sd_create(const char *filename, QEMUOptionParameter *options)
             backing_file = options->value.s;
         } else if (!strcmp(options->name, BLOCK_OPT_PREALLOC)) {
             if (!options->value.s || !strcmp(options->value.s, "off")) {
-                prealloc = false;
+                prealloc = 0;
             } else if (!strcmp(options->value.s, "full")) {
-                prealloc = true;
+                prealloc = 1;
             } else {
                 error_report("Invalid preallocation mode: '%s'",
                              options->value.s);
@@ -1384,7 +1367,6 @@ static void sd_close(BlockDriverState *bs)
     memset(&hdr, 0, sizeof(hdr));
 
     hdr.opcode = SD_OP_RELEASE_VDI;
-    hdr.vdi_id = s->inode.vdi_id;
     wlen = strlen(s->name) + 1;
     hdr.data_length = wlen;
     hdr.flags = SD_FLAG_CMD_WRITE;
@@ -1400,6 +1382,9 @@ static void sd_close(BlockDriverState *bs)
 
     qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL, NULL);
     closesocket(s->fd);
+    if (s->cache_enabled) {
+        closesocket(s->flush_fd);
+    }
     g_free(s->addr);
 }
 
@@ -1433,7 +1418,7 @@ static int sd_truncate(BlockDriverState *bs, int64_t offset)
     datalen = SD_INODE_SIZE - sizeof(s->inode.data_vdi_id);
     s->inode.vdi_size = offset;
     ret = write_object(fd, (char *)&s->inode, vid_to_vdi_oid(s->inode.vdi_id),
-                       s->inode.nr_copies, datalen, 0, false, s->cache_flags);
+                       s->inode.nr_copies, datalen, 0, 0, s->cache_enabled);
     close(fd);
 
     if (ret < 0) {
@@ -1472,7 +1457,7 @@ static void coroutine_fn sd_write_done(SheepdogAIOCB *acb)
         aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id),
                                 data_len, offset, 0, 0, offset);
         QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
-        ret = add_aio_request(s, aio_req, &iov, 1, false, AIOCB_WRITE_UDATA);
+        ret = add_aio_request(s, aio_req, &iov, 1, 0, AIOCB_WRITE_UDATA);
         if (ret) {
             free_aio_req(s, aio_req);
             acb->ret = -EIO;
@@ -1516,7 +1501,7 @@ static int sd_create_branch(BDRVSheepdogState *s)
     }
 
     ret = read_object(fd, buf, vid_to_vdi_oid(vid), s->inode.nr_copies,
-                      SD_INODE_SIZE, 0, s->cache_flags);
+                      SD_INODE_SIZE, 0, s->cache_enabled);
 
     closesocket(fd);
 
@@ -1526,7 +1511,7 @@ static int sd_create_branch(BDRVSheepdogState *s)
 
     memcpy(&s->inode, buf, sizeof(s->inode));
 
-    s->is_snapshot = false;
+    s->is_snapshot = 0;
     ret = 0;
     dprintf("%" PRIx32 " was newly created.\n", s->inode.vdi_id);
 
@@ -1581,7 +1566,7 @@ static int coroutine_fn sd_co_rw_vector(void *p)
     while (done != total) {
         uint8_t flags = 0;
         uint64_t old_oid = 0;
-        bool create = false;
+        int create = 0;
 
         oid = vid_to_data_oid(inode->data_vdi_id[idx], idx);
 
@@ -1596,10 +1581,10 @@ static int coroutine_fn sd_co_rw_vector(void *p)
             break;
         case AIOCB_WRITE_UDATA:
             if (!inode->data_vdi_id[idx]) {
-                create = true;
+                create = 1;
             } else if (!is_data_obj_writable(inode, idx)) {
                 /* Copy-On-Write */
-                create = true;
+                create = 1;
                 old_oid = oid;
                 flags = SD_FLAG_CMD_COW;
             }
@@ -1672,7 +1657,7 @@ static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
         bs->total_sectors = sector_num + nb_sectors;
     }
 
-    acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
+    acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, NULL, NULL);
     acb->aio_done_func = sd_write_done;
     acb->aiocb_type = AIOCB_WRITE_UDATA;
 
@@ -1693,7 +1678,7 @@ static coroutine_fn int sd_co_readv(BlockDriverState *bs, int64_t sector_num,
     SheepdogAIOCB *acb;
     int ret;
 
-    acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
+    acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors, NULL, NULL);
     acb->aiocb_type = AIOCB_READ_UDATA;
     acb->aio_done_func = sd_finish_aiocb;
 
@@ -1711,31 +1696,39 @@ static coroutine_fn int sd_co_readv(BlockDriverState *bs, int64_t sector_num,
 static int coroutine_fn sd_co_flush_to_disk(BlockDriverState *bs)
 {
     BDRVSheepdogState *s = bs->opaque;
-    SheepdogAIOCB *acb;
-    AIOReq *aio_req;
+    SheepdogObjReq hdr = { 0 };
+    SheepdogObjRsp *rsp = (SheepdogObjRsp *)&hdr;
+    SheepdogInode *inode = &s->inode;
     int ret;
+    unsigned int wlen = 0, rlen = 0;
 
-    if (s->cache_flags != SD_FLAG_CMD_CACHE) {
+    if (!s->cache_enabled) {
         return 0;
     }
 
-    acb = sd_aio_setup(bs, NULL, 0, 0);
-    acb->aiocb_type = AIOCB_FLUSH_CACHE;
-    acb->aio_done_func = sd_finish_aiocb;
+    hdr.opcode = SD_OP_FLUSH_VDI;
+    hdr.oid = vid_to_vdi_oid(inode->vdi_id);
 
-    aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id),
-                            0, 0, 0, 0, 0);
-    QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
-    ret = add_aio_request(s, aio_req, NULL, 0, false, acb->aiocb_type);
-    if (ret < 0) {
-        error_report("add_aio_request is failed");
-        free_aio_req(s, aio_req);
-        qemu_aio_release(acb);
+    ret = do_req(s->flush_fd, (SheepdogReq *)&hdr, NULL, &wlen, &rlen);
+    if (ret) {
+        error_report("failed to send a request to the sheep");
         return ret;
     }
 
-    qemu_coroutine_yield();
-    return acb->ret;
+    if (rsp->result == SD_RES_INVALID_PARMS) {
+        dprintf("disable write cache since the server doesn't support it\n");
+
+        s->cache_enabled = 0;
+        closesocket(s->flush_fd);
+        return 0;
+    }
+
+    if (rsp->result != SD_RES_SUCCESS) {
+        error_report("%s", sd_strerror(rsp->result));
+        return -EIO;
+    }
+
+    return 0;
 }
 
 static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
@@ -1761,9 +1754,6 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
 
     s->inode.vm_state_size = sn_info->vm_state_size;
     s->inode.vm_clock_nsec = sn_info->vm_clock_nsec;
-    /* It appears that inode.tag does not require a NUL terminator,
-     * which means this use of strncpy is ok.
-     */
     strncpy(s->inode.tag, sn_info->name, sizeof(s->inode.tag));
     /* we don't need to update entire object */
     datalen = SD_INODE_SIZE - sizeof(s->inode.data_vdi_id);
@@ -1776,7 +1766,7 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     }
 
     ret = write_object(fd, (char *)&s->inode, vid_to_vdi_oid(s->inode.vdi_id),
-                       s->inode.nr_copies, datalen, 0, false, s->cache_flags);
+                       s->inode.nr_copies, datalen, 0, 0, s->cache_enabled);
     if (ret < 0) {
         error_report("failed to write snapshot's inode.");
         goto cleanup;
@@ -1793,7 +1783,7 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     inode = (SheepdogInode *)g_malloc(datalen);
 
     ret = read_object(fd, (char *)inode, vid_to_vdi_oid(new_vid),
-                      s->inode.nr_copies, datalen, 0, s->cache_flags);
+                      s->inode.nr_copies, datalen, 0, s->cache_enabled);
 
     if (ret < 0) {
         error_report("failed to read new inode info. %s", strerror(errno));
@@ -1823,13 +1813,13 @@ static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
 
     memcpy(old_s, s, sizeof(BDRVSheepdogState));
 
-    pstrcpy(vdi, sizeof(vdi), s->name);
+    memset(vdi, 0, sizeof(vdi));
+    strncpy(vdi, s->name, sizeof(vdi));
 
+    memset(tag, 0, sizeof(tag));
     snapid = strtoul(snapshot_id, NULL, 10);
-    if (snapid) {
-        tag[0] = 0;
-    } else {
-        pstrcpy(tag, sizeof(tag), s->name);
+    if (!snapid) {
+        strncpy(tag, s->name, sizeof(tag));
     }
 
     ret = find_vdi_name(s, vdi, snapid, tag, &vid, 1);
@@ -1847,7 +1837,7 @@ static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
 
     buf = g_malloc(SD_INODE_SIZE);
     ret = read_object(fd, buf, vid_to_vdi_oid(vid), s->inode.nr_copies,
-                      SD_INODE_SIZE, 0, s->cache_flags);
+                      SD_INODE_SIZE, 0, s->cache_enabled);
 
     closesocket(fd);
 
@@ -1863,7 +1853,7 @@ static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
         goto out;
     }
 
-    s->is_snapshot = true;
+    s->is_snapshot = 1;
 
     g_free(buf);
     g_free(old_s);
@@ -1944,7 +1934,7 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
         /* we don't need to read entire object */
         ret = read_object(fd, (char *)&inode, vid_to_vdi_oid(vid),
                           0, SD_INODE_SIZE - sizeof(inode.data_vdi_id), 0,
-                          s->cache_flags);
+                          s->cache_enabled);
 
         if (ret) {
             continue;
@@ -1958,9 +1948,8 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
 
             snprintf(sn_tab[found].id_str, sizeof(sn_tab[found].id_str), "%u",
                      inode.snap_id);
-            pstrcpy(sn_tab[found].name,
-                    MIN(sizeof(sn_tab[found].name), sizeof(inode.tag)),
-                    inode.tag);
+            strncpy(sn_tab[found].name, inode.tag,
+                    MIN(sizeof(sn_tab[found].name), sizeof(inode.tag)));
             found++;
         }
     }
@@ -1981,8 +1970,8 @@ out:
 static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data,
                                 int64_t pos, int size, int load)
 {
-    bool create;
-    int fd, ret = 0, remaining = size;
+    int fd, create;
+    int ret = 0, remaining = size;
     unsigned int data_len;
     uint64_t vmstate_oid;
     uint32_t vdi_index;
@@ -2005,11 +1994,11 @@ static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data,
         if (load) {
             ret = read_object(fd, (char *)data, vmstate_oid,
                               s->inode.nr_copies, data_len, offset,
-                              s->cache_flags);
+                              s->cache_enabled);
         } else {
             ret = write_object(fd, (char *)data, vmstate_oid,
                                s->inode.nr_copies, data_len, offset, create,
-                               s->cache_flags);
+                               s->cache_enabled);
         }
 
         if (ret < 0) {

block/stream.c

@@ -12,8 +12,7 @@
  */
 
 #include "trace.h"
-#include "block/block_int.h"
-#include "block/blockjob.h"
+#include "block_int.h"
 #include "qemu/ratelimit.h"
 
 enum {
@@ -31,7 +30,6 @@ typedef struct StreamBlockJob {
     BlockJob common;
     RateLimit limit;
     BlockDriverState *base;
-    BlockdevOnError on_error;
     char backing_file_id[1024];
 } StreamBlockJob;
 
@@ -79,14 +77,13 @@ static void coroutine_fn stream_run(void *opaque)
     BlockDriverState *bs = s->common.bs;
     BlockDriverState *base = s->base;
     int64_t sector_num, end;
-    int error = 0;
     int ret = 0;
     int n = 0;
     void *buf;
 
     s->common.len = bdrv_getlength(bs);
     if (s->common.len < 0) {
-        block_job_completed(&s->common, s->common.len);
+        block_job_complete(&s->common, s->common.len);
         return;
     }
 
@@ -108,7 +105,7 @@ static void coroutine_fn stream_run(void *opaque)
 
 wait:
         /* Note that even when no rate limit is applied we need to yield
-         * with no pending I/O here so that bdrv_drain_all() returns.
+         * with no pending I/O here so that qemu_aio_flush() returns.
          */
         block_job_sleep_ns(&s->common, rt_clock, delay_ns);
         if (block_job_is_cancelled(&s->common)) {
@@ -144,19 +141,7 @@ wait:
             ret = stream_populate(bs, sector_num, n, buf);
         }
         if (ret < 0) {
-            BlockErrorAction action =
-                block_job_error_action(&s->common, s->common.bs, s->on_error,
-                                       true, -ret);
-            if (action == BDRV_ACTION_STOP) {
-                n = 0;
-                continue;
-            }
-            if (error == 0) {
-                error = ret;
-            }
-            if (action == BDRV_ACTION_REPORT) {
-                break;
-            }
+            break;
         }
         ret = 0;
 
@@ -168,9 +153,6 @@ wait:
         bdrv_disable_copy_on_read(bs);
     }
 
-    /* Do not remove the backing file if an error was there but ignored.  */
-    ret = error;
-
     if (!block_job_is_cancelled(&s->common) && sector_num == end && ret == 0) {
         const char *base_id = NULL, *base_fmt = NULL;
         if (base) {
@@ -184,7 +166,7 @@ wait:
     }
 
     qemu_vfree(buf);
-    block_job_completed(&s->common, ret);
+    block_job_complete(&s->common, ret);
 }
 
 static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -206,19 +188,11 @@ static BlockJobType stream_job_type = {
 
 void stream_start(BlockDriverState *bs, BlockDriverState *base,
                   const char *base_id, int64_t speed,
-                  BlockdevOnError on_error,
                   BlockDriverCompletionFunc *cb,
                   void *opaque, Error **errp)
 {
     StreamBlockJob *s;
 
-    if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
-         on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
-        error_set(errp, QERR_INVALID_PARAMETER, "on-error");
-        return;
-    }
-
     s = block_job_create(&stream_job_type, bs, speed, cb, opaque, errp);
     if (!s) {
         return;
@@ -229,7 +203,6 @@ void stream_start(BlockDriverState *bs, BlockDriverState *base,
         pstrcpy(s->backing_file_id, sizeof(s->backing_file_id), base_id);
     }
 
-    s->on_error = on_error;
     s->common.co = qemu_coroutine_create(stream_run);
     trace_stream_start(bs, base, s, s->common.co, opaque);
     qemu_coroutine_enter(s->common.co, s);

block/vdi.c

@@ -50,16 +50,19 @@
  */
 
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "migration/migration.h"
+#include "block_int.h"
+#include "module.h"
+#include "migration.h"
 
 #if defined(CONFIG_UUID)
 #include <uuid/uuid.h>
 #else
 /* TODO: move uuid emulation to some central place in QEMU. */
-#include "sysemu/sysemu.h"     /* UUID_FMT */
+#include "sysemu.h"     /* UUID_FMT */
 typedef unsigned char uuid_t[16];
+void uuid_generate(uuid_t out);
+int uuid_is_null(const uuid_t uu);
+void uuid_unparse(const uuid_t uu, char *out);
 #endif
 
 /* Code configuration options. */
@@ -121,18 +124,18 @@ typedef unsigned char uuid_t[16];
 #define VDI_IS_ALLOCATED(X) ((X) < VDI_DISCARDED)
 
 #if !defined(CONFIG_UUID)
-static inline void uuid_generate(uuid_t out)
+void uuid_generate(uuid_t out)
 {
     memset(out, 0, sizeof(uuid_t));
 }
 
-static inline int uuid_is_null(const uuid_t uu)
+int uuid_is_null(const uuid_t uu)
 {
     uuid_t null_uuid = { 0 };
     return memcmp(uu, null_uuid, sizeof(uuid_t)) == 0;
 }
 
-static inline void uuid_unparse(const uuid_t uu, char *out)
+void uuid_unparse(const uuid_t uu, char *out)
 {
     snprintf(out, 37, UUID_FMT,
             uu[0], uu[1], uu[2], uu[3], uu[4], uu[5], uu[6], uu[7],
@@ -246,7 +249,7 @@ static void vdi_header_print(VdiHeader *header)
 {
     char uuid[37];
     logout("text        %s", header->text);
-    logout("signature   0x%08x\n", header->signature);
+    logout("signature   0x%04x\n", header->signature);
     logout("header size 0x%04x\n", header->header_size);
     logout("image type  0x%04x\n", header->image_type);
     logout("image flags 0x%04x\n", header->image_flags);
@@ -369,12 +372,10 @@ static int vdi_open(BlockDriverState *bs, int flags)
     BDRVVdiState *s = bs->opaque;
     VdiHeader header;
     size_t bmap_size;
-    int ret;
 
     logout("\n");
 
-    ret = bdrv_read(bs->file, 0, (uint8_t *)&header, 1);
-    if (ret < 0) {
+    if (bdrv_read(bs->file, 0, (uint8_t *)&header, 1) < 0) {
         goto fail;
     }
 
@@ -392,45 +393,33 @@ static int vdi_open(BlockDriverState *bs, int flags)
         header.disk_size &= ~(SECTOR_SIZE - 1);
     }
 
-    if (header.signature != VDI_SIGNATURE) {
-        logout("bad vdi signature %08x\n", header.signature);
-        ret = -EMEDIUMTYPE;
-        goto fail;
-    } else if (header.version != VDI_VERSION_1_1) {
+    if (header.version != VDI_VERSION_1_1) {
         logout("unsupported version %u.%u\n",
                header.version >> 16, header.version & 0xffff);
-        ret = -ENOTSUP;
         goto fail;
     } else if (header.offset_bmap % SECTOR_SIZE != 0) {
         /* We only support block maps which start on a sector boundary. */
         logout("unsupported block map offset 0x%x B\n", header.offset_bmap);
-        ret = -ENOTSUP;
         goto fail;
     } else if (header.offset_data % SECTOR_SIZE != 0) {
         /* We only support data blocks which start on a sector boundary. */
         logout("unsupported data offset 0x%x B\n", header.offset_data);
-        ret = -ENOTSUP;
         goto fail;
     } else if (header.sector_size != SECTOR_SIZE) {
         logout("unsupported sector size %u B\n", header.sector_size);
-        ret = -ENOTSUP;
         goto fail;
     } else if (header.block_size != 1 * MiB) {
         logout("unsupported block size %u B\n", header.block_size);
-        ret = -ENOTSUP;
         goto fail;
     } else if (header.disk_size >
                (uint64_t)header.blocks_in_image * header.block_size) {
         logout("unsupported disk size %" PRIu64 " B\n", header.disk_size);
-        ret = -ENOTSUP;
         goto fail;
     } else if (!uuid_is_null(header.uuid_link)) {
         logout("link uuid != 0, unsupported\n");
-        ret = -ENOTSUP;
         goto fail;
     } else if (!uuid_is_null(header.uuid_parent)) {
         logout("parent uuid != 0, unsupported\n");
-        ret = -ENOTSUP;
         goto fail;
     }
 
@@ -443,9 +432,10 @@ static int vdi_open(BlockDriverState *bs, int flags)
 
     bmap_size = header.blocks_in_image * sizeof(uint32_t);
     bmap_size = (bmap_size + SECTOR_SIZE - 1) / SECTOR_SIZE;
-    s->bmap = g_malloc(bmap_size * SECTOR_SIZE);
-    ret = bdrv_read(bs->file, s->bmap_sector, (uint8_t *)s->bmap, bmap_size);
-    if (ret < 0) {
+    if (bmap_size > 0) {
+        s->bmap = g_malloc(bmap_size * SECTOR_SIZE);
+    }
+    if (bdrv_read(bs->file, s->bmap_sector, (uint8_t *)s->bmap, bmap_size) < 0) {
         goto fail_free_bmap;
     }
 
@@ -461,13 +451,7 @@ static int vdi_open(BlockDriverState *bs, int flags)
     g_free(s->bmap);
 
  fail:
-    return ret;
-}
-
-static int vdi_reopen_prepare(BDRVReopenState *state,
-                              BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
+    return -1;
 }
 
 static int coroutine_fn vdi_co_is_allocated(BlockDriverState *bs,
@@ -777,7 +761,6 @@ static BlockDriver bdrv_vdi = {
     .bdrv_probe = vdi_probe,
     .bdrv_open = vdi_open,
     .bdrv_close = vdi_close,
-    .bdrv_reopen_prepare = vdi_reopen_prepare,
     .bdrv_create = vdi_create,
     .bdrv_co_is_allocated = vdi_co_is_allocated,
     .bdrv_make_empty = vdi_make_empty,

block/vmdk.c

@@ -24,9 +24,9 @@
  */
 
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "migration/migration.h"
+#include "block_int.h"
+#include "module.h"
+#include "migration.h"
 #include <zlib.h>
 
 #define VMDK3_MAGIC (('C' << 24) | ('O' << 16) | ('W' << 8) | 'D')
@@ -300,40 +300,6 @@ static int vmdk_is_cid_valid(BlockDriverState *bs)
     return 1;
 }
 
-/* Queue extents, if any, for reopen() */
-static int vmdk_reopen_prepare(BDRVReopenState *state,
-                               BlockReopenQueue *queue, Error **errp)
-{
-    BDRVVmdkState *s;
-    int ret = -1;
-    int i;
-    VmdkExtent *e;
-
-    assert(state != NULL);
-    assert(state->bs != NULL);
-
-    if (queue == NULL) {
-        error_set(errp, ERROR_CLASS_GENERIC_ERROR,
-                 "No reopen queue for VMDK extents");
-        goto exit;
-    }
-
-    s = state->bs->opaque;
-
-    assert(s != NULL);
-
-    for (i = 0; i < s->num_extents; i++) {
-        e = &s->extents[i];
-        if (e->file != state->bs->file) {
-            bdrv_reopen_queue(queue, e->file, state->flags);
-        }
-    }
-    ret = 0;
-
-exit:
-    return ret;
-}
-
 static int vmdk_parent_open(BlockDriverState *bs)
 {
     char *p_name;
@@ -616,7 +582,7 @@ static int vmdk_open_sparse(BlockDriverState *bs,
             return vmdk_open_vmdk4(bs, file, flags);
             break;
         default:
-            return -EMEDIUMTYPE;
+            return -EINVAL;
             break;
     }
 }
@@ -641,7 +607,7 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
          * RW [size in sectors] SPARSE "file-name.vmdk"
          */
         flat_offset = -1;
-        ret = sscanf(p, "%10s %" SCNd64 " %10s \"%511[^\n\r\"]\" %" SCNd64,
+        ret = sscanf(p, "%10s %" SCNd64 " %10s %511s %" SCNd64,
                 access, &sectors, type, fname, &flat_offset);
         if (ret < 4 || strcmp(access, "RW")) {
             goto next_line;
@@ -653,6 +619,14 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
             return -EINVAL;
         }
 
+        /* trim the quotation marks around */
+        if (fname[0] == '"') {
+            memmove(fname, fname + 1, strlen(fname));
+            if (strlen(fname) <= 1 || fname[strlen(fname) - 1] != '"') {
+                return -EINVAL;
+            }
+            fname[strlen(fname) - 1] = '\0';
+        }
         if (sectors <= 0 ||
             (strcmp(type, "FLAT") && strcmp(type, "SPARSE")) ||
             (strcmp(access, "RW"))) {
@@ -710,7 +684,7 @@ static int vmdk_open_desc_file(BlockDriverState *bs, int flags,
     }
     buf[2047] = '\0';
     if (vmdk_parse_description(buf, "createType", ct, sizeof(ct))) {
-        return -EMEDIUMTYPE;
+        return -EINVAL;
     }
     if (strcmp(ct, "monolithicFlat") &&
         strcmp(ct, "twoGbMaxExtentSparse") &&
@@ -1084,7 +1058,6 @@ static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
     BDRVVmdkState *s = bs->opaque;
     int ret;
     uint64_t n, index_in_cluster;
-    uint64_t extent_begin_sector, extent_relative_sector_num;
     VmdkExtent *extent = NULL;
     uint64_t cluster_offset;
 
@@ -1096,9 +1069,7 @@ static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
         ret = get_cluster_offset(
                             bs, extent, NULL,
                             sector_num << 9, 0, &cluster_offset);
-        extent_begin_sector = extent->end_sector - extent->sectors;
-        extent_relative_sector_num = sector_num - extent_begin_sector;
-        index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
+        index_in_cluster = sector_num % extent->cluster_sectors;
         n = extent->cluster_sectors - index_in_cluster;
         if (n > nb_sectors) {
             n = nb_sectors;
@@ -1149,7 +1120,6 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
     VmdkExtent *extent = NULL;
     int n, ret;
     int64_t index_in_cluster;
-    uint64_t extent_begin_sector, extent_relative_sector_num;
     uint64_t cluster_offset;
     VmdkMetaData m_data;
 
@@ -1192,9 +1162,7 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
         if (ret) {
             return -EINVAL;
         }
-        extent_begin_sector = extent->end_sector - extent->sectors;
-        extent_relative_sector_num = sector_num - extent_begin_sector;
-        index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
+        index_in_cluster = sector_num % extent->cluster_sectors;
         n = extent->cluster_sectors - index_in_cluster;
         if (n > nb_sectors) {
             n = nb_sectors;
@@ -1406,7 +1374,8 @@ static int relative_path(char *dest, int dest_size,
         return -1;
     }
     if (path_is_absolute(target)) {
-        pstrcpy(dest, dest_size, target);
+        dest[dest_size - 1] = '\0';
+        strncpy(dest, target, dest_size - 1);
         return 0;
     }
     while (base[i] == target[i]) {
@@ -1434,7 +1403,6 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
     int fd, idx = 0;
     char desc[BUF_SIZE];
     int64_t total_size = 0, filesize;
-    const char *adapter_type = NULL;
     const char *backing_file = NULL;
     const char *fmt = NULL;
     int flags = 0;
@@ -1446,7 +1414,6 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
     const char *desc_extent_line;
     char parent_desc_line[BUF_SIZE] = "";
     uint32_t parent_cid = 0xffffffff;
-    uint32_t number_heads = 16;
     const char desc_template[] =
         "# Disk DescriptorFile\n"
         "version=1\n"
@@ -1463,9 +1430,9 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
         "\n"
         "ddb.virtualHWVersion = \"%d\"\n"
         "ddb.geometry.cylinders = \"%" PRId64 "\"\n"
-        "ddb.geometry.heads = \"%d\"\n"
+        "ddb.geometry.heads = \"16\"\n"
         "ddb.geometry.sectors = \"63\"\n"
-        "ddb.adapterType = \"%s\"\n";
+        "ddb.adapterType = \"ide\"\n";
 
     if (filename_decompose(filename, path, prefix, postfix, PATH_MAX)) {
         return -EINVAL;
@@ -1474,8 +1441,6 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
     while (options && options->name) {
         if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
             total_size = options->value.n;
-        } else if (!strcmp(options->name, BLOCK_OPT_ADAPTER_TYPE)) {
-            adapter_type = options->value.s;
         } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
             backing_file = options->value.s;
         } else if (!strcmp(options->name, BLOCK_OPT_COMPAT6)) {
@@ -1485,20 +1450,6 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
         }
         options++;
     }
-    if (!adapter_type) {
-        adapter_type = "ide";
-    } else if (strcmp(adapter_type, "ide") &&
-               strcmp(adapter_type, "buslogic") &&
-               strcmp(adapter_type, "lsilogic") &&
-               strcmp(adapter_type, "legacyESX")) {
-        fprintf(stderr, "VMDK: Unknown adapter type: '%s'.\n", adapter_type);
-        return -EINVAL;
-    }
-    if (strcmp(adapter_type, "ide") != 0) {
-        /* that's the number of heads with which vmware operates when
-           creating, exporting, etc. vmdk files with a non-ide adapter type */
-        number_heads = 255;
-    }
     if (!fmt) {
         /* Default format to monolithicSparse */
         fmt = "monolithicSparse";
@@ -1586,8 +1537,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
             parent_desc_line,
             ext_desc_lines,
             (flags & BLOCK_FLAG_COMPAT6 ? 6 : 4),
-            total_size / (int64_t)(63 * number_heads * 512), number_heads,
-                adapter_type);
+            total_size / (int64_t)(63 * 16 * 512));
     if (split || flat) {
         fd = qemu_open(filename,
                        O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
@@ -1671,12 +1621,6 @@ static QEMUOptionParameter vmdk_create_options[] = {
         .type = OPT_SIZE,
         .help = "Virtual disk size"
     },
-    {
-        .name = BLOCK_OPT_ADAPTER_TYPE,
-        .type = OPT_STRING,
-        .help = "Virtual adapter type, can be one of "
-                "ide (default), lsilogic, buslogic or legacyESX"
-    },
     {
         .name = BLOCK_OPT_BACKING_FILE,
         .type = OPT_STRING,
@@ -1702,7 +1646,6 @@ static BlockDriver bdrv_vmdk = {
     .instance_size  = sizeof(BDRVVmdkState),
     .bdrv_probe     = vmdk_probe,
     .bdrv_open      = vmdk_open,
-    .bdrv_reopen_prepare = vmdk_reopen_prepare,
     .bdrv_read      = vmdk_co_read,
     .bdrv_write     = vmdk_co_write,
     .bdrv_close     = vmdk_close,

block/vpc.c

@@ -23,12 +23,9 @@
  * THE SOFTWARE.
  */
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "migration/migration.h"
-#if defined(CONFIG_UUID)
-#include <uuid/uuid.h>
-#endif
+#include "block_int.h"
+#include "module.h"
+#include "migration.h"
 
 /**************************************************************/
 
@@ -163,33 +160,24 @@ static int vpc_open(BlockDriverState *bs, int flags)
     struct vhd_dyndisk_header* dyndisk_header;
     uint8_t buf[HEADER_SIZE];
     uint32_t checksum;
+    int err = -1;
     int disk_type = VHD_DYNAMIC;
-    int ret;
 
-    ret = bdrv_pread(bs->file, 0, s->footer_buf, HEADER_SIZE);
-    if (ret < 0) {
+    if (bdrv_pread(bs->file, 0, s->footer_buf, HEADER_SIZE) != HEADER_SIZE)
         goto fail;
-    }
 
     footer = (struct vhd_footer*) s->footer_buf;
     if (strncmp(footer->creator, "conectix", 8)) {
         int64_t offset = bdrv_getlength(bs->file);
-        if (offset < 0) {
-            ret = offset;
-            goto fail;
-        } else if (offset < HEADER_SIZE) {
-            ret = -EINVAL;
+        if (offset < HEADER_SIZE) {
             goto fail;
         }
-
         /* If a fixed disk, the footer is found only at the end of the file */
-        ret = bdrv_pread(bs->file, offset-HEADER_SIZE, s->footer_buf,
-                         HEADER_SIZE);
-        if (ret < 0) {
+        if (bdrv_pread(bs->file, offset-HEADER_SIZE, s->footer_buf, HEADER_SIZE)
+                != HEADER_SIZE) {
             goto fail;
         }
         if (strncmp(footer->creator, "conectix", 8)) {
-            ret = -EMEDIUMTYPE;
             goto fail;
         }
         disk_type = VHD_FIXED;
@@ -210,23 +198,20 @@ static int vpc_open(BlockDriverState *bs, int flags)
     bs->total_sectors = (int64_t)
         be16_to_cpu(footer->cyls) * footer->heads * footer->secs_per_cyl;
 
-    /* Allow a maximum disk size of approximately 2 TB */
-    if (bs->total_sectors >= 65535LL * 255 * 255) {
-        ret = -EFBIG;
+    if (bs->total_sectors >= 65535 * 16 * 255) {
+        err = -EFBIG;
         goto fail;
     }
 
     if (disk_type == VHD_DYNAMIC) {
-        ret = bdrv_pread(bs->file, be64_to_cpu(footer->data_offset), buf,
-                         HEADER_SIZE);
-        if (ret < 0) {
+        if (bdrv_pread(bs->file, be64_to_cpu(footer->data_offset), buf,
+                HEADER_SIZE) != HEADER_SIZE) {
             goto fail;
         }
 
         dyndisk_header = (struct vhd_dyndisk_header *) buf;
 
         if (strncmp(dyndisk_header->magic, "cxsparse", 8)) {
-            ret = -EINVAL;
             goto fail;
         }
 
@@ -237,10 +222,8 @@ static int vpc_open(BlockDriverState *bs, int flags)
         s->pagetable = g_malloc(s->max_table_entries * 4);
 
         s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);
-
-        ret = bdrv_pread(bs->file, s->bat_offset, s->pagetable,
-                         s->max_table_entries * 4);
-        if (ret < 0) {
+        if (bdrv_pread(bs->file, s->bat_offset, s->pagetable,
+                s->max_table_entries * 4) != s->max_table_entries * 4) {
             goto fail;
         }
 
@@ -278,19 +261,8 @@ static int vpc_open(BlockDriverState *bs, int flags)
     migrate_add_blocker(s->migration_blocker);
 
     return 0;
-
-fail:
-    g_free(s->pagetable);
-#ifdef CACHE
-    g_free(s->pageentry_u8);
-#endif
-    return ret;
-}
-
-static int vpc_reopen_prepare(BDRVReopenState *state,
-                              BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
+ fail:
+    return err;
 }
 
 /*
@@ -546,27 +518,19 @@ static coroutine_fn int vpc_co_write(BlockDriverState *bs, int64_t sector_num,
  * Note that the geometry doesn't always exactly match total_sectors but
  * may round it down.
  *
- * Returns 0 on success, -EFBIG if the size is larger than ~2 TB. Override
- * the hardware EIDE and ATA-2 limit of 16 heads (max disk size of 127 GB)
- * and instead allow up to 255 heads.
+ * Returns 0 on success, -EFBIG if the size is larger than 127 GB
  */
 static int calculate_geometry(int64_t total_sectors, uint16_t* cyls,
     uint8_t* heads, uint8_t* secs_per_cyl)
 {
     uint32_t cyls_times_heads;
 
-    /* Allow a maximum disk size of approximately 2 TB */
-    if (total_sectors > 65535LL * 255 * 255) {
+    if (total_sectors > 65535 * 16 * 255)
         return -EFBIG;
-    }
 
     if (total_sectors > 65535 * 16 * 63) {
         *secs_per_cyl = 255;
-        if (total_sectors > 65535 * 16 * 255) {
-            *heads = 255;
-        } else {
-            *heads = 16;
-        }
+        *heads = 16;
         cyls_times_heads = total_sectors / *secs_per_cyl;
     } else {
         *secs_per_cyl = 17;
@@ -769,9 +733,7 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options)
 
     footer->type = be32_to_cpu(disk_type);
 
-#if defined(CONFIG_UUID)
-    uuid_generate(footer->uuid);
-#endif
+    /* TODO uuid is missing */
 
     footer->checksum = be32_to_cpu(vpc_checksum(buf, HEADER_SIZE));
 
@@ -821,7 +783,6 @@ static BlockDriver bdrv_vpc = {
     .bdrv_probe     = vpc_probe,
     .bdrv_open      = vpc_open,
     .bdrv_close     = vpc_close,
-    .bdrv_reopen_prepare = vpc_reopen_prepare,
     .bdrv_create    = vpc_create,
 
     .bdrv_read              = vpc_co_read,

block/vvfat.c

@@ -25,9 +25,9 @@
 #include <sys/stat.h>
 #include <dirent.h>
 #include "qemu-common.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "migration/migration.h"
+#include "block_int.h"
+#include "module.h"
+#include "migration.h"
 
 #ifndef S_IWGRP
 #define S_IWGRP 0
@@ -529,9 +529,13 @@ static inline uint8_t fat_chksum(const direntry_t* entry)
 /* if return_time==0, this returns the fat_date, else the fat_time */
 static uint16_t fat_datetime(time_t time,int return_time) {
     struct tm* t;
+#ifdef _WIN32
+    t=localtime(&time); /* this is not thread safe */
+#else
     struct tm t1;
     t = &t1;
     localtime_r(&time,t);
+#endif
     if(return_time)
 	return cpu_to_le16((t->tm_sec/2)|(t->tm_min<<5)|(t->tm_hour<<11));
     return cpu_to_le16((t->tm_mday)|((t->tm_mon+1)<<5)|((t->tm_year-80)<<9));

block/win32-aio.c

@@ -1,215 +0,0 @@
-/*
- * Block driver for RAW files (win32)
- *
- * Copyright (c) 2006 Fabrice Bellard
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
- */
-#include "qemu-common.h"
-#include "qemu/timer.h"
-#include "block/block_int.h"
-#include "qemu/module.h"
-#include "qemu-common.h"
-#include "block/aio.h"
-#include "raw-aio.h"
-#include "qemu/event_notifier.h"
-#include "qemu/iov.h"
-#include <windows.h>
-#include <winioctl.h>
-
-#define FTYPE_FILE 0
-#define FTYPE_CD     1
-#define FTYPE_HARDDISK 2
-
-struct QEMUWin32AIOState {
-    HANDLE hIOCP;
-    EventNotifier e;
-    int count;
-};
-
-typedef struct QEMUWin32AIOCB {
-    BlockDriverAIOCB common;
-    struct QEMUWin32AIOState *ctx;
-    int nbytes;
-    OVERLAPPED ov;
-    QEMUIOVector *qiov;
-    void *buf;
-    bool is_read;
-    bool is_linear;
-} QEMUWin32AIOCB;
-
-/*
- * Completes an AIO request (calls the callback and frees the ACB).
- */
-static void win32_aio_process_completion(QEMUWin32AIOState *s,
-    QEMUWin32AIOCB *waiocb, DWORD count)
-{
-    int ret;
-    s->count--;
-
-    if (waiocb->ov.Internal != 0) {
-        ret = -EIO;
-    } else {
-        ret = 0;
-        if (count < waiocb->nbytes) {
-            /* Short reads mean EOF, pad with zeros. */
-            if (waiocb->is_read) {
-                qemu_iovec_memset(waiocb->qiov, count, 0,
-                    waiocb->qiov->size - count);
-            } else {
-                ret = -EINVAL;
-            }
-       }
-    }
-
-    if (!waiocb->is_linear) {
-        if (ret == 0 && waiocb->is_read) {
-            QEMUIOVector *qiov = waiocb->qiov;
-            iov_from_buf(qiov->iov, qiov->niov, 0, waiocb->buf, qiov->size);
-        }
-        qemu_vfree(waiocb->buf);
-    }
-
-
-    waiocb->common.cb(waiocb->common.opaque, ret);
-    qemu_aio_release(waiocb);
-}
-
-static void win32_aio_completion_cb(EventNotifier *e)
-{
-    QEMUWin32AIOState *s = container_of(e, QEMUWin32AIOState, e);
-    DWORD count;
-    ULONG_PTR key;
-    OVERLAPPED *ov;
-
-    event_notifier_test_and_clear(&s->e);
-    while (GetQueuedCompletionStatus(s->hIOCP, &count, &key, &ov, 0)) {
-        QEMUWin32AIOCB *waiocb = container_of(ov, QEMUWin32AIOCB, ov);
-
-        win32_aio_process_completion(s, waiocb, count);
-    }
-}
-
-static int win32_aio_flush_cb(EventNotifier *e)
-{
-    QEMUWin32AIOState *s = container_of(e, QEMUWin32AIOState, e);
-
-    return (s->count > 0) ? 1 : 0;
-}
-
-static void win32_aio_cancel(BlockDriverAIOCB *blockacb)
-{
-    QEMUWin32AIOCB *waiocb = (QEMUWin32AIOCB *)blockacb;
-
-    /*
-     * CancelIoEx is only supported in Vista and newer.  For now, just
-     * wait for completion.
-     */
-    while (!HasOverlappedIoCompleted(&waiocb->ov)) {
-        qemu_aio_wait();
-    }
-}
-
-static const AIOCBInfo win32_aiocb_info = {
-    .aiocb_size         = sizeof(QEMUWin32AIOCB),
-    .cancel             = win32_aio_cancel,
-};
-
-BlockDriverAIOCB *win32_aio_submit(BlockDriverState *bs,
-        QEMUWin32AIOState *aio, HANDLE hfile,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque, int type)
-{
-    struct QEMUWin32AIOCB *waiocb;
-    uint64_t offset = sector_num * 512;
-    DWORD rc;
-
-    waiocb = qemu_aio_get(&win32_aiocb_info, bs, cb, opaque);
-    waiocb->nbytes = nb_sectors * 512;
-    waiocb->qiov = qiov;
-    waiocb->is_read = (type == QEMU_AIO_READ);
-
-    if (qiov->niov > 1) {
-        waiocb->buf = qemu_blockalign(bs, qiov->size);
-        if (type & QEMU_AIO_WRITE) {
-            iov_to_buf(qiov->iov, qiov->niov, 0, waiocb->buf, qiov->size);
-        }
-        waiocb->is_linear = false;
-    } else {
-        waiocb->buf = qiov->iov[0].iov_base;
-        waiocb->is_linear = true;
-    }
-
-    memset(&waiocb->ov, 0, sizeof(waiocb->ov));
-    waiocb->ov.Offset = (DWORD)offset;
-    waiocb->ov.OffsetHigh = (DWORD)(offset >> 32);
-    waiocb->ov.hEvent = event_notifier_get_handle(&aio->e);
-
-    aio->count++;
-
-    if (type & QEMU_AIO_READ) {
-        rc = ReadFile(hfile, waiocb->buf, waiocb->nbytes, NULL, &waiocb->ov);
-    } else {
-        rc = WriteFile(hfile, waiocb->buf, waiocb->nbytes, NULL, &waiocb->ov);
-    }
-    if(rc == 0 && GetLastError() != ERROR_IO_PENDING) {
-        goto out_dec_count;
-    }
-    return &waiocb->common;
-
-out_dec_count:
-    aio->count--;
-    qemu_aio_release(waiocb);
-    return NULL;
-}
-
-int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile)
-{
-    if (CreateIoCompletionPort(hfile, aio->hIOCP, (ULONG_PTR) 0, 0) == NULL) {
-        return -EINVAL;
-    } else {
-        return 0;
-    }
-}
-
-QEMUWin32AIOState *win32_aio_init(void)
-{
-    QEMUWin32AIOState *s;
-
-    s = g_malloc0(sizeof(*s));
-    if (event_notifier_init(&s->e, false) < 0) {
-        goto out_free_state;
-    }
-
-    s->hIOCP = CreateIoCompletionPort(INVALID_HANDLE_VALUE, NULL, 0, 0);
-    if (s->hIOCP == NULL) {
-        goto out_close_efd;
-    }
-
-    qemu_aio_set_event_notifier(&s->e, win32_aio_completion_cb,
-                                win32_aio_flush_cb);
-
-    return s;
-
-out_close_efd:
-    event_notifier_cleanup(&s->e);
-out_free_state:
-    g_free(s);
-    return NULL;
-}

block_int.h

@@ -24,15 +24,13 @@
 #ifndef BLOCK_INT_H
 #define BLOCK_INT_H
 
-#include "block/block.h"
-#include "qemu/option.h"
-#include "qemu/queue.h"
-#include "block/coroutine.h"
-#include "qemu/timer.h"
+#include "block.h"
+#include "qemu-option.h"
+#include "qemu-queue.h"
+#include "qemu-coroutine.h"
+#include "qemu-timer.h"
 #include "qapi-types.h"
-#include "qapi/qmp/qerror.h"
-#include "monitor/monitor.h"
-#include "qemu/hbitmap.h"
+#include "qerror.h"
 
 #define BLOCK_FLAG_ENCRYPT          1
 #define BLOCK_FLAG_COMPAT6          4
@@ -56,7 +54,6 @@
 #define BLOCK_OPT_SUBFMT            "subformat"
 #define BLOCK_OPT_COMPAT_LEVEL      "compat"
 #define BLOCK_OPT_LAZY_REFCOUNTS    "lazy_refcounts"
-#define BLOCK_OPT_ADAPTER_TYPE      "adapter_type"
 
 typedef struct BdrvTrackedRequest BdrvTrackedRequest;
 
@@ -70,18 +67,78 @@ typedef struct BlockIOBaseValue {
     uint64_t ios[2];
 } BlockIOBaseValue;
 
+typedef struct BlockJob BlockJob;
+
+/**
+ * BlockJobType:
+ *
+ * A class type for block job objects.
+ */
+typedef struct BlockJobType {
+    /** Derived BlockJob struct size */
+    size_t instance_size;
+
+    /** String describing the operation, part of query-block-jobs QMP API */
+    const char *job_type;
+
+    /** Optional callback for job types that support setting a speed limit */
+    void (*set_speed)(BlockJob *job, int64_t speed, Error **errp);
+} BlockJobType;
+
+/**
+ * BlockJob:
+ *
+ * Long-running operation on a BlockDriverState.
+ */
+struct BlockJob {
+    /** The job type, including the job vtable.  */
+    const BlockJobType *job_type;
+
+    /** The block device on which the job is operating.  */
+    BlockDriverState *bs;
+
+    /**
+     * The coroutine that executes the job.  If not NULL, it is
+     * reentered when busy is false and the job is cancelled.
+     */
+    Coroutine *co;
+
+    /**
+     * Set to true if the job should cancel itself.  The flag must
+     * always be tested just before toggling the busy flag from false
+     * to true.  After a job has been cancelled, it should only yield
+     * if #qemu_aio_wait will ("sooner or later") reenter the coroutine.
+     */
+    bool cancelled;
+
+    /**
+     * Set to false by the job while it is in a quiescent state, where
+     * no I/O is pending and the job has yielded on any condition
+     * that is not detected by #qemu_aio_wait, such as a timer.
+     */
+    bool busy;
+
+    /** Offset that is published by the query-block-jobs QMP API */
+    int64_t offset;
+
+    /** Length that is published by the query-block-jobs QMP API */
+    int64_t len;
+
+    /** Speed that was set with @block_job_set_speed.  */
+    int64_t speed;
+
+    /** The completion function that will be called when the job completes.  */
+    BlockDriverCompletionFunc *cb;
+
+    /** The opaque value that is passed to the completion function.  */
+    void *opaque;
+};
+
 struct BlockDriver {
     const char *format_name;
     int instance_size;
     int (*bdrv_probe)(const uint8_t *buf, int buf_size, const char *filename);
     int (*bdrv_probe_device)(const char *filename);
-
-    /* For handling image reopen for split or non-split files */
-    int (*bdrv_reopen_prepare)(BDRVReopenState *reopen_state,
-                               BlockReopenQueue *queue, Error **errp);
-    void (*bdrv_reopen_commit)(BDRVReopenState *reopen_state);
-    void (*bdrv_reopen_abort)(BDRVReopenState *reopen_state);
-
     int (*bdrv_open)(BlockDriverState *bs, int flags);
     int (*bdrv_file_open)(BlockDriverState *bs, const char *filename, int flags);
     int (*bdrv_read)(BlockDriverState *bs, int64_t sector_num,
@@ -192,12 +249,6 @@ struct BlockDriver {
 
     void (*bdrv_debug_event)(BlockDriverState *bs, BlkDebugEvent event);
 
-    /* TODO Better pass a option string/QDict/QemuOpts to add any rule? */
-    int (*bdrv_debug_breakpoint)(BlockDriverState *bs, const char *event,
-        const char *tag);
-    int (*bdrv_debug_resume)(BlockDriverState *bs, const char *tag);
-    bool (*bdrv_debug_is_suspended)(BlockDriverState *bs, const char *tag);
-
     /*
      * Returns 1 if newly created images are guaranteed to contain only
      * zeros, 0 otherwise.
@@ -217,6 +268,7 @@ struct BlockDriverState {
     int64_t total_sectors; /* if we are reading a disk image, give its
                               size in sectors */
     int read_only; /* if true, the media is read only */
+    int keep_read_only; /* if true, the media was requested to stay read only */
     int open_flags; /* flags used to open the file, re-used for re-open */
     int encrypted; /* if true, the media is encrypted */
     int valid_key; /* if true, a valid encryption key has been set */
@@ -241,8 +293,6 @@ struct BlockDriverState {
     BlockDriverState *backing_hd;
     BlockDriverState *file;
 
-    NotifierList close_notifiers;
-
     /* number of in-flight copy-on-read requests */
     unsigned int copy_on_read_in_flight;
 
@@ -273,11 +323,12 @@ struct BlockDriverState {
 
     /* NOTE: the following infos are only hints for real hardware
        drivers. They are not used by the block driver */
-    BlockdevOnError on_read_error, on_write_error;
+    BlockErrorAction on_read_error, on_write_error;
     bool iostatus_enabled;
     BlockDeviceIoStatus iostatus;
     char device_name[32];
-    HBitmap *dirty_bitmap;
+    unsigned long *dirty_bitmap;
+    int64_t dirty_count;
     int in_use; /* users other than guest access, eg. block migration */
     QTAILQ_ENTRY(BlockDriverState) list;
 
@@ -285,7 +336,6 @@ struct BlockDriverState {
 
     /* long-running background operation */
     BlockJob *job;
-
 };
 
 int get_tmp_filename(char *filename, int size);
@@ -296,9 +346,92 @@ void bdrv_set_io_limits(BlockDriverState *bs,
 #ifdef _WIN32
 int is_windows_drive(const char *filename);
 #endif
-void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
-                               enum MonitorEvent ev,
-                               BlockErrorAction action, bool is_read);
+
+/**
+ * block_job_create:
+ * @job_type: The class object for the newly-created job.
+ * @bs: The block
+ * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
+ * @cb: Completion function for the job.
+ * @opaque: Opaque pointer value passed to @cb.
+ * @errp: Error object.
+ *
+ * Create a new long-running block device job and return it.  The job
+ * will call @cb asynchronously when the job completes.  Note that
+ * @bs may have been closed at the time the @cb it is called.  If
+ * this is the case, the job may be reported as either cancelled or
+ * completed.
+ *
+ * This function is not part of the public job interface; it should be
+ * called from a wrapper that is specific to the job type.
+ */
+void *block_job_create(const BlockJobType *job_type, BlockDriverState *bs,
+                       int64_t speed, BlockDriverCompletionFunc *cb,
+                       void *opaque, Error **errp);
+
+/**
+ * block_job_sleep_ns:
+ * @job: The job that calls the function.
+ * @clock: The clock to sleep on.
+ * @ns: How many nanoseconds to stop for.
+ *
+ * Put the job to sleep (assuming that it wasn't canceled) for @ns
+ * nanoseconds.  Canceling the job will interrupt the wait immediately.
+ */
+void block_job_sleep_ns(BlockJob *job, QEMUClock *clock, int64_t ns);
+
+/**
+ * block_job_complete:
+ * @job: The job being completed.
+ * @ret: The status code.
+ *
+ * Call the completion function that was registered at creation time, and
+ * free @job.
+ */
+void block_job_complete(BlockJob *job, int ret);
+
+/**
+ * block_job_set_speed:
+ * @job: The job to set the speed for.
+ * @speed: The new value
+ * @errp: Error object.
+ *
+ * Set a rate-limiting parameter for the job; the actual meaning may
+ * vary depending on the job type.
+ */
+void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp);
+
+/**
+ * block_job_cancel:
+ * @job: The job to be canceled.
+ *
+ * Asynchronously cancel the specified job.
+ */
+void block_job_cancel(BlockJob *job);
+
+/**
+ * block_job_is_cancelled:
+ * @job: The job being queried.
+ *
+ * Returns whether the job is scheduled for cancellation.
+ */
+bool block_job_is_cancelled(BlockJob *job);
+
+/**
+ * block_job_cancel:
+ * @job: The job to be canceled.
+ *
+ * Asynchronously cancel the job and wait for it to reach a quiescent
+ * state.  Note that the completion callback will still be called
+ * asynchronously, hence it is *not* valid to call #bdrv_delete
+ * immediately after #block_job_cancel_sync.  Users of block jobs
+ * will usually protect the BlockDriverState objects with a reference
+ * count, should this be a concern.
+ *
+ * Returns the return value from the job if the job actually completed
+ * during the call, or -ECANCELED if it was canceled.
+ */
+int block_job_cancel_sync(BlockJob *job);
 
 /**
  * stream_start:
@@ -308,7 +441,6 @@ void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
  * @base_id: The file name that will be written to @bs as the new
  * backing file if the job completes.  Ignored if @base is %NULL.
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
- * @on_error: The action to take upon error.
  * @cb: Completion function for the job.
  * @opaque: Opaque pointer value passed to @cb.
  * @errp: Error object.
@@ -320,49 +452,7 @@ void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
  * @base_id in the written image and to @base in the live BlockDriverState.
  */
 void stream_start(BlockDriverState *bs, BlockDriverState *base,
-                  const char *base_id, int64_t speed, BlockdevOnError on_error,
-                  BlockDriverCompletionFunc *cb,
-                  void *opaque, Error **errp);
-
-/**
- * commit_start:
- * @bs: Top Block device
- * @base: Block device that will be written into, and become the new top
- * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
- * @on_error: The action to take upon error.
- * @cb: Completion function for the job.
- * @opaque: Opaque pointer value passed to @cb.
- * @errp: Error object.
- *
- */
-void commit_start(BlockDriverState *bs, BlockDriverState *base,
-                 BlockDriverState *top, int64_t speed,
-                 BlockdevOnError on_error, BlockDriverCompletionFunc *cb,
-                 void *opaque, Error **errp);
-
-/*
- * mirror_start:
- * @bs: Block device to operate on.
- * @target: Block device to write to.
- * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
- * @granularity: The chosen granularity for the dirty bitmap.
- * @buf_size: The amount of data that can be in flight at one time.
- * @mode: Whether to collapse all images in the chain to the target.
- * @on_source_error: The action to take upon error reading from the source.
- * @on_target_error: The action to take upon error writing to the target.
- * @cb: Completion function for the job.
- * @opaque: Opaque pointer value passed to @cb.
- * @errp: Error object.
- *
- * Start a mirroring operation on @bs.  Clusters that are allocated
- * in @bs will be written to @bs until the job is cancelled or
- * manually completed.  At the end of a successful mirroring job,
- * @bs will be switched to read from @target.
- */
-void mirror_start(BlockDriverState *bs, BlockDriverState *target,
-                  int64_t speed, int64_t granularity, int64_t buf_size,
-                  MirrorSyncMode mode, BlockdevOnError on_source_error,
-                  BlockdevOnError on_target_error,
+                  const char *base_id, int64_t speed,
                   BlockDriverCompletionFunc *cb,
                   void *opaque, Error **errp);
 

blockdev-nbd.c

@@ -1,133 +0,0 @@
-/*
- * Serving QEMU block devices via NBD
- *
- * Copyright (c) 2012 Red Hat, Inc.
- *
- * Author: 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 "sysemu/blockdev.h"
-#include "hw/block-common.h"
-#include "monitor/monitor.h"
-#include "qapi/qmp/qerror.h"
-#include "sysemu/sysemu.h"
-#include "qmp-commands.h"
-#include "trace.h"
-#include "block/nbd.h"
-#include "qemu/sockets.h"
-
-static int server_fd = -1;
-
-static void nbd_accept(void *opaque)
-{
-    struct sockaddr_in addr;
-    socklen_t addr_len = sizeof(addr);
-
-    int fd = accept(server_fd, (struct sockaddr *)&addr, &addr_len);
-    if (fd >= 0) {
-        nbd_client_new(NULL, fd, nbd_client_put);
-    }
-}
-
-void qmp_nbd_server_start(SocketAddress *addr, Error **errp)
-{
-    if (server_fd != -1) {
-        error_setg(errp, "NBD server already running");
-        return;
-    }
-
-    server_fd = socket_listen(addr, errp);
-    if (server_fd != -1) {
-        qemu_set_fd_handler2(server_fd, NULL, nbd_accept, NULL, NULL);
-    }
-}
-
-/* Hook into the BlockDriverState notifiers to close the export when
- * the file is closed.
- */
-typedef struct NBDCloseNotifier {
-    Notifier n;
-    NBDExport *exp;
-    QTAILQ_ENTRY(NBDCloseNotifier) next;
-} NBDCloseNotifier;
-
-static QTAILQ_HEAD(, NBDCloseNotifier) close_notifiers =
-    QTAILQ_HEAD_INITIALIZER(close_notifiers);
-
-static void nbd_close_notifier(Notifier *n, void *data)
-{
-    NBDCloseNotifier *cn = DO_UPCAST(NBDCloseNotifier, n, n);
-
-    notifier_remove(&cn->n);
-    QTAILQ_REMOVE(&close_notifiers, cn, next);
-
-    nbd_export_close(cn->exp);
-    nbd_export_put(cn->exp);
-    g_free(cn);
-}
-
-static void nbd_server_put_ref(NBDExport *exp)
-{
-    BlockDriverState *bs = nbd_export_get_blockdev(exp);
-    drive_put_ref(drive_get_by_blockdev(bs));
-}
-
-void qmp_nbd_server_add(const char *device, bool has_writable, bool writable,
-                        Error **errp)
-{
-    BlockDriverState *bs;
-    NBDExport *exp;
-    NBDCloseNotifier *n;
-
-    if (server_fd == -1) {
-        error_setg(errp, "NBD server not running");
-        return;
-    }
-
-    if (nbd_export_find(device)) {
-        error_setg(errp, "NBD server already exporting device '%s'", device);
-        return;
-    }
-
-    bs = bdrv_find(device);
-    if (!bs) {
-        error_set(errp, QERR_DEVICE_NOT_FOUND, device);
-        return;
-    }
-
-    if (!has_writable) {
-        writable = false;
-    }
-    if (bdrv_is_read_only(bs)) {
-        writable = false;
-    }
-
-    exp = nbd_export_new(bs, 0, -1, writable ? 0 : NBD_FLAG_READ_ONLY,
-                         nbd_server_put_ref);
-
-    nbd_export_set_name(exp, device);
-    drive_get_ref(drive_get_by_blockdev(bs));
-
-    n = g_malloc0(sizeof(NBDCloseNotifier));
-    n->n.notify = nbd_close_notifier;
-    n->exp = exp;
-    bdrv_add_close_notifier(bs, &n->n);
-    QTAILQ_INSERT_TAIL(&close_notifiers, n, next);
-}
-
-void qmp_nbd_server_stop(Error **errp)
-{
-    while (!QTAILQ_EMPTY(&close_notifiers)) {
-        NBDCloseNotifier *cn = QTAILQ_FIRST(&close_notifiers);
-        nbd_close_notifier(&cn->n, nbd_export_get_blockdev(cn->exp));
-    }
-
-    if (server_fd != -1) {
-        qemu_set_fd_handler2(server_fd, NULL, NULL, NULL, NULL);
-        close(server_fd);
-        server_fd = -1;
-    }
-}

blockdev.c

@@ -7,19 +7,18 @@
  * later.  See the COPYING file in the top-level directory.
  */
 
-#include "sysemu/blockdev.h"
+#include "blockdev.h"
 #include "hw/block-common.h"
-#include "block/blockjob.h"
-#include "monitor/monitor.h"
-#include "qapi/qmp/qerror.h"
-#include "qemu/option.h"
-#include "qemu/config-file.h"
-#include "qapi/qmp/types.h"
-#include "sysemu/sysemu.h"
-#include "block/block_int.h"
+#include "monitor.h"
+#include "qerror.h"
+#include "qemu-option.h"
+#include "qemu-config.h"
+#include "qemu-objects.h"
+#include "sysemu.h"
+#include "block_int.h"
 #include "qmp-commands.h"
 #include "trace.h"
-#include "sysemu/arch_init.h"
+#include "arch_init.h"
 
 static QTAILQ_HEAD(drivelist, DriveInfo) drives = QTAILQ_HEAD_INITIALIZER(drives);
 
@@ -238,16 +237,16 @@ static void drive_put_ref_bh_schedule(DriveInfo *dinfo)
     qemu_bh_schedule(s->bh);
 }
 
-static int parse_block_error_action(const char *buf, bool is_read)
+static int parse_block_error_action(const char *buf, int is_read)
 {
     if (!strcmp(buf, "ignore")) {
-        return BLOCKDEV_ON_ERROR_IGNORE;
+        return BLOCK_ERR_IGNORE;
     } else if (!is_read && !strcmp(buf, "enospc")) {
-        return BLOCKDEV_ON_ERROR_ENOSPC;
+        return BLOCK_ERR_STOP_ENOSPC;
     } else if (!strcmp(buf, "stop")) {
-        return BLOCKDEV_ON_ERROR_STOP;
+        return BLOCK_ERR_STOP_ANY;
     } else if (!strcmp(buf, "report")) {
-        return BLOCKDEV_ON_ERROR_REPORT;
+        return BLOCK_ERR_REPORT;
     } else {
         error_report("'%s' invalid %s error action",
                      buf, is_read ? "read" : "write");
@@ -275,7 +274,7 @@ static bool do_check_io_limits(BlockIOLimit *io_limits)
     return true;
 }
 
-DriveInfo *drive_init(QemuOpts *opts, BlockInterfaceType block_default_type)
+DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 {
     const char *buf;
     const char *file = NULL;
@@ -325,7 +324,7 @@ DriveInfo *drive_init(QemuOpts *opts, BlockInterfaceType block_default_type)
             return NULL;
 	}
     } else {
-        type = block_default_type;
+        type = default_to_scsi ? IF_SCSI : IF_IDE;
     }
 
     max_devs = if_max_devs[type];
@@ -433,13 +432,7 @@ DriveInfo *drive_init(QemuOpts *opts, BlockInterfaceType block_default_type)
         return NULL;
     }
 
-    if (qemu_opt_get(opts, "boot") != NULL) {
-        fprintf(stderr, "qemu-kvm: boot=on|off is deprecated and will be "
-                "ignored. Future versions will reject this parameter. Please "
-                "update your scripts.\n");
-    }
-
-    on_write_error = BLOCKDEV_ON_ERROR_ENOSPC;
+    on_write_error = BLOCK_ERR_STOP_ENOSPC;
     if ((buf = qemu_opt_get(opts, "werror")) != NULL) {
         if (type != IF_IDE && type != IF_SCSI && type != IF_VIRTIO && type != IF_NONE) {
             error_report("werror is not supported by this bus type");
@@ -452,7 +445,7 @@ DriveInfo *drive_init(QemuOpts *opts, BlockInterfaceType block_default_type)
         }
     }
 
-    on_read_error = BLOCKDEV_ON_ERROR_REPORT;
+    on_read_error = BLOCK_ERR_REPORT;
     if ((buf = qemu_opt_get(opts, "rerror")) != NULL) {
         if (type != IF_IDE && type != IF_VIRTIO && type != IF_SCSI && type != IF_NONE) {
             error_report("rerror is not supported by this bus type");
@@ -568,7 +561,7 @@ DriveInfo *drive_init(QemuOpts *opts, BlockInterfaceType block_default_type)
         break;
     case IF_VIRTIO:
         /* add virtio block device */
-        opts = qemu_opts_create_nofail(qemu_find_opts("device"));
+        opts = qemu_opts_create(qemu_find_opts("device"), NULL, 0, NULL);
         if (arch_type == QEMU_ARCH_S390X) {
             qemu_opt_set(opts, "driver", "virtio-blk-s390");
         } else {
@@ -617,13 +610,8 @@ DriveInfo *drive_init(QemuOpts *opts, BlockInterfaceType block_default_type)
 
     ret = bdrv_open(dinfo->bdrv, file, bdrv_flags, drv);
     if (ret < 0) {
-        if (ret == -EMEDIUMTYPE) {
-            error_report("could not open disk image %s: not in %s format",
-                         file, drv->format_name);
-        } else {
-            error_report("could not open disk image %s: %s",
-                         file, strerror(-ret));
-        }
+        error_report("could not open disk image %s: %s",
+                     file, strerror(-ret));
         goto err;
     }
 
@@ -647,17 +635,21 @@ void do_commit(Monitor *mon, const QDict *qdict)
 
     if (!strcmp(device, "all")) {
         ret = bdrv_commit_all();
+        if (ret == -EBUSY) {
+            qerror_report(QERR_DEVICE_IN_USE, device);
+            return;
+        }
     } else {
         bs = bdrv_find(device);
         if (!bs) {
-            monitor_printf(mon, "Device '%s' not found\n", device);
+            qerror_report(QERR_DEVICE_NOT_FOUND, device);
             return;
         }
         ret = bdrv_commit(bs);
-    }
-    if (ret < 0) {
-        monitor_printf(mon, "'commit' error for '%s': %s\n", device,
-                       strerror(-ret));
+        if (ret == -EBUSY) {
+            qerror_report(QERR_DEVICE_IN_USE, device);
+            return;
+        }
     }
 }
 
@@ -708,7 +700,6 @@ void qmp_transaction(BlockdevActionList *dev_list, Error **errp)
     int ret = 0;
     BlockdevActionList *dev_entry = dev_list;
     BlkTransactionStates *states, *next;
-    Error *local_err = NULL;
 
     QSIMPLEQ_HEAD(snap_bdrv_states, BlkTransactionStates) snap_bdrv_states;
     QSIMPLEQ_INIT(&snap_bdrv_states);
@@ -788,12 +779,12 @@ void qmp_transaction(BlockdevActionList *dev_list, Error **errp)
 
         /* create new image w/backing file */
         if (mode != NEW_IMAGE_MODE_EXISTING) {
-            bdrv_img_create(new_image_file, format,
-                            states->old_bs->filename,
-                            states->old_bs->drv->format_name,
-                            NULL, -1, flags, &local_err);
-            if (error_is_set(&local_err)) {
-                error_propagate(errp, local_err);
+            ret = bdrv_img_create(new_image_file, format,
+                                  states->old_bs->filename,
+                                  states->old_bs->drv->format_name,
+                                  NULL, -1, flags);
+            if (ret) {
+                error_set(errp, QERR_OPEN_FILE_FAILED, new_image_file);
                 goto delete_and_fail;
             }
         }
@@ -814,11 +805,6 @@ void qmp_transaction(BlockdevActionList *dev_list, Error **errp)
     QSIMPLEQ_FOREACH(states, &snap_bdrv_states, entry) {
         /* This removes our old bs from the bdrv_states, and adds the new bs */
         bdrv_append(states->new_bs, states->old_bs);
-        /* We don't need (or want) to use the transactional
-         * bdrv_reopen_multiple() across all the entries at once, because we
-         * don't want to abort all of them if one of them fails the reopen */
-        bdrv_reopen(states->new_bs, states->new_bs->open_flags & ~BDRV_O_RDWR,
-                    NULL);
     }
 
     /* success */
@@ -838,6 +824,7 @@ exit:
     QSIMPLEQ_FOREACH_SAFE(states, &snap_bdrv_states, entry, next) {
         g_free(states);
     }
+    return;
 }
 
 
@@ -1043,9 +1030,6 @@ void qmp_block_resize(const char *device, int64_t size, Error **errp)
         return;
     }
 
-    /* complete all in-flight operations before resizing the device */
-    bdrv_drain_all();
-
     switch (bdrv_truncate(bs, size)) {
     case 0:
         break;
@@ -1067,12 +1051,26 @@ void qmp_block_resize(const char *device, int64_t size, Error **errp)
     }
 }
 
-static void block_job_cb(void *opaque, int ret)
+static QObject *qobject_from_block_job(BlockJob *job)
+{
+    return qobject_from_jsonf("{ 'type': %s,"
+                              "'device': %s,"
+                              "'len': %" PRId64 ","
+                              "'offset': %" PRId64 ","
+                              "'speed': %" PRId64 " }",
+                              job->job_type->job_type,
+                              bdrv_get_device_name(job->bs),
+                              job->len,
+                              job->offset,
+                              job->speed);
+}
+
+static void block_stream_cb(void *opaque, int ret)
 {
     BlockDriverState *bs = opaque;
     QObject *obj;
 
-    trace_block_job_cb(bs, bs->job, ret);
+    trace_block_stream_cb(bs, bs->job, ret);
 
     assert(bs->job);
     obj = qobject_from_block_job(bs->job);
@@ -1092,18 +1090,13 @@ static void block_job_cb(void *opaque, int ret)
 }
 
 void qmp_block_stream(const char *device, bool has_base,
-                      const char *base, bool has_speed, int64_t speed,
-                      bool has_on_error, BlockdevOnError on_error,
-                      Error **errp)
+                      const char *base, bool has_speed,
+                      int64_t speed, Error **errp)
 {
     BlockDriverState *bs;
     BlockDriverState *base_bs = NULL;
     Error *local_err = NULL;
 
-    if (!has_on_error) {
-        on_error = BLOCKDEV_ON_ERROR_REPORT;
-    }
-
     bs = bdrv_find(device);
     if (!bs) {
         error_set(errp, QERR_DEVICE_NOT_FOUND, device);
@@ -1119,7 +1112,7 @@ void qmp_block_stream(const char *device, bool has_base,
     }
 
     stream_start(bs, base_bs, base, has_speed ? speed : 0,
-                 on_error, block_job_cb, bs, &local_err);
+                 block_stream_cb, bs, &local_err);
     if (error_is_set(&local_err)) {
         error_propagate(errp, local_err);
         return;
@@ -1133,210 +1126,6 @@ void qmp_block_stream(const char *device, bool has_base,
     trace_qmp_block_stream(bs, bs->job);
 }
 
-void qmp_block_commit(const char *device,
-                      bool has_base, const char *base, const char *top,
-                      bool has_speed, int64_t speed,
-                      Error **errp)
-{
-    BlockDriverState *bs;
-    BlockDriverState *base_bs, *top_bs;
-    Error *local_err = NULL;
-    /* This will be part of the QMP command, if/when the
-     * BlockdevOnError change for blkmirror makes it in
-     */
-    BlockdevOnError on_error = BLOCKDEV_ON_ERROR_REPORT;
-
-    /* drain all i/o before commits */
-    bdrv_drain_all();
-
-    bs = bdrv_find(device);
-    if (!bs) {
-        error_set(errp, QERR_DEVICE_NOT_FOUND, device);
-        return;
-    }
-
-    /* default top_bs is the active layer */
-    top_bs = bs;
-
-    if (top) {
-        if (strcmp(bs->filename, top) != 0) {
-            top_bs = bdrv_find_backing_image(bs, top);
-        }
-    }
-
-    if (top_bs == NULL) {
-        error_setg(errp, "Top image file %s not found", top ? top : "NULL");
-        return;
-    }
-
-    if (has_base && base) {
-        base_bs = bdrv_find_backing_image(top_bs, base);
-    } else {
-        base_bs = bdrv_find_base(top_bs);
-    }
-
-    if (base_bs == NULL) {
-        error_set(errp, QERR_BASE_NOT_FOUND, base ? base : "NULL");
-        return;
-    }
-
-    commit_start(bs, base_bs, top_bs, speed, on_error, block_job_cb, bs,
-                &local_err);
-    if (local_err != NULL) {
-        error_propagate(errp, local_err);
-        return;
-    }
-    /* Grab a reference so hotplug does not delete the BlockDriverState from
-     * underneath us.
-     */
-    drive_get_ref(drive_get_by_blockdev(bs));
-}
-
-#define DEFAULT_MIRROR_BUF_SIZE   (10 << 20)
-
-void qmp_drive_mirror(const char *device, const char *target,
-                      bool has_format, const char *format,
-                      enum MirrorSyncMode sync,
-                      bool has_mode, enum NewImageMode mode,
-                      bool has_speed, int64_t speed,
-                      bool has_granularity, uint32_t granularity,
-                      bool has_buf_size, int64_t buf_size,
-                      bool has_on_source_error, BlockdevOnError on_source_error,
-                      bool has_on_target_error, BlockdevOnError on_target_error,
-                      Error **errp)
-{
-    BlockDriverState *bs;
-    BlockDriverState *source, *target_bs;
-    BlockDriver *proto_drv;
-    BlockDriver *drv = NULL;
-    Error *local_err = NULL;
-    int flags;
-    uint64_t size;
-    int ret;
-
-    if (!has_speed) {
-        speed = 0;
-    }
-    if (!has_on_source_error) {
-        on_source_error = BLOCKDEV_ON_ERROR_REPORT;
-    }
-    if (!has_on_target_error) {
-        on_target_error = BLOCKDEV_ON_ERROR_REPORT;
-    }
-    if (!has_mode) {
-        mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS;
-    }
-    if (!has_granularity) {
-        granularity = 0;
-    }
-    if (!has_buf_size) {
-        buf_size = DEFAULT_MIRROR_BUF_SIZE;
-    }
-
-    if (granularity != 0 && (granularity < 512 || granularity > 1048576 * 64)) {
-        error_set(errp, QERR_INVALID_PARAMETER, device);
-        return;
-    }
-    if (granularity & (granularity - 1)) {
-        error_set(errp, QERR_INVALID_PARAMETER, device);
-        return;
-    }
-
-    bs = bdrv_find(device);
-    if (!bs) {
-        error_set(errp, QERR_DEVICE_NOT_FOUND, device);
-        return;
-    }
-
-    if (!bdrv_is_inserted(bs)) {
-        error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);
-        return;
-    }
-
-    if (!has_format) {
-        format = mode == NEW_IMAGE_MODE_EXISTING ? NULL : bs->drv->format_name;
-    }
-    if (format) {
-        drv = bdrv_find_format(format);
-        if (!drv) {
-            error_set(errp, QERR_INVALID_BLOCK_FORMAT, format);
-            return;
-        }
-    }
-
-    if (bdrv_in_use(bs)) {
-        error_set(errp, QERR_DEVICE_IN_USE, device);
-        return;
-    }
-
-    flags = bs->open_flags | BDRV_O_RDWR;
-    source = bs->backing_hd;
-    if (!source && sync == MIRROR_SYNC_MODE_TOP) {
-        sync = MIRROR_SYNC_MODE_FULL;
-    }
-
-    proto_drv = bdrv_find_protocol(target);
-    if (!proto_drv) {
-        error_set(errp, QERR_INVALID_BLOCK_FORMAT, format);
-        return;
-    }
-
-    bdrv_get_geometry(bs, &size);
-    size *= 512;
-    if (sync == MIRROR_SYNC_MODE_FULL && mode != NEW_IMAGE_MODE_EXISTING) {
-        /* create new image w/o backing file */
-        assert(format && drv);
-        bdrv_img_create(target, format,
-                        NULL, NULL, NULL, size, flags, &local_err);
-    } else {
-        switch (mode) {
-        case NEW_IMAGE_MODE_EXISTING:
-            ret = 0;
-            break;
-        case NEW_IMAGE_MODE_ABSOLUTE_PATHS:
-            /* create new image with backing file */
-            bdrv_img_create(target, format,
-                            source->filename,
-                            source->drv->format_name,
-                            NULL, size, flags, &local_err);
-            break;
-        default:
-            abort();
-        }
-    }
-
-    if (error_is_set(&local_err)) {
-        error_propagate(errp, local_err);
-        return;
-    }
-
-    /* Mirroring takes care of copy-on-write using the source's backing
-     * file.
-     */
-    target_bs = bdrv_new("");
-    ret = bdrv_open(target_bs, target, flags | BDRV_O_NO_BACKING, drv);
-
-    if (ret < 0) {
-        bdrv_delete(target_bs);
-        error_set(errp, QERR_OPEN_FILE_FAILED, target);
-        return;
-    }
-
-    mirror_start(bs, target_bs, speed, granularity, buf_size, sync,
-                 on_source_error, on_target_error,
-                 block_job_cb, bs, &local_err);
-    if (local_err != NULL) {
-        bdrv_delete(target_bs);
-        error_propagate(errp, local_err);
-        return;
-    }
-
-    /* Grab a reference so hotplug does not delete the BlockDriverState from
-     * underneath us.
-     */
-    drive_get_ref(drive_get_by_blockdev(bs));
-}
-
 static BlockJob *find_block_job(const char *device)
 {
     BlockDriverState *bs;
@@ -1353,28 +1142,19 @@ void qmp_block_job_set_speed(const char *device, int64_t speed, Error **errp)
     BlockJob *job = find_block_job(device);
 
     if (!job) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
+        error_set(errp, QERR_DEVICE_NOT_ACTIVE, device);
         return;
     }
 
     block_job_set_speed(job, speed, errp);
 }
 
-void qmp_block_job_cancel(const char *device,
-                          bool has_force, bool force, Error **errp)
+void qmp_block_job_cancel(const char *device, Error **errp)
 {
     BlockJob *job = find_block_job(device);
 
-    if (!has_force) {
-        force = false;
-    }
-
     if (!job) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
-        return;
-    }
-    if (job->paused && !force) {
-        error_set(errp, QERR_BLOCK_JOB_PAUSED, device);
+        error_set(errp, QERR_DEVICE_NOT_ACTIVE, device);
         return;
     }
 
@@ -1382,53 +1162,25 @@ void qmp_block_job_cancel(const char *device,
     block_job_cancel(job);
 }
 
-void qmp_block_job_pause(const char *device, Error **errp)
-{
-    BlockJob *job = find_block_job(device);
-
-    if (!job) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
-        return;
-    }
-
-    trace_qmp_block_job_pause(job);
-    block_job_pause(job);
-}
-
-void qmp_block_job_resume(const char *device, Error **errp)
-{
-    BlockJob *job = find_block_job(device);
-
-    if (!job) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
-        return;
-    }
-
-    trace_qmp_block_job_resume(job);
-    block_job_resume(job);
-}
-
-void qmp_block_job_complete(const char *device, Error **errp)
-{
-    BlockJob *job = find_block_job(device);
-
-    if (!job) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
-        return;
-    }
-
-    trace_qmp_block_job_complete(job);
-    block_job_complete(job, errp);
-}
-
 static void do_qmp_query_block_jobs_one(void *opaque, BlockDriverState *bs)
 {
     BlockJobInfoList **prev = opaque;
     BlockJob *job = bs->job;
 
     if (job) {
-        BlockJobInfoList *elem = g_new0(BlockJobInfoList, 1);
-        elem->value = block_job_query(bs->job);
+        BlockJobInfoList *elem;
+        BlockJobInfo *info = g_new(BlockJobInfo, 1);
+        *info = (BlockJobInfo){
+            .type   = g_strdup(job->job_type->job_type),
+            .device = g_strdup(bdrv_get_device_name(bs)),
+            .len    = job->len,
+            .offset = job->offset,
+            .speed  = job->speed,
+        };
+
+        elem = g_new0(BlockJobInfoList, 1);
+        elem->value = info;
+
         (*prev)->next = elem;
         *prev = elem;
     }
@@ -1442,121 +1194,3 @@ BlockJobInfoList *qmp_query_block_jobs(Error **errp)
     bdrv_iterate(do_qmp_query_block_jobs_one, &prev);
     return dummy.next;
 }
-
-QemuOptsList qemu_drive_opts = {
-    .name = "drive",
-    .head = QTAILQ_HEAD_INITIALIZER(qemu_drive_opts.head),
-    .desc = {
-        {
-            .name = "bus",
-            .type = QEMU_OPT_NUMBER,
-            .help = "bus number",
-        },{
-            .name = "unit",
-            .type = QEMU_OPT_NUMBER,
-            .help = "unit number (i.e. lun for scsi)",
-        },{
-            .name = "if",
-            .type = QEMU_OPT_STRING,
-            .help = "interface (ide, scsi, sd, mtd, floppy, pflash, virtio)",
-        },{
-            .name = "index",
-            .type = QEMU_OPT_NUMBER,
-            .help = "index number",
-        },{
-            .name = "cyls",
-            .type = QEMU_OPT_NUMBER,
-            .help = "number of cylinders (ide disk geometry)",
-        },{
-            .name = "heads",
-            .type = QEMU_OPT_NUMBER,
-            .help = "number of heads (ide disk geometry)",
-        },{
-            .name = "secs",
-            .type = QEMU_OPT_NUMBER,
-            .help = "number of sectors (ide disk geometry)",
-        },{
-            .name = "trans",
-            .type = QEMU_OPT_STRING,
-            .help = "chs translation (auto, lba. none)",
-        },{
-            .name = "media",
-            .type = QEMU_OPT_STRING,
-            .help = "media type (disk, cdrom)",
-        },{
-            .name = "snapshot",
-            .type = QEMU_OPT_BOOL,
-            .help = "enable/disable snapshot mode",
-        },{
-            .name = "file",
-            .type = QEMU_OPT_STRING,
-            .help = "disk image",
-        },{
-            .name = "cache",
-            .type = QEMU_OPT_STRING,
-            .help = "host cache usage (none, writeback, writethrough, "
-                    "directsync, unsafe)",
-        },{
-            .name = "aio",
-            .type = QEMU_OPT_STRING,
-            .help = "host AIO implementation (threads, native)",
-        },{
-            .name = "format",
-            .type = QEMU_OPT_STRING,
-            .help = "disk format (raw, qcow2, ...)",
-        },{
-            .name = "serial",
-            .type = QEMU_OPT_STRING,
-            .help = "disk serial number",
-        },{
-            .name = "rerror",
-            .type = QEMU_OPT_STRING,
-            .help = "read error action",
-        },{
-            .name = "werror",
-            .type = QEMU_OPT_STRING,
-            .help = "write error action",
-        },{
-            .name = "addr",
-            .type = QEMU_OPT_STRING,
-            .help = "pci address (virtio only)",
-        },{
-            .name = "readonly",
-            .type = QEMU_OPT_BOOL,
-            .help = "open drive file as read-only",
-        },{
-            .name = "iops",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit total I/O operations per second",
-        },{
-            .name = "iops_rd",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit read operations per second",
-        },{
-            .name = "iops_wr",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit write operations per second",
-        },{
-            .name = "bps",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit total bytes per second",
-        },{
-            .name = "bps_rd",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit read bytes per second",
-        },{
-            .name = "bps_wr",
-            .type = QEMU_OPT_NUMBER,
-            .help = "limit write bytes per second",
-        },{
-            .name = "copy-on-read",
-            .type = QEMU_OPT_BOOL,
-            .help = "copy read data from backing file into image file",
-        },{
-            .name = "boot",
-            .type = QEMU_OPT_BOOL,
-            .help = "(deprecated, ignored)",
-        },
-        { /* end of list */ }
-    },
-};

blockdev.h

@@ -10,22 +10,17 @@
 #ifndef BLOCKDEV_H
 #define BLOCKDEV_H
 
-#include "block/block.h"
-#include "qapi/error.h"
-#include "qemu/queue.h"
+#include "block.h"
+#include "error.h"
+#include "qemu-queue.h"
 
 void blockdev_mark_auto_del(BlockDriverState *bs);
 void blockdev_auto_del(BlockDriverState *bs);
 
 typedef enum {
     IF_DEFAULT = -1,            /* for use with drive_add() only */
-    /*
-     * IF_IDE must be zero, because we want QEMUMachine member
-     * block_default_type to default-initialize to IF_IDE
-     */
-    IF_IDE = 0,
     IF_NONE,
-    IF_SCSI, IF_FLOPPY, IF_PFLASH, IF_MTD, IF_SD, IF_VIRTIO, IF_XEN,
+    IF_IDE, IF_SCSI, IF_FLOPPY, IF_PFLASH, IF_MTD, IF_SD, IF_VIRTIO, IF_XEN,
     IF_COUNT
 } BlockInterfaceType;
 
@@ -56,7 +51,7 @@ DriveInfo *drive_get_by_blockdev(BlockDriverState *bs);
 QemuOpts *drive_def(const char *optstr);
 QemuOpts *drive_add(BlockInterfaceType type, int index, const char *file,
                     const char *optstr);
-DriveInfo *drive_init(QemuOpts *arg, BlockInterfaceType block_default_type);
+DriveInfo *drive_init(QemuOpts *arg, int default_to_scsi);
 
 /* device-hotplug */
 

blockjob.c

@@ -1,283 +0,0 @@
-/*
- * QEMU System Emulator block driver
- *
- * Copyright (c) 2011 IBM Corp.
- * Copyright (c) 2012 Red Hat, Inc.
- *
- * 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 "qemu-common.h"
-#include "trace.h"
-#include "monitor/monitor.h"
-#include "block/block.h"
-#include "block/blockjob.h"
-#include "block/block_int.h"
-#include "qapi/qmp/qjson.h"
-#include "block/coroutine.h"
-#include "qmp-commands.h"
-#include "qemu/timer.h"
-
-void *block_job_create(const BlockJobType *job_type, BlockDriverState *bs,
-                       int64_t speed, BlockDriverCompletionFunc *cb,
-                       void *opaque, Error **errp)
-{
-    BlockJob *job;
-
-    if (bs->job || bdrv_in_use(bs)) {
-        error_set(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
-        return NULL;
-    }
-    bdrv_set_in_use(bs, 1);
-
-    job = g_malloc0(job_type->instance_size);
-    job->job_type      = job_type;
-    job->bs            = bs;
-    job->cb            = cb;
-    job->opaque        = opaque;
-    job->busy          = true;
-    bs->job = job;
-
-    /* Only set speed when necessary to avoid NotSupported error */
-    if (speed != 0) {
-        Error *local_err = NULL;
-
-        block_job_set_speed(job, speed, &local_err);
-        if (error_is_set(&local_err)) {
-            bs->job = NULL;
-            g_free(job);
-            bdrv_set_in_use(bs, 0);
-            error_propagate(errp, local_err);
-            return NULL;
-        }
-    }
-    return job;
-}
-
-void block_job_completed(BlockJob *job, int ret)
-{
-    BlockDriverState *bs = job->bs;
-
-    assert(bs->job == job);
-    job->cb(job->opaque, ret);
-    bs->job = NULL;
-    g_free(job);
-    bdrv_set_in_use(bs, 0);
-}
-
-void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
-{
-    Error *local_err = NULL;
-
-    if (!job->job_type->set_speed) {
-        error_set(errp, QERR_NOT_SUPPORTED);
-        return;
-    }
-    job->job_type->set_speed(job, speed, &local_err);
-    if (error_is_set(&local_err)) {
-        error_propagate(errp, local_err);
-        return;
-    }
-
-    job->speed = speed;
-}
-
-void block_job_complete(BlockJob *job, Error **errp)
-{
-    if (job->paused || job->cancelled || !job->job_type->complete) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_READY, job->bs->device_name);
-        return;
-    }
-
-    job->job_type->complete(job, errp);
-}
-
-void block_job_pause(BlockJob *job)
-{
-    job->paused = true;
-}
-
-bool block_job_is_paused(BlockJob *job)
-{
-    return job->paused;
-}
-
-void block_job_resume(BlockJob *job)
-{
-    job->paused = false;
-    block_job_iostatus_reset(job);
-    if (job->co && !job->busy) {
-        qemu_coroutine_enter(job->co, NULL);
-    }
-}
-
-void block_job_cancel(BlockJob *job)
-{
-    job->cancelled = true;
-    block_job_resume(job);
-}
-
-bool block_job_is_cancelled(BlockJob *job)
-{
-    return job->cancelled;
-}
-
-void block_job_iostatus_reset(BlockJob *job)
-{
-    job->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
-    if (job->job_type->iostatus_reset) {
-        job->job_type->iostatus_reset(job);
-    }
-}
-
-struct BlockCancelData {
-    BlockJob *job;
-    BlockDriverCompletionFunc *cb;
-    void *opaque;
-    bool cancelled;
-    int ret;
-};
-
-static void block_job_cancel_cb(void *opaque, int ret)
-{
-    struct BlockCancelData *data = opaque;
-
-    data->cancelled = block_job_is_cancelled(data->job);
-    data->ret = ret;
-    data->cb(data->opaque, ret);
-}
-
-int block_job_cancel_sync(BlockJob *job)
-{
-    struct BlockCancelData data;
-    BlockDriverState *bs = job->bs;
-
-    assert(bs->job == job);
-
-    /* Set up our own callback to store the result and chain to
-     * the original callback.
-     */
-    data.job = job;
-    data.cb = job->cb;
-    data.opaque = job->opaque;
-    data.ret = -EINPROGRESS;
-    job->cb = block_job_cancel_cb;
-    job->opaque = &data;
-    block_job_cancel(job);
-    while (data.ret == -EINPROGRESS) {
-        qemu_aio_wait();
-    }
-    return (data.cancelled && data.ret == 0) ? -ECANCELED : data.ret;
-}
-
-void block_job_sleep_ns(BlockJob *job, QEMUClock *clock, int64_t ns)
-{
-    assert(job->busy);
-
-    /* Check cancellation *before* setting busy = false, too!  */
-    if (block_job_is_cancelled(job)) {
-        return;
-    }
-
-    job->busy = false;
-    if (block_job_is_paused(job)) {
-        qemu_coroutine_yield();
-    } else {
-        co_sleep_ns(clock, ns);
-    }
-    job->busy = true;
-}
-
-BlockJobInfo *block_job_query(BlockJob *job)
-{
-    BlockJobInfo *info = g_new0(BlockJobInfo, 1);
-    info->type      = g_strdup(job->job_type->job_type);
-    info->device    = g_strdup(bdrv_get_device_name(job->bs));
-    info->len       = job->len;
-    info->busy      = job->busy;
-    info->paused    = job->paused;
-    info->offset    = job->offset;
-    info->speed     = job->speed;
-    info->io_status = job->iostatus;
-    return info;
-}
-
-static void block_job_iostatus_set_err(BlockJob *job, int error)
-{
-    if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
-        job->iostatus = error == ENOSPC ? BLOCK_DEVICE_IO_STATUS_NOSPACE :
-                                          BLOCK_DEVICE_IO_STATUS_FAILED;
-    }
-}
-
-
-QObject *qobject_from_block_job(BlockJob *job)
-{
-    return qobject_from_jsonf("{ 'type': %s,"
-                              "'device': %s,"
-                              "'len': %" PRId64 ","
-                              "'offset': %" PRId64 ","
-                              "'speed': %" PRId64 " }",
-                              job->job_type->job_type,
-                              bdrv_get_device_name(job->bs),
-                              job->len,
-                              job->offset,
-                              job->speed);
-}
-
-void block_job_ready(BlockJob *job)
-{
-    QObject *data = qobject_from_block_job(job);
-    monitor_protocol_event(QEVENT_BLOCK_JOB_READY, data);
-    qobject_decref(data);
-}
-
-BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
-                                        BlockdevOnError on_err,
-                                        int is_read, int error)
-{
-    BlockErrorAction action;
-
-    switch (on_err) {
-    case BLOCKDEV_ON_ERROR_ENOSPC:
-        action = (error == ENOSPC) ? BDRV_ACTION_STOP : BDRV_ACTION_REPORT;
-        break;
-    case BLOCKDEV_ON_ERROR_STOP:
-        action = BDRV_ACTION_STOP;
-        break;
-    case BLOCKDEV_ON_ERROR_REPORT:
-        action = BDRV_ACTION_REPORT;
-        break;
-    case BLOCKDEV_ON_ERROR_IGNORE:
-        action = BDRV_ACTION_IGNORE;
-        break;
-    default:
-        abort();
-    }
-    bdrv_emit_qmp_error_event(job->bs, QEVENT_BLOCK_JOB_ERROR, action, is_read);
-    if (action == BDRV_ACTION_STOP) {
-        block_job_pause(job);
-        block_job_iostatus_set_err(job, error);
-        if (bs != job->bs) {
-            bdrv_iostatus_set_err(bs, error);
-        }
-    }
-    return action;
-}

bsd-user/elfload.c

@@ -10,7 +10,7 @@
 #include <string.h>
 
 #include "qemu.h"
-#include "disas/disas.h"
+#include "disas.h"
 
 #ifdef _ARCH_PPC64
 #undef ARCH_DLINFO

bsd-user/main.c

@@ -31,8 +31,8 @@
 /* For tb_lock */
 #include "cpu.h"
 #include "tcg.h"
-#include "qemu/timer.h"
-#include "qemu/envlist.h"
+#include "qemu-timer.h"
+#include "envlist.h"
 
 #define DEBUG_LOGFILE "/tmp/qemu.log"
 
@@ -917,7 +917,7 @@ int main(int argc, char **argv)
         fprintf(stderr, "Unable to find CPU definition\n");
         exit(1);
     }
-#if defined(TARGET_SPARC) || defined(TARGET_PPC)
+#if defined(TARGET_I386) || defined(TARGET_SPARC) || defined(TARGET_PPC)
     cpu_reset(ENV_GET_CPU(env));
 #endif
     thread_env = env;

bsd-user/mmap.c

@@ -74,7 +74,7 @@ void mmap_unlock(void)
 }
 #endif
 
-static void *bsd_vmalloc(size_t size)
+void *qemu_vmalloc(size_t size)
 {
     void *p;
     mmap_lock();
@@ -98,7 +98,7 @@ void *g_malloc(size_t size)
 {
     char * p;
     size += 16;
-    p = bsd_vmalloc(size);
+    p = qemu_vmalloc(size);
     *(size_t *)p = size;
     return p + 16;
 }

bsd-user/qemu-types.h

@@ -0,0 +1,24 @@
+#ifndef QEMU_TYPES_H
+#define QEMU_TYPES_H
+#include "cpu.h"
+
+#ifdef TARGET_ABI32
+typedef uint32_t abi_ulong;
+typedef int32_t abi_long;
+#define TARGET_ABI_FMT_lx "%08x"
+#define TARGET_ABI_FMT_ld "%d"
+#define TARGET_ABI_FMT_lu "%u"
+#define TARGET_ABI_BITS 32
+#else
+typedef target_ulong abi_ulong;
+typedef target_long abi_long;
+#define TARGET_ABI_FMT_lx TARGET_FMT_lx
+#define TARGET_ABI_FMT_ld TARGET_FMT_ld
+#define TARGET_ABI_FMT_lu TARGET_FMT_lu
+#define TARGET_ABI_BITS TARGET_LONG_BITS
+/* for consistency, define ABI32 too */
+#if TARGET_ABI_BITS == 32
+#define TARGET_ABI32 1
+#endif
+#endif
+#endif