update VERSION for 1.1.2

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

.exrc

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

.gitignore

@@ -12,6 +12,8 @@ trace-dtrace.dtrace
 *-linux-user
 *-bsd-user
 libdis*
+libhw32
+libhw64
 libuser
 linux-headers/asm
 qapi-generated
@@ -39,14 +41,12 @@ qemu-io
 qemu-ga
 qemu-bridge-helper
 qemu-monitor.texi
-vscclient
 QMP/qmp-commands.txt
 test-coroutine
 test-qmp-input-visitor
 test-qmp-output-visitor
 test-string-input-visitor
 test-string-output-visitor
-test-visitor-serialization
 fsdev/virtfs-proxy-helper.1
 fsdev/virtfs-proxy-helper.pod
 .gdbinit
@@ -69,10 +69,6 @@ fsdev/virtfs-proxy-helper.pod
 *.vr
 *.d
 *.o
-*.lo
-*.la
-*.pc
-.libs
 *.swp
 *.orig
 .pc

.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)

MAINTAINERS

@@ -207,12 +207,6 @@ M: qemu-devel@nongnu.org
 S: Orphan
 F: hw/gumstix.c
 
-i.MX31
-M: Peter Chubb <peter.chubb@nicta.com.au>
-S: Odd fixes
-F: hw/imx*
-F: hw/kzm.c
-
 Integrator CP
 M: Paul Brook <paul@codesourcery.com>
 M: Peter Maydell <peter.maydell@linaro.org>
@@ -268,7 +262,6 @@ S: Maintained
 F: hw/xilinx_zynq.c
 F: hw/zynq_slcr.c
 F: hw/cadence_*
-F: hw/xilinx_spips.c
 
 CRIS Machines
 -------------
@@ -318,11 +311,6 @@ M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
 S: Maintained
 F: hw/petalogix_s3adsp1800.c
 
-petalogix_ml605
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-S: Maintained
-F: hw/petalogix_ml605_mmu.c
-
 MIPS Machines
 -------------
 Jazz
@@ -350,31 +338,9 @@ 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
@@ -397,19 +363,6 @@ S: Odd Fixes
 F: hw/ppc_prep.c
 F: hw/prep_pci.[hc]
 
-sPAPR
-M: David Gibson <david@gibson.dropbear.id.au>
-M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/spapr*
-
-virtex_ml507
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/virtex_ml507.c
-
 SH4 Machines
 ------------
 R2D
@@ -434,12 +387,6 @@ M: Blue Swirl <blauwirbel@gmail.com>
 S: Maintained
 F: hw/sun4u.c
 
-Leon3
-M: Fabien Chouteau <chouteau@adacore.com>
-S: Maintained
-F: hw/leon3.c
-F: hw/grlib*
-
 S390 Machines
 -------------
 S390 Virtio
@@ -447,14 +394,6 @@ M: Alexander Graf <agraf@suse.de>
 S: Maintained
 F: hw/s390-*.c
 
-UniCore32 Machines
--------------
-PKUnity-3 SoC initramfs-with-busybox
-M: Guan Xuetao <gxt@mprc.pku.edu.cn>
-S: Maintained
-F: hw/puv3*
-F: hw/unicore32/
-
 X86 Machines
 ------------
 PC
@@ -493,19 +432,6 @@ S: Supported
 F: hw/pci*
 F: hw/piix*
 
-ppc4xx
-M: Alexander Graf <agraf@suse.de>
-L: qemu-ppc@nongnu.org
-S: Odd Fixes
-F: hw/ppc4xx*.[hc]
-
-ppce500
-M: Alexander Graf <agraf@suse.de>
-M: Scott Wood <scottwood@freescale.com>
-L: qemu-ppc@nongnu.org
-S: Supported
-F: hw/ppce500_*
-
 SCSI
 M: Paolo Bonzini <pbonzini@redhat.com>
 S: Supported
@@ -518,22 +444,11 @@ 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
@@ -553,7 +468,6 @@ 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*
 
@@ -563,18 +477,6 @@ S: Supported
 F: hw/virtio-serial*
 F: hw/virtio-console*
 
-Xilinx EDK
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
-S: Maintained
-F: hw/xilinx_axi*
-F: hw/xilinx_uartlite.c
-F: hw/xilinx_intc.c
-F: hw/xilinx_ethlite.c
-F: hw/xilinx_timer.c
-F: hw/xilinx.h
-F: hw/xilinx_spi.c
-
 Subsystems
 ----------
 Audio
@@ -584,7 +486,6 @@ F: audio/
 
 Block
 M: Kevin Wolf <kwolf@redhat.com>
-M: Stefan Hajnoczi <stefanha@redhat.com>
 S: Supported
 F: block*
 F: block/
@@ -594,18 +495,6 @@ M: Anthony Liguori <aliguori@us.ibm.com>
 S: Maintained
 F: qemu-char.c
 
-CPU
-M: Andreas Färber <afaerber@suse.de>
-S: Supported
-F: qom/cpu.c
-F: include/qemu/cpu.h
-
-Device Tree
-M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
-M: Alexander Graf <agraf@suse.de>
-S: Maintained
-F: device-tree.[ch]
-
 GDB stub
 M: qemu-devel@nongnu.org
 S: Odd Fixes
@@ -643,10 +532,9 @@ F: monitor.c
 
 Network device layer
 M: Anthony Liguori <aliguori@us.ibm.com>
-M: Stefan Hajnoczi <stefanha@redhat.com>
+M: Mark McLoughlin <markmc@redhat.com>
 S: Maintained
 F: net/
-T: git git://github.com/stefanha/qemu.git net
 
 Network Block Device (NBD)
 M: Paolo Bonzini <pbonzini@redhat.com>
@@ -663,7 +551,7 @@ F: slirp/
 T: git git://git.kiszka.org/qemu.git queues/slirp
 
 Tracing
-M: Stefan Hajnoczi <stefanha@redhat.com>
+M: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
 S: Maintained
 F: trace/
 F: scripts/tracetool.py

Makefile

@@ -6,30 +6,17 @@ BUILD_DIR=$(CURDIR)
 # All following code might depend on configuration variables
 ifneq ($(wildcard config-host.mak),)
 # Put the all: rule here so that config-host.mak can contain dependencies.
-all:
+all: build-all
 include config-host.mak
-
-# Check that we're not trying to do an out-of-tree build from
-# a tree that's been used for an in-tree build.
-ifneq ($(realpath $(SRC_PATH)),$(realpath .))
-ifneq ($(wildcard $(SRC_PATH)/config-host.mak),)
-$(error This is an out of tree build but your source tree ($(SRC_PATH)) \
-seems to have been used for an in-tree build. You can fix this by running \
-"make distclean && rm -rf *-linux-user *-softmmu" in your source tree)
-endif
-endif
-
 include $(SRC_PATH)/rules.mak
 config-host.mak: $(SRC_PATH)/configure
 	@echo $@ is out-of-date, running configure
 	@sed -n "/.*Configured with/s/[^:]*: //p" $@ | sh
 else
 config-host.mak:
-ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
 	@echo "Please call configure before running make!"
 	@exit 1
 endif
-endif
 
 GENERATED_HEADERS = config-host.h trace.h qemu-options.def
 ifeq ($(TRACE_BACKEND),dtrace)
@@ -44,9 +31,9 @@ Makefile: ;
 configure: ;
 
 .PHONY: all clean cscope distclean dvi html info install install-doc \
-	pdf recurse-all speed test dist
+	pdf recurse-all speed tar tarbin test build-all
 
-$(call set-vpath, $(SRC_PATH))
+$(call set-vpath, $(SRC_PATH):$(SRC_PATH)/hw)
 
 LIBS+=-lz $(LIBS_TOOLS)
 
@@ -65,13 +52,8 @@ SUBDIR_MAKEFLAGS=$(if $(V),,--no-print-directory) BUILD_DIR=$(BUILD_DIR)
 SUBDIR_DEVICES_MAK=$(patsubst %, %/config-devices.mak, $(TARGET_DIRS))
 SUBDIR_DEVICES_MAK_DEP=$(patsubst %, %/config-devices.mak.d, $(TARGET_DIRS))
 
-ifeq ($(SUBDIR_DEVICES_MAK),)
-config-all-devices.mak:
-	$(call quiet-command,echo '# no devices' > $@,"  GEN   $@")
-else
 config-all-devices.mak: $(SUBDIR_DEVICES_MAK)
 	$(call quiet-command,cat $(SUBDIR_DEVICES_MAK) | grep =y | sort -u > $@,"  GEN   $@")
-endif
 
 -include $(SUBDIR_DEVICES_MAK_DEP)
 
@@ -100,7 +82,7 @@ defconfig:
 
 -include config-all-devices.mak
 
-all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all
+build-all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all
 
 config-host.h: config-host.h-timestamp
 config-host.h-timestamp: config-host.mak
@@ -109,29 +91,19 @@ qemu-options.def: $(SRC_PATH)/qemu-options.hx
 
 SUBDIR_RULES=$(patsubst %,subdir-%, $(TARGET_DIRS))
 
-subdir-%:
+subdir-%: $(GENERATED_HEADERS)
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C $* V="$(V)" TARGET_DIR="$*/" all,)
 
 ifneq ($(wildcard config-host.mak),)
 include $(SRC_PATH)/Makefile.objs
 endif
 
+$(universal-obj-y) $(common-obj-y): $(GENERATED_HEADERS)
 subdir-libcacard: $(oslib-obj-y) $(trace-obj-y) qemu-timer-common.o
 
-subdir-pixman: pixman/Makefile
-	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C pixman V="$(V)" all,)
+$(filter %-softmmu,$(SUBDIR_RULES)): $(universal-obj-y) $(trace-obj-y) $(common-obj-y) subdir-libdis
 
-pixman/Makefile: $(SRC_PATH)/pixman/configure
-	(cd pixman; CFLAGS="$(CFLAGS) -fPIC" $(SRC_PATH)/pixman/configure $(AUTOCONF_HOST) --disable-gtk --disable-shared --enable-static)
-
-$(SRC_PATH)/pixman/configure:
-	(cd $(SRC_PATH)/pixman; autoreconf -v --install)
-
-$(SUBDIR_RULES): libqemustub.a
-
-$(filter %-softmmu,$(SUBDIR_RULES)): $(universal-obj-y) $(trace-obj-y) $(common-obj-y) $(extra-obj-y) subdir-libdis
-
-$(filter %-user,$(SUBDIR_RULES)): $(universal-obj-y) $(trace-obj-y) subdir-libdis-user subdir-libuser
+$(filter %-user,$(SUBDIR_RULES)): $(GENERATED_HEADERS) $(universal-obj-y) $(trace-obj-y) subdir-libdis-user subdir-libuser
 
 ROMSUBDIR_RULES=$(patsubst %,romsubdir-%, $(ROMS))
 romsubdir-%:
@@ -149,7 +121,7 @@ QEMU_CFLAGS += -I$(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/sdl.o audio/sdlaudio.o ui/sdl_zoom.o baum.o: QEMU_CFLAGS += $(SDL_CFLAGS)
 
 ui/vnc.o: QEMU_CFLAGS += $(VNC_TLS_CFLAGS)
 
@@ -159,12 +131,6 @@ version.o: $(SRC_PATH)/version.rc config-host.h
 	$(call quiet-command,$(WINDRES) -I. -o $@ $<,"  RC    $(TARGET_DIR)$@")
 
 version-obj-$(CONFIG_WIN32) += version.o
-
-######################################################################
-# Build library with stubs
-
-libqemustub.a: $(stub-obj-y)
-
 ######################################################################
 # Support building shared library libcacard
 
@@ -176,29 +142,27 @@ libcacard.la:
 install-libcacard:
 	@echo "libtool is missing, please install and rerun configure"; exit 1
 else
-libcacard.la: $(oslib-obj-y) qemu-timer-common.o $(addsuffix .lo, $(basename $(trace-obj-y)))
+libcacard.la: $(GENERATED_HEADERS) $(oslib-obj-y) qemu-timer-common.o $(addsuffix .lo, $(basename $(trace-obj-y)))
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C libcacard V="$(V)" TARGET_DIR="$*/" libcacard.la,)
 
 install-libcacard: libcacard.la
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C libcacard V="$(V)" TARGET_DIR="$*/" install-libcacard,)
 endif
-
 ######################################################################
 
 qemu-img.o: qemu-img-cmds.h
+qemu-img.o qemu-tool.o qemu-nbd.o qemu-io.o cmd.o qemu-ga.o: $(GENERATED_HEADERS)
 
 tools-obj-y = $(oslib-obj-y) $(trace-obj-y) qemu-tool.o qemu-timer.o \
-	main-loop.o iohandler.o error.o
+	qemu-timer-common.o main-loop.o notify.o iohandler.o cutils.o async.o
 tools-obj-$(CONFIG_POSIX) += compatfd.o
 
-qemu-img$(EXESUF): qemu-img.o $(tools-obj-y) $(block-obj-y) libqemustub.a
-qemu-nbd$(EXESUF): qemu-nbd.o $(tools-obj-y) $(block-obj-y) libqemustub.a
-qemu-io$(EXESUF): qemu-io.o cmd.o $(tools-obj-y) $(block-obj-y) libqemustub.a
+qemu-img$(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$(EXESUF): qemu-bridge-helper.o
-
-vscclient$(EXESUF): $(libcacard-y) $(oslib-obj-y) $(trace-obj-y) libcacard/vscclient.o libqemustub.a
-	$(call quiet-command,$(CC) $(LDFLAGS) -o $@ $^ $(libcacard_libs) $(LIBS),"  LINK  $@")
+qemu-bridge-helper.o: $(GENERATED_HEADERS)
 
 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
@@ -206,8 +170,10 @@ fsdev/virtfs-proxy-helper$(EXESUF): LIBS += -lcap
 qemu-img-cmds.h: $(SRC_PATH)/qemu-img-cmds.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $@")
 
+$(qapi-obj-y): $(GENERATED_HEADERS)
+qapi-dir := $(BUILD_DIR)/qapi-generated
 qemu-ga$(EXESUF): LIBS = $(LIBS_QGA)
-qemu-ga$(EXESUF): QEMU_CFLAGS += -I qga/qapi-generated
+qemu-ga$(EXESUF): QEMU_CFLAGS += -I $(qapi-dir)
 
 gen-out-type = $(subst .,-,$(suffix $@))
 
@@ -215,63 +181,57 @@ 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)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, "  GEN   $@")
-qga/qapi-generated/qga-qapi-visit.c qga/qapi-generated/qga-qapi-visit.h :\
-$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, "  GEN   $@")
-qga/qapi-generated/qga-qmp-commands.h qga/qapi-generated/qga-qmp-marshal.c :\
-$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, "  GEN   $@")
+$(qapi-dir)/qga-qapi-types.c $(qapi-dir)/qga-qapi-types.h :\
+$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-types.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py $(gen-out-type) -o "$(qapi-dir)" -p "qga-" < $<, "  GEN   $@")
+$(qapi-dir)/qga-qapi-visit.c $(qapi-dir)/qga-qapi-visit.h :\
+$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-visit.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py $(gen-out-type) -o "$(qapi-dir)" -p "qga-" < $<, "  GEN   $@")
+$(qapi-dir)/qga-qmp-commands.h $(qapi-dir)/qga-qmp-marshal.c :\
+$(SRC_PATH)/qapi-schema-guest.json $(SRC_PATH)/scripts/qapi-commands.py
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py $(gen-out-type) -o "$(qapi-dir)" -p "qga-" < $<, "  GEN   $@")
 
 qapi-types.c qapi-types.h :\
-$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
+$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py $(gen-out-type) -o "." < $<, "  GEN   $@")
 qapi-visit.c qapi-visit.h :\
-$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
+$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py $(gen-out-type) -o "."  < $<, "  GEN   $@")
 qmp-commands.h qmp-marshal.c :\
-$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
+$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py $(gen-out-type) -m -o "." < $<, "  GEN   $@")
 
-QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
-$(qga-obj-y) qemu-ga.o: $(QGALIB_GEN)
+QGALIB_OBJ=$(addprefix $(qapi-dir)/, qga-qapi-types.o qga-qapi-visit.o qga-qmp-marshal.o)
+QGALIB_GEN=$(addprefix $(qapi-dir)/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
+$(QGALIB_OBJ): $(QGALIB_GEN) $(GENERATED_HEADERS)
+$(qga-obj-y) qemu-ga.o: $(QGALIB_GEN) $(GENERATED_HEADERS)
 
-qemu-ga$(EXESUF): qemu-ga.o $(qga-obj-y) $(oslib-obj-y) $(trace-obj-y) $(qapi-obj-y) $(qobject-obj-y) $(version-obj-y) libqemustub.a
+qemu-ga$(EXESUF): qemu-ga.o $(qga-obj-y) $(tools-obj-y) $(qapi-obj-y) $(qobject-obj-y) $(version-obj-y) $(QGALIB_OBJ)
 
-QEMULIBS=libuser libdis libdis-user
+QEMULIBS=libhw32 libhw64 libuser libdis libdis-user
 
 clean:
 # avoid old build problems by removing potentially incorrect old files
 	rm -f config.mak op-i386.h opc-i386.h gen-op-i386.h op-arm.h opc-arm.h gen-op-arm.h
 	rm -f qemu-options.def
-	find . -name '*.[od]' -exec rm -f {} +
-	rm -f *.a *.lo $(TOOLS) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
+	rm -f *.o *.d *.a *.lo $(TOOLS) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
 	rm -Rf .libs
+	rm -f slirp/*.o slirp/*.d audio/*.o audio/*.d block/*.o block/*.d net/*.o net/*.d fsdev/*.o fsdev/*.d ui/*.o ui/*.d qapi/*.o qapi/*.d qga/*.o qga/*.d
+	rm -f qom/*.o qom/*.d
 	rm -f qemu-img-cmds.h
+	rm -f trace/*.o trace/*.d
 	rm -f trace-dtrace.dtrace trace-dtrace.dtrace-timestamp
 	@# May not be present in GENERATED_HEADERS
 	rm -f trace-dtrace.h trace-dtrace.h-timestamp
 	rm -f $(foreach f,$(GENERATED_HEADERS),$(f) $(f)-timestamp)
 	rm -f $(foreach f,$(GENERATED_SOURCES),$(f) $(f)-timestamp)
-	rm -rf qapi-generated
-	rm -rf qga/qapi-generated
+	rm -rf $(qapi-dir)
 	$(MAKE) -C tests/tcg clean
 	for d in $(ALL_SUBDIRS) $(QEMULIBS) libcacard; do \
 	if test -d $$d; then $(MAKE) -C $$d $@ || exit 1; fi; \
 	rm -f $$d/qemu-options.def; \
         done
 
-VERSION ?= $(shell cat VERSION)
-
-dist: qemu-$(VERSION).tar.bz2
-
-qemu-%.tar.bz2:
-	$(SRC_PATH)/scripts/make-release "$(SRC_PATH)" "$(patsubst qemu-%.tar.bz2,%,$@)"
-
 distclean: clean
 	rm -f config-host.mak config-host.h* config-host.ld $(DOCS) qemu-options.texi qemu-img-cmds.texi qemu-monitor.texi
 	rm -f config-all-devices.mak
@@ -286,12 +246,10 @@ distclean: clean
 	for d in $(TARGET_DIRS) $(QEMULIBS); do \
 	rm -rf $$d || exit 1 ; \
         done
-	if test -f pixman/config.log; then make -C pixman distclean; fi
 
 KEYMAPS=da     en-gb  et  fr     fr-ch  is  lt  modifiers  no  pt-br  sv \
 ar      de     en-us  fi  fr-be  hr     it  lv  nl         pl  ru     th \
-common  de-ch  es     fo  fr-ca  hu     ja  mk  nl-be      pt  sl     tr \
-bepo
+common  de-ch  es     fo  fr-ca  hu     ja  mk  nl-be      pt  sl     tr
 
 ifdef INSTALL_BLOBS
 BLOBS=bios.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
@@ -301,6 +259,7 @@ pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
 pxe-pcnet.rom pxe-rtl8139.rom pxe-virtio.rom \
 qemu-icon.bmp \
 bamboo.dtb petalogix-s3adsp1800.dtb petalogix-ml605.dtb \
+mpc8544ds.dtb \
 multiboot.bin linuxboot.bin kvmvapic.bin \
 s390-zipl.rom \
 spapr-rtas.bin slof.bin \
@@ -332,6 +291,7 @@ 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)"
@@ -430,12 +390,15 @@ qemu-doc.dvi qemu-doc.html qemu-doc.info qemu-doc.pdf: \
 	qemu-img.texi qemu-nbd.texi qemu-options.texi \
 	qemu-monitor.texi qemu-img-cmds.texi
 
-# Add a dependency on the generated files, so that they are always
-# rebuilt before other object files
-ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
-Makefile: $(GENERATED_HEADERS)
-endif
+VERSION ?= $(shell cat VERSION)
+FILE = qemu-$(VERSION)
+
+# tar release (use 'make -k tar' on a checkouted tree)
+tar:
+	rm -rf /tmp/$(FILE)
+	cp -r . /tmp/$(FILE)
+	cd /tmp && tar zcvf ~/$(FILE).tar.gz $(FILE) --exclude CVS --exclude .git --exclude .svn
+	rm -rf /tmp/$(FILE)
 
 # Include automatically generated dependency files
-# Dependencies in Makefile.objs files come from our recursive subdir rules
--include $(wildcard *.d tests/*.d)
+-include $(wildcard *.d audio/*.d slirp/*.d block/*.d net/*.d ui/*.d qapi/*.d qga/*.d)

Makefile.dis

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

Makefile.hw

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

Makefile.objs

@@ -1,11 +1,6 @@
-#######################################################################
-# Stub library, linked in tools
-stub-obj-y = stubs/
-
 #######################################################################
 # Target-independent parts used in system and user emulation
 universal-obj-y =
-universal-obj-y += qemu-log.o
 
 #######################################################################
 # QObject
@@ -17,13 +12,15 @@ universal-obj-y += $(qobject-obj-y)
 
 #######################################################################
 # QOM
-qom-obj-y = qom/
+include $(SRC_PATH)/qom/Makefile
+qom-obj-y = $(addprefix qom/, $(qom-y))
+qom-obj-twice-y = $(addprefix qom/, $(qom-twice-y))
 
 universal-obj-y += $(qom-obj-y)
 
 #######################################################################
 # oslib-obj-y is code depending on the OS (win32 vs posix)
-oslib-obj-y = osdep.o cutils.o qemu-timer-common.o
+oslib-obj-y = osdep.o
 oslib-obj-$(CONFIG_WIN32) += oslib-win32.o qemu-thread-win32.o
 oslib-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-thread-posix.o
 
@@ -45,72 +42,155 @@ coroutine-obj-$(CONFIG_WIN32) += coroutine-win32.o
 #######################################################################
 # block-obj-y is code used by both qemu system emulation and qemu-img
 
-block-obj-y = iov.o cache-utils.o qemu-option.o module.o async.o
-block-obj-y += nbd.o block.o blockjob.o aes.o qemu-config.o
-block-obj-y += thread-pool.o qemu-progress.o qemu-sockets.o uri.o notify.o
+block-obj-y = cutils.o cache-utils.o qemu-option.o module.o async.o
+block-obj-y += nbd.o block.o aio.o aes.o qemu-config.o qemu-progress.o qemu-sockets.o
 block-obj-y += $(coroutine-obj-y) $(qobject-obj-y) $(version-obj-y)
-block-obj-$(CONFIG_POSIX) += event_notifier-posix.o aio-posix.o
-block-obj-$(CONFIG_WIN32) += event_notifier-win32.o aio-win32.o
-block-obj-y += block/
-block-obj-y += $(qapi-obj-y) qapi-types.o qapi-visit.o
+block-obj-$(CONFIG_POSIX) += posix-aio-compat.o
+block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
+
+block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
+block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
+block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
+block-nested-y += qed-check.o
+block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
+block-nested-y += stream.o
+block-nested-$(CONFIG_WIN32) += raw-win32.o
+block-nested-$(CONFIG_POSIX) += raw-posix.o
+block-nested-$(CONFIG_LIBISCSI) += iscsi.o
+block-nested-$(CONFIG_CURL) += curl.o
+block-nested-$(CONFIG_RBD) += rbd.o
+
+block-obj-y +=  $(addprefix block/, $(block-nested-y))
+
+net-obj-y = net.o
+net-nested-y = queue.o checksum.o util.o
+net-nested-y += socket.o
+net-nested-y += dump.o
+net-nested-$(CONFIG_POSIX) += tap.o
+net-nested-$(CONFIG_LINUX) += tap-linux.o
+net-nested-$(CONFIG_WIN32) += tap-win32.o
+net-nested-$(CONFIG_BSD) += tap-bsd.o
+net-nested-$(CONFIG_SOLARIS) += tap-solaris.o
+net-nested-$(CONFIG_AIX) += tap-aix.o
+net-nested-$(CONFIG_HAIKU) += tap-haiku.o
+net-nested-$(CONFIG_SLIRP) += slirp.o
+net-nested-$(CONFIG_VDE) += vde.o
+net-obj-y += $(addprefix net/, $(net-nested-y))
 
 ifeq ($(CONFIG_VIRTIO)$(CONFIG_VIRTFS)$(CONFIG_PCI),yyy)
 # Lots of the fsdev/9pcode is pulled in by vl.c via qemu_fsdev_add.
 # only pull in the actual virtio-9p device if we also enabled virtio.
 CONFIG_REALLY_VIRTFS=y
+fsdev-nested-y = qemu-fsdev.o virtio-9p-marshal.o
+else
+fsdev-nested-y = qemu-fsdev-dummy.o
 endif
+fsdev-obj-$(CONFIG_VIRTFS) += $(addprefix fsdev/, $(fsdev-nested-y))
 
 ######################################################################
 # Target independent part of system emulation. The long term path is to
 # suppress *all* target specific code in case of system emulation, i.e. a
 # single QEMU executable should support all CPUs and machines.
 
-common-obj-y = $(block-obj-y) blockdev.o blockdev-nbd.o block/
-common-obj-y += net.o net/
-common-obj-y += qom/
+common-obj-y = $(block-obj-y) blockdev.o
+common-obj-y += $(net-obj-y)
+common-obj-y += $(qom-obj-twice-y)
+common-obj-$(CONFIG_LINUX) += $(fsdev-obj-$(CONFIG_LINUX))
 common-obj-y += readline.o console.o cursor.o
-common-obj-y += qemu-pixman.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 += irq.o input.o
+common-obj-$(CONFIG_PTIMER) += ptimer.o
+common-obj-$(CONFIG_MAX7310) += max7310.o
+common-obj-$(CONFIG_WM8750) += wm8750.o
+common-obj-$(CONFIG_TWL92230) += twl92230.o
+common-obj-$(CONFIG_TSC2005) += tsc2005.o
+common-obj-$(CONFIG_LM832X) += lm832x.o
+common-obj-$(CONFIG_TMP105) += tmp105.o
+common-obj-$(CONFIG_STELLARIS_INPUT) += stellaris_input.o
+common-obj-$(CONFIG_SSD0303) += ssd0303.o
+common-obj-$(CONFIG_SSD0323) += ssd0323.o
+common-obj-$(CONFIG_ADS7846) += ads7846.o
+common-obj-$(CONFIG_MAX111X) += max111x.o
+common-obj-$(CONFIG_DS1338) += ds1338.o
+common-obj-y += i2c.o smbus.o smbus_eeprom.o
+common-obj-y += eeprom93xx.o
+common-obj-y += scsi-disk.o cdrom.o
+common-obj-y += scsi-generic.o scsi-bus.o
+common-obj-y += hid.o
+common-obj-y += usb/core.o usb/bus.o usb/desc.o usb/dev-hub.o
+common-obj-y += usb/host-$(HOST_USB).o
+common-obj-y += usb/dev-hid.o usb/dev-storage.o usb/dev-wacom.o
+common-obj-y += usb/dev-serial.o usb/dev-network.o usb/dev-audio.o
+common-obj-$(CONFIG_SSI) += ssi.o
+common-obj-$(CONFIG_SSI_SD) += ssi-sd.o
+common-obj-$(CONFIG_SD) += sd.o
+common-obj-y += bt.o bt-host.o bt-vhci.o bt-l2cap.o bt-sdp.o bt-hci.o bt-hid.o
+common-obj-y += bt-hci-csr.o usb/dev-bluetooth.o
 common-obj-y += buffered_file.o migration.o migration-tcp.o
 common-obj-y += qemu-char.o #aio.o
+common-obj-y += msmouse.o ps2.o
+common-obj-y += qdev.o qdev-properties.o qdev-monitor.o
 common-obj-y += block-migration.o iohandler.o
+common-obj-y += pflib.o
 common-obj-y += bitmap.o bitops.o
-common-obj-y += page_cache.o
 
+common-obj-$(CONFIG_BRLAPI) += baum.o
 common-obj-$(CONFIG_POSIX) += migration-exec.o migration-unix.o migration-fd.o
 common-obj-$(CONFIG_WIN32) += version.o
 
-common-obj-$(CONFIG_SPICE) += spice-qemu-char.o
+common-obj-$(CONFIG_SPICE) += ui/spice-core.o ui/spice-input.o ui/spice-display.o spice-qemu-char.o
 
-common-obj-y += audio/
-common-obj-y += hw/
-common-obj-y += ui/
-common-obj-y += bt-host.o bt-vhci.o
+audio-obj-y = audio.o noaudio.o wavaudio.o mixeng.o
+audio-obj-$(CONFIG_SDL) += sdlaudio.o
+audio-obj-$(CONFIG_OSS) += ossaudio.o
+audio-obj-$(CONFIG_SPICE) += spiceaudio.o
+audio-obj-$(CONFIG_COREAUDIO) += coreaudio.o
+audio-obj-$(CONFIG_ALSA) += alsaaudio.o
+audio-obj-$(CONFIG_DSOUND) += dsoundaudio.o
+audio-obj-$(CONFIG_FMOD) += fmodaudio.o
+audio-obj-$(CONFIG_ESD) += esdaudio.o
+audio-obj-$(CONFIG_PA) += paaudio.o
+audio-obj-$(CONFIG_WINWAVE) += winwaveaudio.o
+audio-obj-$(CONFIG_AUDIO_PT_INT) += audio_pt_int.o
+audio-obj-$(CONFIG_AUDIO_WIN_INT) += audio_win_int.o
+audio-obj-y += wavcapture.o
+common-obj-y += $(addprefix audio/, $(audio-obj-y))
 
-common-obj-y += dma-helpers.o
-common-obj-y += acl.o
-common-obj-$(CONFIG_POSIX) += compatfd.o
-common-obj-y += qemu-timer.o qemu-timer-common.o
-common-obj-y += qtest.o
-common-obj-y += vl.o
-
-common-obj-$(CONFIG_SLIRP) += slirp/
-
-common-obj-y += backends/
-
-######################################################################
-# libseccomp
-ifeq ($(CONFIG_SECCOMP),y)
-common-obj-y += qemu-seccomp.o
+ui-obj-y += keymaps.o
+ui-obj-$(CONFIG_SDL) += sdl.o sdl_zoom.o x_keymap.o
+ui-obj-$(CONFIG_COCOA) += cocoa.o
+ui-obj-$(CONFIG_CURSES) += curses.o
+vnc-obj-y += vnc.o d3des.o
+vnc-obj-y += vnc-enc-zlib.o vnc-enc-hextile.o
+vnc-obj-y += vnc-enc-tight.o vnc-palette.o
+vnc-obj-y += vnc-enc-zrle.o
+vnc-obj-$(CONFIG_VNC_TLS) += vnc-tls.o vnc-auth-vencrypt.o
+vnc-obj-$(CONFIG_VNC_SASL) += vnc-auth-sasl.o
+ifdef CONFIG_VNC_THREAD
+vnc-obj-y += vnc-jobs-async.o
+else
+vnc-obj-y += vnc-jobs-sync.o
 endif
+common-obj-y += $(addprefix ui/, $(ui-obj-y))
+common-obj-$(CONFIG_VNC) += $(addprefix ui/, $(vnc-obj-y))
+
+common-obj-y += iov.o acl.o
+common-obj-$(CONFIG_POSIX) += compatfd.o
+common-obj-y += notify.o event_notifier.o
+common-obj-y += qemu-timer.o qemu-timer-common.o
+
+slirp-obj-y = cksum.o if.o ip_icmp.o ip_input.o ip_output.o
+slirp-obj-y += slirp.o mbuf.o misc.o sbuf.o socket.o tcp_input.o tcp_output.o
+slirp-obj-y += tcp_subr.o tcp_timer.o udp.o bootp.o tftp.o arp_table.o
+common-obj-$(CONFIG_SLIRP) += $(addprefix slirp/, $(slirp-obj-y))
+
+# xen backend driver support
+common-obj-$(CONFIG_XEN_BACKEND) += xen_backend.o xen_devconfig.o
+common-obj-$(CONFIG_XEN_BACKEND) += xen_console.o xenfb.o xen_disk.o xen_nic.o
 
 ######################################################################
 # libuser
@@ -118,11 +198,156 @@ endif
 user-obj-y =
 user-obj-y += envlist.o path.o
 user-obj-y += tcg-runtime.o host-utils.o
-user-obj-y += cache-utils.o
+user-obj-y += cutils.o cache-utils.o
 user-obj-y += module.o
 user-obj-y += qemu-user.o
 user-obj-y += $(trace-obj-y)
-user-obj-y += qom/
+user-obj-y += $(qom-obj-twice-y)
+
+######################################################################
+# libhw
+
+hw-obj-y =
+hw-obj-y += vl.o loader.o
+hw-obj-$(CONFIG_VIRTIO) += virtio-console.o
+hw-obj-y += usb/libhw.o
+hw-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o
+hw-obj-y += fw_cfg.o
+hw-obj-$(CONFIG_PCI) += pci.o pci_bridge.o pci_bridge_dev.o
+hw-obj-$(CONFIG_PCI) += msix.o msi.o
+hw-obj-$(CONFIG_PCI) += shpc.o
+hw-obj-$(CONFIG_PCI) += slotid_cap.o
+hw-obj-$(CONFIG_PCI) += pci_host.o pcie_host.o
+hw-obj-$(CONFIG_PCI) += ioh3420.o xio3130_upstream.o xio3130_downstream.o
+hw-obj-y += watchdog.o
+hw-obj-$(CONFIG_ISA_MMIO) += isa_mmio.o
+hw-obj-$(CONFIG_ECC) += ecc.o
+hw-obj-$(CONFIG_NAND) += nand.o
+hw-obj-$(CONFIG_PFLASH_CFI01) += pflash_cfi01.o
+hw-obj-$(CONFIG_PFLASH_CFI02) += pflash_cfi02.o
+
+hw-obj-$(CONFIG_M48T59) += m48t59.o
+hw-obj-$(CONFIG_ESCC) += escc.o
+hw-obj-$(CONFIG_EMPTY_SLOT) += empty_slot.o
+
+hw-obj-$(CONFIG_SERIAL) += serial.o
+hw-obj-$(CONFIG_PARALLEL) += parallel.o
+hw-obj-$(CONFIG_I8254) += i8254_common.o i8254.o
+hw-obj-$(CONFIG_PCSPK) += pcspk.o
+hw-obj-$(CONFIG_PCKBD) += pckbd.o
+hw-obj-$(CONFIG_USB_UHCI) += usb/hcd-uhci.o
+hw-obj-$(CONFIG_USB_OHCI) += usb/hcd-ohci.o
+hw-obj-$(CONFIG_USB_EHCI) += usb/hcd-ehci.o
+hw-obj-$(CONFIG_USB_XHCI) += usb/hcd-xhci.o
+hw-obj-$(CONFIG_FDC) += fdc.o
+hw-obj-$(CONFIG_ACPI) += acpi.o acpi_piix4.o
+hw-obj-$(CONFIG_APM) += pm_smbus.o apm.o
+hw-obj-$(CONFIG_DMA) += dma.o
+hw-obj-$(CONFIG_I82374) += i82374.o
+hw-obj-$(CONFIG_HPET) += hpet.o
+hw-obj-$(CONFIG_APPLESMC) += applesmc.o
+hw-obj-$(CONFIG_SMARTCARD) += usb/dev-smartcard-reader.o ccid-card-passthru.o
+hw-obj-$(CONFIG_SMARTCARD_NSS) += ccid-card-emulated.o
+hw-obj-$(CONFIG_USB_REDIR) += usb/redirect.o
+hw-obj-$(CONFIG_I8259) += i8259_common.o i8259.o
+
+# PPC devices
+hw-obj-$(CONFIG_PREP_PCI) += prep_pci.o
+hw-obj-$(CONFIG_I82378) += i82378.o
+# Mac shared devices
+hw-obj-$(CONFIG_MACIO) += macio.o
+hw-obj-$(CONFIG_CUDA) += cuda.o
+hw-obj-$(CONFIG_ADB) += adb.o
+hw-obj-$(CONFIG_MAC_NVRAM) += mac_nvram.o
+hw-obj-$(CONFIG_MAC_DBDMA) += mac_dbdma.o
+# OldWorld PowerMac
+hw-obj-$(CONFIG_HEATHROW_PIC) += heathrow_pic.o
+hw-obj-$(CONFIG_GRACKLE_PCI) += grackle_pci.o
+# NewWorld PowerMac
+hw-obj-$(CONFIG_UNIN_PCI) += unin_pci.o
+hw-obj-$(CONFIG_DEC_PCI) += dec_pci.o
+# PowerPC E500 boards
+hw-obj-$(CONFIG_PPCE500_PCI) += ppce500_pci.o
+
+# MIPS devices
+hw-obj-$(CONFIG_PIIX4) += piix4.o
+hw-obj-$(CONFIG_G364FB) += g364fb.o
+hw-obj-$(CONFIG_JAZZ_LED) += jazz_led.o
+
+# PCI watchdog devices
+hw-obj-$(CONFIG_PCI) += wdt_i6300esb.o
+
+hw-obj-$(CONFIG_PCI) += pcie.o pcie_aer.o pcie_port.o
+
+# PCI network cards
+hw-obj-$(CONFIG_NE2000_PCI) += ne2000.o
+hw-obj-$(CONFIG_EEPRO100_PCI) += eepro100.o
+hw-obj-$(CONFIG_PCNET_PCI) += pcnet-pci.o
+hw-obj-$(CONFIG_PCNET_COMMON) += pcnet.o
+hw-obj-$(CONFIG_E1000_PCI) += e1000.o
+hw-obj-$(CONFIG_RTL8139_PCI) += rtl8139.o
+
+hw-obj-$(CONFIG_SMC91C111) += smc91c111.o
+hw-obj-$(CONFIG_LAN9118) += lan9118.o
+hw-obj-$(CONFIG_NE2000_ISA) += ne2000-isa.o
+hw-obj-$(CONFIG_OPENCORES_ETH) += opencores_eth.o
+
+# IDE
+hw-obj-$(CONFIG_IDE_CORE) += ide/core.o ide/atapi.o
+hw-obj-$(CONFIG_IDE_QDEV) += ide/qdev.o
+hw-obj-$(CONFIG_IDE_PCI) += ide/pci.o
+hw-obj-$(CONFIG_IDE_ISA) += ide/isa.o
+hw-obj-$(CONFIG_IDE_PIIX) += ide/piix.o
+hw-obj-$(CONFIG_IDE_CMD646) += ide/cmd646.o
+hw-obj-$(CONFIG_IDE_MACIO) += ide/macio.o
+hw-obj-$(CONFIG_IDE_VIA) += ide/via.o
+hw-obj-$(CONFIG_AHCI) += ide/ahci.o
+hw-obj-$(CONFIG_AHCI) += ide/ich.o
+
+# SCSI layer
+hw-obj-$(CONFIG_LSI_SCSI_PCI) += lsi53c895a.o
+hw-obj-$(CONFIG_ESP) += esp.o
+
+hw-obj-y += dma-helpers.o sysbus.o isa-bus.o
+hw-obj-y += qdev-addr.o
+
+# VGA
+hw-obj-$(CONFIG_VGA_PCI) += vga-pci.o
+hw-obj-$(CONFIG_VGA_ISA) += vga-isa.o
+hw-obj-$(CONFIG_VGA_ISA_MM) += vga-isa-mm.o
+hw-obj-$(CONFIG_VMWARE_VGA) += vmware_vga.o
+hw-obj-$(CONFIG_VMMOUSE) += vmmouse.o
+hw-obj-$(CONFIG_VGA_CIRRUS) += cirrus_vga.o
+
+hw-obj-$(CONFIG_RC4030) += rc4030.o
+hw-obj-$(CONFIG_DP8393X) += dp8393x.o
+hw-obj-$(CONFIG_DS1225Y) += ds1225y.o
+hw-obj-$(CONFIG_MIPSNET) += mipsnet.o
+
+hw-obj-y += qtest.o
+
+# Sound
+sound-obj-y =
+sound-obj-$(CONFIG_SB16) += sb16.o
+sound-obj-$(CONFIG_ES1370) += es1370.o
+sound-obj-$(CONFIG_AC97) += ac97.o
+sound-obj-$(CONFIG_ADLIB) += fmopl.o adlib.o
+sound-obj-$(CONFIG_GUS) += gus.o gusemu_hal.o gusemu_mixer.o
+sound-obj-$(CONFIG_CS4231A) += cs4231a.o
+sound-obj-$(CONFIG_HDA) += intel-hda.o hda-audio.o
+
+adlib.o fmopl.o: QEMU_CFLAGS += -DBUILD_Y8950=0
+hw-obj-$(CONFIG_SOUND) += $(sound-obj-y)
+
+9pfs-nested-$(CONFIG_VIRTFS)  = virtio-9p.o
+9pfs-nested-$(CONFIG_VIRTFS) += virtio-9p-local.o virtio-9p-xattr.o
+9pfs-nested-$(CONFIG_VIRTFS) += virtio-9p-xattr-user.o virtio-9p-posix-acl.o
+9pfs-nested-$(CONFIG_VIRTFS) += virtio-9p-coth.o cofs.o codir.o cofile.o
+9pfs-nested-$(CONFIG_VIRTFS) += coxattr.o virtio-9p-synth.o
+9pfs-nested-$(CONFIG_OPEN_BY_HANDLE) +=  virtio-9p-handle.o
+9pfs-nested-$(CONFIG_VIRTFS) += virtio-9p-proxy.o
+
+hw-obj-$(CONFIG_REALLY_VIRTFS) += $(addprefix 9pfs/, $(9pfs-nested-y))
 
 ######################################################################
 # libdis
@@ -200,30 +425,31 @@ 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-nested-$(CONFIG_TRACE_DEFAULT) += default.o
+
+trace-nested-$(CONFIG_TRACE_SIMPLE) += 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-nested-$(CONFIG_TRACE_STDERR) += stderr.o
+
+trace-nested-y += control.o
+
+trace-obj-y += $(addprefix trace/, $(trace-nested-y))
 
 $(trace-obj-y): $(GENERATED_HEADERS)
 
 ######################################################################
 # smartcard
 
-libcacard-y += libcacard/cac.o libcacard/event.o
-libcacard-y += libcacard/vcard.o libcacard/vreader.o
-libcacard-y += libcacard/vcard_emul_nss.o
-libcacard-y += libcacard/vcard_emul_type.o
-libcacard-y += libcacard/card_7816.o
-
-common-obj-$(CONFIG_SMARTCARD_NSS) += $(libcacard-y)
+libcacard-y = cac.o event.o vcard.o vreader.o vcard_emul_nss.o vcard_emul_type.o card_7816.o
 
 ######################################################################
 # qapi
 
-qapi-obj-y = qapi/
-qapi-obj-y += qapi-types.o qapi-visit.o
+qapi-nested-y = qapi-visit-core.o qapi-dealloc-visitor.o qmp-input-visitor.o
+qapi-nested-y += qmp-output-visitor.o qmp-registry.o qmp-dispatch.o
+qapi-nested-y += string-input-visitor.o string-output-visitor.o
+qapi-obj-y = $(addprefix qapi/, $(qapi-nested-y))
 
 common-obj-y += qmp-marshal.o qapi-visit.o qapi-types.o
 common-obj-y += qmp.o hmp.o
@@ -233,8 +459,13 @@ universal-obj-y += $(qapi-obj-y)
 ######################################################################
 # guest agent
 
-qga-obj-y = qga/ qemu-ga.o module.o qemu-tool.o
-qga-obj-$(CONFIG_POSIX) += qemu-sockets.o qemu-option.o
+qga-nested-y = commands.o guest-agent-command-state.o
+qga-nested-$(CONFIG_POSIX) += commands-posix.o channel-posix.o
+qga-nested-$(CONFIG_WIN32) += commands-win32.o channel-win32.o service-win32.o
+qga-obj-y = $(addprefix qga/, $(qga-nested-y))
+qga-obj-y += qemu-ga.o module.o
+qga-obj-$(CONFIG_WIN32) += oslib-win32.o
+qga-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-sockets.o qemu-option.o
 
 vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
 
@@ -242,13 +473,3 @@ vl.o: QEMU_CFLAGS+=$(SDL_CFLAGS)
 
 QEMU_CFLAGS+=$(GLIB_CFLAGS)
 
-nested-vars += \
-	stub-obj-y \
-	qga-obj-y \
-	qom-obj-y \
-	qapi-obj-y \
-	block-obj-y \
-	user-obj-y \
-	common-obj-y \
-	extra-obj-y
-dummy := $(call unnest-vars)

Makefile.target

@@ -1,15 +1,26 @@
 # -*- Mode: makefile -*-
 
+GENERATED_HEADERS = config-target.h
+CONFIG_NO_PCI = $(if $(subst n,,$(CONFIG_PCI)),n,y)
+CONFIG_NO_KVM = $(if $(subst n,,$(CONFIG_KVM)),n,y)
+CONFIG_NO_XEN = $(if $(subst n,,$(CONFIG_XEN)),n,y)
+
 include ../config-host.mak
 include config-devices.mak
 include config-target.mak
 include $(SRC_PATH)/rules.mak
+ifneq ($(HWDIR),)
+include $(HWDIR)/config.mak
+endif
 
-$(call set-vpath, $(SRC_PATH))
+TARGET_PATH=$(SRC_PATH)/target-$(TARGET_BASE_ARCH)
+$(call set-vpath, $(SRC_PATH):$(TARGET_PATH):$(SRC_PATH)/hw)
 ifdef CONFIG_LINUX
 QEMU_CFLAGS += -I../linux-headers
 endif
-QEMU_CFLAGS += -I.. -I$(SRC_PATH)/target-$(TARGET_BASE_ARCH) -DNEED_CPU_H
+QEMU_CFLAGS += -I.. -I$(TARGET_PATH) -DNEED_CPU_H
+
+include $(SRC_PATH)/Makefile.objs
 
 QEMU_CFLAGS+=-I$(SRC_PATH)/include
 
@@ -66,26 +77,78 @@ all: $(PROGS) stap
 
 #########################################################
 # cpu emulator library
-obj-y = exec.o translate-all.o cpu-exec.o
-obj-y += tcg/tcg.o tcg/optimize.o
-obj-$(CONFIG_TCG_INTERPRETER) += tci.o
-obj-y += fpu/softfloat.o
-obj-y += disas.o
-obj-$(CONFIG_TCI_DIS) += tci-dis.o
-obj-y += target-$(TARGET_BASE_ARCH)/
-obj-$(CONFIG_GDBSTUB_XML) += gdbstub-xml.o
+libobj-y = exec.o translate-all.o cpu-exec.o translate.o
+libobj-y += tcg/tcg.o tcg/optimize.o
+libobj-$(CONFIG_TCG_INTERPRETER) += tci.o
+libobj-y += fpu/softfloat.o
+ifneq ($(TARGET_BASE_ARCH), sparc)
+ifneq ($(TARGET_BASE_ARCH), alpha)
+libobj-y += op_helper.o
+endif
+endif
+libobj-y += helper.o
+ifneq ($(TARGET_BASE_ARCH), ppc)
+libobj-y += cpu.o
+endif
+libobj-$(TARGET_SPARC64) += vis_helper.o
+libobj-$(CONFIG_NEED_MMU) += mmu.o
+libobj-$(TARGET_ARM) += neon_helper.o iwmmxt_helper.o
+ifeq ($(TARGET_BASE_ARCH), sparc)
+libobj-y += fop_helper.o cc_helper.o win_helper.o mmu_helper.o ldst_helper.o
+endif
+libobj-$(TARGET_SPARC) += int32_helper.o
+libobj-$(TARGET_SPARC64) += int64_helper.o
+libobj-$(TARGET_ALPHA) += int_helper.o fpu_helper.o sys_helper.o mem_helper.o
+
+libobj-y += disas.o
+libobj-$(CONFIG_TCI_DIS) += tci-dis.o
 
 tci-dis.o: QEMU_CFLAGS += -I$(SRC_PATH)/tcg -I$(SRC_PATH)/tcg/tci
 
+$(libobj-y): $(GENERATED_HEADERS)
+
+# HELPER_CFLAGS is used for all the legacy code compiled with static register
+# variables
+ifneq ($(TARGET_BASE_ARCH), sparc)
+op_helper.o: QEMU_CFLAGS += $(HELPER_CFLAGS)
+endif
+user-exec.o: QEMU_CFLAGS += $(HELPER_CFLAGS)
+
+# Note: this is a workaround. The real fix is to avoid compiling
+# cpu_signal_handler() in user-exec.c.
+signal.o: QEMU_CFLAGS += $(HELPER_CFLAGS)
+
 #########################################################
 # Linux user emulator target
 
 ifdef CONFIG_LINUX_USER
 
-QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) -I$(SRC_PATH)/linux-user
+$(call set-vpath, $(SRC_PATH)/linux-user:$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR))
 
-obj-y += linux-user/
-obj-y += gdbstub.o thunk.o user-exec.o $(oslib-obj-y)
+QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) -I$(SRC_PATH)/linux-user
+obj-y = main.o syscall.o strace.o mmap.o signal.o thunk.o \
+      elfload.o linuxload.o uaccess.o gdbstub.o cpu-uname.o \
+      user-exec.o $(oslib-obj-y)
+
+obj-$(TARGET_HAS_BFLT) += flatload.o
+
+obj-$(TARGET_I386) += vm86.o
+
+obj-i386-y += ioport-user.o
+
+nwfpe-obj-y = fpa11.o fpa11_cpdo.o fpa11_cpdt.o fpa11_cprt.o fpopcode.o
+nwfpe-obj-y += single_cpdo.o double_cpdo.o extended_cpdo.o
+obj-arm-y +=  $(addprefix nwfpe/, $(nwfpe-obj-y))
+obj-arm-y += arm-semi.o
+
+obj-m68k-y += m68k-sim.o m68k-semi.o
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../, $(universal-obj-y))
+obj-y += $(addprefix ../libuser/, $(user-obj-y))
+obj-y += $(addprefix ../libdis-user/, $(libdis-y))
+obj-y += $(libobj-y)
 
 endif #CONFIG_LINUX_USER
 
@@ -94,83 +157,269 @@ endif #CONFIG_LINUX_USER
 
 ifdef CONFIG_BSD_USER
 
+$(call set-vpath, $(SRC_PATH)/bsd-user)
+
 QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ARCH)
 
-obj-y += bsd-user/
-obj-y += gdbstub.o user-exec.o $(oslib-obj-y)
+obj-y = main.o bsdload.o elfload.o mmap.o signal.o strace.o syscall.o \
+        gdbstub.o uaccess.o user-exec.o
+
+obj-i386-y += ioport-user.o
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../, $(universal-obj-y))
+obj-y += $(addprefix ../libuser/, $(user-obj-y))
+obj-y += $(addprefix ../libdis-user/, $(libdis-y))
+obj-y += $(libobj-y)
 
 endif #CONFIG_BSD_USER
 
 #########################################################
 # System emulator target
 ifdef CONFIG_SOFTMMU
-CONFIG_NO_PCI = $(if $(subst n,,$(CONFIG_PCI)),n,y)
-CONFIG_NO_KVM = $(if $(subst n,,$(CONFIG_KVM)),n,y)
-CONFIG_NO_XEN = $(if $(subst n,,$(CONFIG_XEN)),n,y)
-CONFIG_NO_GET_MEMORY_MAPPING = $(if $(subst n,,$(CONFIG_HAVE_GET_MEMORY_MAPPING)),n,y)
-CONFIG_NO_CORE_DUMP = $(if $(subst n,,$(CONFIG_HAVE_CORE_DUMP)),n,y)
 
-obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o
-obj-y += hw/
-obj-$(CONFIG_KVM) += kvm-all.o
+obj-y = arch_init.o cpus.o monitor.o machine.o gdbstub.o balloon.o ioport.o
+# virtio has to be here due to weird dependency between PCI and virtio-net.
+# need to fix this properly
+obj-$(CONFIG_NO_PCI) += pci-stub.o
+obj-$(CONFIG_VIRTIO) += virtio.o virtio-blk.o virtio-balloon.o virtio-net.o virtio-serial-bus.o
+obj-$(CONFIG_VIRTIO) += virtio-scsi.o
+obj-y += vhost_net.o
+obj-$(CONFIG_VHOST_NET) += vhost.o
+obj-$(CONFIG_REALLY_VIRTFS) += 9pfs/virtio-9p-device.o
+obj-$(CONFIG_KVM) += kvm.o kvm-all.o
 obj-$(CONFIG_NO_KVM) += kvm-stub.o
+obj-$(CONFIG_VGA) += vga.o
 obj-y += memory.o savevm.o cputlb.o
-obj-$(CONFIG_HAVE_GET_MEMORY_MAPPING) += memory_mapping.o
-obj-$(CONFIG_HAVE_CORE_DUMP) += dump.o
-obj-$(CONFIG_NO_GET_MEMORY_MAPPING) += memory_mapping-stub.o
-obj-$(CONFIG_NO_CORE_DUMP) += dump-stub.o
 LIBS+=-lz
 
+obj-i386-$(CONFIG_KVM) += hyperv.o
+
 QEMU_CFLAGS += $(VNC_TLS_CFLAGS)
 QEMU_CFLAGS += $(VNC_SASL_CFLAGS)
 QEMU_CFLAGS += $(VNC_JPEG_CFLAGS)
 QEMU_CFLAGS += $(VNC_PNG_CFLAGS)
 
 # xen support
-obj-$(CONFIG_XEN) += xen-all.o xen-mapcache.o
+obj-$(CONFIG_XEN) += xen-all.o xen_machine_pv.o xen_domainbuild.o xen-mapcache.o
 obj-$(CONFIG_NO_XEN) += xen-stub.o
 
-# Hardware support
-ifeq ($(TARGET_ARCH), sparc64)
-obj-y += hw/sparc64/
-else
-obj-y += hw/$(TARGET_BASE_ARCH)/
+obj-i386-$(CONFIG_XEN) += xen_platform.o xen_apic.o
+
+# Inter-VM PCI shared memory
+CONFIG_IVSHMEM =
+ifeq ($(CONFIG_KVM), y)
+  ifeq ($(CONFIG_PCI), y)
+    CONFIG_IVSHMEM = y
+  endif
 endif
+obj-$(CONFIG_IVSHMEM) += ivshmem.o
+
+# Generic hotplugging
+obj-y += device-hotplug.o
+
+# Hardware support
+obj-i386-y += mc146818rtc.o pc.o
+obj-i386-y += apic_common.o apic.o kvmvapic.o
+obj-i386-y += sga.o ioapic_common.o ioapic.o piix_pci.o
+obj-i386-y += vmport.o
+obj-i386-y += pci-hotplug.o smbios.o wdt_ib700.o
+obj-i386-y += debugcon.o multiboot.o
+obj-i386-y += pc_piix.o
+obj-i386-y += pc_sysfw.o
+obj-i386-$(CONFIG_KVM) += kvm/clock.o kvm/apic.o kvm/i8259.o kvm/ioapic.o kvm/i8254.o
+obj-i386-$(CONFIG_SPICE) += qxl.o qxl-logger.o qxl-render.o
+
+# shared objects
+obj-ppc-y = ppc.o ppc_booke.o
+# PREP target
+obj-ppc-y += mc146818rtc.o
+obj-ppc-y += ppc_prep.o
+# OldWorld PowerMac
+obj-ppc-y += ppc_oldworld.o
+# NewWorld PowerMac
+obj-ppc-y += ppc_newworld.o
+# IBM pSeries (sPAPR)
+obj-ppc-$(CONFIG_PSERIES) += spapr.o spapr_hcall.o spapr_rtas.o spapr_vio.o
+obj-ppc-$(CONFIG_PSERIES) += xics.o spapr_vty.o spapr_llan.o spapr_vscsi.o
+obj-ppc-$(CONFIG_PSERIES) += spapr_pci.o device-hotplug.o pci-hotplug.o
+# PowerPC 4xx boards
+obj-ppc-y += ppc4xx_devs.o ppc4xx_pci.o ppc405_uc.o ppc405_boards.o
+obj-ppc-y += ppc440_bamboo.o
+# PowerPC E500 boards
+obj-ppc-y += ppce500_mpc8544ds.o mpc8544_guts.o ppce500_spin.o
+# PowerPC 440 Xilinx ML507 reference board.
+obj-ppc-y += virtex_ml507.o
+obj-ppc-$(CONFIG_KVM) += kvm_ppc.o
+obj-ppc-$(CONFIG_FDT) += device_tree.o
+# PowerPC OpenPIC
+obj-ppc-y += openpic.o
+
+# Xilinx PPC peripherals
+obj-ppc-y += xilinx_intc.o
+obj-ppc-y += xilinx_timer.o
+obj-ppc-y += xilinx_uartlite.o
+obj-ppc-y += xilinx_ethlite.o
+
+# LM32 boards
+obj-lm32-y += lm32_boards.o
+obj-lm32-y += milkymist.o
+
+# LM32 peripherals
+obj-lm32-y += lm32_pic.o
+obj-lm32-y += lm32_juart.o
+obj-lm32-y += lm32_timer.o
+obj-lm32-y += lm32_uart.o
+obj-lm32-y += lm32_sys.o
+obj-lm32-y += milkymist-ac97.o
+obj-lm32-y += milkymist-hpdmc.o
+obj-lm32-y += milkymist-memcard.o
+obj-lm32-y += milkymist-minimac2.o
+obj-lm32-y += milkymist-pfpu.o
+obj-lm32-y += milkymist-softusb.o
+obj-lm32-y += milkymist-sysctl.o
+obj-lm32-$(CONFIG_OPENGL) += milkymist-tmu2.o
+obj-lm32-y += milkymist-uart.o
+obj-lm32-y += milkymist-vgafb.o
+obj-lm32-y += framebuffer.o
+
+obj-mips-y = mips_r4k.o mips_jazz.o mips_malta.o mips_mipssim.o
+obj-mips-y += mips_addr.o mips_timer.o mips_int.o
+obj-mips-y += gt64xxx.o mc146818rtc.o
+obj-mips-$(CONFIG_FULONG) += bonito.o vt82c686.o mips_fulong2e.o
+
+obj-microblaze-y = petalogix_s3adsp1800_mmu.o
+obj-microblaze-y += petalogix_ml605_mmu.o
+obj-microblaze-y += microblaze_boot.o
+
+obj-microblaze-y += microblaze_pic_cpu.o
+obj-microblaze-y += xilinx_intc.o
+obj-microblaze-y += xilinx_timer.o
+obj-microblaze-y += xilinx_uartlite.o
+obj-microblaze-y += xilinx_ethlite.o
+obj-microblaze-y += xilinx_axidma.o
+obj-microblaze-y += xilinx_axienet.o
+
+obj-microblaze-$(CONFIG_FDT) += device_tree.o
+
+# Boards
+obj-cris-y = cris_pic_cpu.o
+obj-cris-y += cris-boot.o
+obj-cris-y += axis_dev88.o
+
+# IO blocks
+obj-cris-y += etraxfs_dma.o
+obj-cris-y += etraxfs_pic.o
+obj-cris-y += etraxfs_eth.o
+obj-cris-y += etraxfs_timer.o
+obj-cris-y += etraxfs_ser.o
+
+ifeq ($(TARGET_ARCH), sparc64)
+obj-sparc-y = sun4u.o apb_pci.o
+obj-sparc-y += mc146818rtc.o
+else
+obj-sparc-y = sun4m.o lance.o tcx.o sun4m_iommu.o slavio_intctl.o
+obj-sparc-y += slavio_timer.o slavio_misc.o sparc32_dma.o
+obj-sparc-y += cs4231.o eccmemctl.o sbi.o sun4c_intctl.o leon3.o
+
+# GRLIB
+obj-sparc-y += grlib_gptimer.o grlib_irqmp.o grlib_apbuart.o
+endif
+
+obj-arm-y = integratorcp.o versatilepb.o arm_pic.o arm_timer.o
+obj-arm-y += arm_boot.o pl011.o pl031.o pl050.o pl080.o pl110.o pl181.o pl190.o
+obj-arm-y += versatile_pci.o
+obj-arm-y += versatile_i2c.o
+obj-arm-y += cadence_uart.o
+obj-arm-y += cadence_ttc.o
+obj-arm-y += cadence_gem.o
+obj-arm-y += xilinx_zynq.o zynq_slcr.o
+obj-arm-y += arm_gic.o
+obj-arm-y += realview_gic.o realview.o arm_sysctl.o arm11mpcore.o a9mpcore.o
+obj-arm-y += exynos4210_gic.o exynos4210_combiner.o exynos4210.o
+obj-arm-y += exynos4_boards.o exynos4210_uart.o exynos4210_pwm.o
+obj-arm-y += exynos4210_pmu.o exynos4210_mct.o exynos4210_fimd.o
+obj-arm-y += arm_l2x0.o
+obj-arm-y += arm_mptimer.o a15mpcore.o
+obj-arm-y += armv7m.o armv7m_nvic.o stellaris.o pl022.o stellaris_enet.o
+obj-arm-y += highbank.o
+obj-arm-y += pl061.o
+obj-arm-y += xgmac.o
+obj-arm-y += arm-semi.o
+obj-arm-y += pxa2xx.o pxa2xx_pic.o pxa2xx_gpio.o pxa2xx_timer.o pxa2xx_dma.o
+obj-arm-y += pxa2xx_lcd.o pxa2xx_mmci.o pxa2xx_pcmcia.o pxa2xx_keypad.o
+obj-arm-y += gumstix.o
+obj-arm-y += zaurus.o ide/microdrive.o spitz.o tosa.o tc6393xb.o
+obj-arm-y += omap1.o omap_lcdc.o omap_dma.o omap_clk.o omap_mmc.o omap_i2c.o \
+		omap_gpio.o omap_intc.o omap_uart.o
+obj-arm-y += omap2.o omap_dss.o soc_dma.o omap_gptimer.o omap_synctimer.o \
+		omap_gpmc.o omap_sdrc.o omap_spi.o omap_tap.o omap_l4.o
+obj-arm-y += omap_sx1.o palm.o tsc210x.o
+obj-arm-y += nseries.o blizzard.o onenand.o cbus.o tusb6010.o usb/hcd-musb.o
+obj-arm-y += mst_fpga.o mainstone.o
+obj-arm-y += z2.o
+obj-arm-y += musicpal.o bitbang_i2c.o marvell_88w8618_audio.o
+obj-arm-y += framebuffer.o
+obj-arm-y += vexpress.o
+obj-arm-y += strongarm.o
+obj-arm-y += collie.o
+obj-arm-y += pl041.o lm4549.o
+obj-arm-$(CONFIG_FDT) += device_tree.o
+
+obj-sh4-y = shix.o r2d.o sh7750.o sh7750_regnames.o tc58128.o
+obj-sh4-y += sh_timer.o sh_serial.o sh_intc.o sh_pci.o sm501.o
+obj-sh4-y += ide/mmio.o
+
+obj-m68k-y = an5206.o mcf5206.o mcf_uart.o mcf_intc.o mcf5208.o mcf_fec.o
+obj-m68k-y += m68k-semi.o dummy_m68k.o
+
+obj-s390x-y = s390-virtio-bus.o s390-virtio.o
+
+obj-alpha-y = mc146818rtc.o
+obj-alpha-y += alpha_pci.o alpha_dp264.o alpha_typhoon.o
+
+obj-xtensa-y += xtensa_pic.o
+obj-xtensa-y += xtensa_sim.o
+obj-xtensa-y += xtensa_lx60.o
+obj-xtensa-y += xtensa-semi.o
+obj-xtensa-y += core-dc232b.o
+obj-xtensa-y += core-dc233c.o
+obj-xtensa-y += core-fsf.o
 
 main.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
 
-GENERATED_HEADERS += hmp-commands.h qmp-commands-old.h
+monitor.o: hmp-commands.h qmp-commands-old.h
+
+$(obj-y) $(obj-$(TARGET_BASE_ARCH)-y): $(GENERATED_HEADERS)
+
+obj-y += $(addprefix ../, $(universal-obj-y))
+obj-y += $(addprefix ../, $(common-obj-y))
+obj-y += $(addprefix ../libdis/, $(libdis-y))
+obj-y += $(libobj-y)
+obj-y += $(addprefix $(HWDIR)/, $(hw-obj-y))
+obj-y += $(addprefix ../, $(trace-obj-y))
 
 endif # CONFIG_SOFTMMU
 
-# Workaround for http://gcc.gnu.org/PR55489, see configure.
-%/translate.o: QEMU_CFLAGS += $(TRANSLATE_OPT_CFLAGS)
+ifndef CONFIG_LINUX_USER
+ifndef CONFIG_BSD_USER
+# libcacard needs qemu-thread support, and besides is only needed by devices
+# so not requires with linux-user / bsd-user targets
+obj-$(CONFIG_SMARTCARD_NSS) += $(addprefix ../libcacard/, $(libcacard-y))
+endif # CONFIG_BSD_USER
+endif # CONFIG_LINUX_USER
 
-nested-vars += obj-y
-
-# This resolves all nested paths, so it must come last
-include $(SRC_PATH)/Makefile.objs
-
-all-obj-y = $(obj-y)
-all-obj-y += $(addprefix ../, $(universal-obj-y))
-
-ifdef CONFIG_SOFTMMU
-all-obj-y += $(addprefix ../, $(common-obj-y))
-all-obj-y += $(addprefix ../libdis/, $(libdis-y))
-all-obj-y += $(addprefix ../, $(trace-obj-y))
-else
-all-obj-y += $(addprefix ../libuser/, $(user-obj-y))
-all-obj-y += $(addprefix ../libdis-user/, $(libdis-y))
-endif #CONFIG_LINUX_USER
+obj-$(CONFIG_GDBSTUB_XML) += gdbstub-xml.o
 
 ifdef QEMU_PROGW
 # The linker builds a windows executable. Make also a console executable.
-$(QEMU_PROGW): $(all-obj-y) ../libqemustub.a
+$(QEMU_PROGW): $(obj-y) $(obj-$(TARGET_BASE_ARCH)-y)
 	$(call LINK,$^)
 $(QEMU_PROG): $(QEMU_PROGW)
 	$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG),"  GEN   $(TARGET_DIR)$(QEMU_PROG)")
 else
-$(QEMU_PROG): $(all-obj-y) ../libqemustub.a
+$(QEMU_PROG): $(obj-y) $(obj-$(TARGET_BASE_ARCH)-y)
 	$(call LINK,$^)
 endif
 
@@ -184,8 +433,8 @@ qmp-commands-old.h: $(SRC_PATH)/qmp-commands.hx
 	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")
 
 clean:
-	rm -f *.a *~ $(PROGS)
-	rm -f $(shell find . -name '*.[od]')
+	rm -f *.o *.a *~ $(PROGS) nwfpe/*.o fpu/*.o
+	rm -f *.d */*.d tcg/*.o ide/*.o 9pfs/*.o kvm/*.o
 	rm -f hmp-commands.h qmp-commands-old.h gdbstub-xml.c
 ifdef CONFIG_TRACE_SYSTEMTAP
 	rm -f *.stp
@@ -203,5 +452,5 @@ ifdef CONFIG_TRACE_SYSTEMTAP
 	$(INSTALL_DATA) $(QEMU_PROG).stp "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset"
 endif
 
-GENERATED_HEADERS += config-target.h
-Makefile: $(GENERATED_HEADERS)
+# Include automatically generated dependency files
+-include $(wildcard *.d */*.d)

Makefile.user

@@ -10,7 +10,6 @@ $(call set-vpath, $(SRC_PATH))
 
 QEMU_CFLAGS+=-I..
 QEMU_CFLAGS += -I$(SRC_PATH)/include
-QEMU_CFLAGS += -DCONFIG_USER_ONLY
 
 include $(SRC_PATH)/Makefile.objs
 
@@ -22,3 +21,6 @@ clean:
 	for d in . trace; do \
 	rm -f $$d/*.o $$d/*.d $$d/*.a $$d/*~; \
 	done
+
+# Include automatically generated dependency files
+-include $(wildcard *.d */*.d)

QMP/qemu-ga-client

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

QMP/qmp-events.txt

@@ -1,23 +1,6 @@
                    QEMU Monitor Protocol Events
                    ============================
 
-BALLOON_CHANGE
---------------
-
-Emitted when the guest changes the actual BALLOON level. This
-value is equivalent to the 'actual' field return by the
-'query-balloon' command
-
-Data:
-
-- "actual": actual level of the guest memory balloon in bytes (json-number)
-
-Example:
-
-{ "event": "BALLOON_CHANGE",
-    "data": { "actual": 944766976 },
-    "timestamp": { "seconds": 1267020223, "microseconds": 435656 } }
-
 BLOCK_IO_ERROR
 --------------
 
@@ -43,99 +26,6 @@ Example:
 Note: If action is "stop", a STOP event will eventually follow the
 BLOCK_IO_ERROR event.
 
-BLOCK_JOB_CANCELLED
--------------------
-
-Emitted when a block job has been cancelled.
-
-Data:
-
-- "type":     Job type (json-string; "stream" for image streaming
-                                     "commit" for block commit)
-- "device":   Device name (json-string)
-- "len":      Maximum progress value (json-int)
-- "offset":   Current progress value (json-int)
-              On success this is equal to len.
-              On failure this is less than len.
-- "speed":    Rate limit, bytes per second (json-int)
-
-Example:
-
-{ "event": "BLOCK_JOB_CANCELLED",
-     "data": { "type": "stream", "device": "virtio-disk0",
-               "len": 10737418240, "offset": 134217728,
-               "speed": 0 },
-     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }
-
-BLOCK_JOB_COMPLETED
--------------------
-
-Emitted when a block job has completed.
-
-Data:
-
-- "type":     Job type (json-string; "stream" for image streaming
-                                     "commit" for block commit)
-- "device":   Device name (json-string)
-- "len":      Maximum progress value (json-int)
-- "offset":   Current progress value (json-int)
-              On success this is equal to len.
-              On failure this is less than len.
-- "speed":    Rate limit, bytes per second (json-int)
-- "error":    Error message (json-string, optional)
-              Only present on failure.  This field contains a human-readable
-              error message.  There are no semantics other than that streaming
-              has failed and clients should not try to interpret the error
-              string.
-
-Example:
-
-{ "event": "BLOCK_JOB_COMPLETED",
-     "data": { "type": "stream", "device": "virtio-disk0",
-               "len": 10737418240, "offset": 10737418240,
-               "speed": 0 },
-     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }
-
-BLOCK_JOB_ERROR
----------------
-
-Emitted when a block job encounters an error.
-
-Data:
-
-- "device": device name (json-string)
-- "operation": I/O operation (json-string, "read" or "write")
-- "action": action that has been taken, it's one of the following (json-string):
-    "ignore": error has been ignored, the job may fail later
-    "report": error will be reported and the job canceled
-    "stop": error caused job to be paused
-
-Example:
-
-{ "event": "BLOCK_JOB_ERROR",
-    "data": { "device": "ide0-hd1",
-              "operation": "write",
-              "action": "stop" },
-    "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
-BLOCK_JOB_READY
----------------
-
-Emitted when a block job is ready to complete.
-
-Data:
-
-- "device": device name (json-string)
-
-Example:
-
-{ "event": "BLOCK_JOB_READY",
-    "data": { "device": "ide0-hd1" },
-    "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
-Note: The "ready to complete" status is always reset by a BLOCK_JOB_ERROR
-event.
-
 DEVICE_TRAY_MOVED
 -----------------
 
@@ -208,68 +98,6 @@ Example:
 Note: If the command-line option "-no-shutdown" has been specified, a STOP
 event will eventually follow the SHUTDOWN event.
 
-SPICE_CONNECTED, SPICE_DISCONNECTED
------------------------------------
-
-Emitted when a SPICE client connects or disconnects.
-
-Data:
-
-- "server": Server information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-- "client": Client information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-
-Example:
-
-{ "timestamp": {"seconds": 1290688046, "microseconds": 388707},
-  "event": "SPICE_CONNECTED",
-  "data": {
-    "server": { "port": "5920", "family": "ipv4", "host": "127.0.0.1"},
-    "client": {"port": "52873", "family": "ipv4", "host": "127.0.0.1"}
-}}
-
-SPICE_INITIALIZED
------------------
-
-Emitted after initial handshake and authentication takes place (if any)
-and the SPICE channel is up'n'running
-
-Data:
-
-- "server": Server information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-  - "auth": authentication method (json-string, optional)
-- "client": Client information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-  - "connection-id": spice connection id.  All channels with the same id
-                     belong to the same spice session (json-int)
-  - "channel-type": channel type.  "1" is the main control channel, filter for
-                    this one if you want track spice sessions only (json-int)
-  - "channel-id": channel id.  Usually "0", might be different needed when
-                  multiple channels of the same type exist, such as multiple
-                  display channels in a multihead setup (json-int)
-  - "tls": whevener the channel is encrypted (json-bool)
-
-Example:
-
-{ "timestamp": {"seconds": 1290688046, "microseconds": 417172},
-  "event": "SPICE_INITIALIZED",
-  "data": {"server": {"auth": "spice", "port": "5921",
-                      "family": "ipv4", "host": "127.0.0.1"},
-           "client": {"port": "49004", "family": "ipv4", "channel-type": 3,
-                      "connection-id": 1804289383, "host": "127.0.0.1",
-                      "channel-id": 0, "tls": true}
-}}
-
 STOP
 ----
 
@@ -282,32 +110,6 @@ Example:
 { "event": "STOP",
     "timestamp": { "seconds": 1267041730, "microseconds": 281295 } }
 
-SUSPEND
--------
-
-Emitted when guest enters S3 state.
-
-Data: None.
-
-Example:
-
-{ "event": "SUSPEND",
-     "timestamp": { "seconds": 1344456160, "microseconds": 309119 } }
-
-SUSPEND_DISK
-------------
-
-Emitted when the guest makes a request to enter S4 state.
-
-Data: None.
-
-Example:
-
-{ "event": "SUSPEND_DISK",
-     "timestamp": { "seconds": 1344456160, "microseconds": 309119 } }
-
-Note: QEMU shuts down when entering S4 state.
-
 VNC_CONNECTED
 -------------
 
@@ -398,17 +200,69 @@ Example:
                     "host": "127.0.0.1", "sasl_username": "luiz" } },
         "timestamp": { "seconds": 1263475302, "microseconds": 150772 } }
 
-WAKEUP
-------
+SPICE_CONNECTED, SPICE_DISCONNECTED
+-----------------------------------
 
-Emitted when the guest has woken up from S3 and is running.
+Emitted when a SPICE client connects or disconnects.
 
-Data: None.
+Data:
+
+- "server": Server information (json-object)
+  - "host": IP address (json-string)
+  - "port": port number (json-string)
+  - "family": address family (json-string, "ipv4" or "ipv6")
+- "client": Client information (json-object)
+  - "host": IP address (json-string)
+  - "port": port number (json-string)
+  - "family": address family (json-string, "ipv4" or "ipv6")
 
 Example:
 
-{ "event": "WATCHDOG",
-     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
+{ "timestamp": {"seconds": 1290688046, "microseconds": 388707},
+  "event": "SPICE_CONNECTED",
+  "data": {
+    "server": { "port": "5920", "family": "ipv4", "host": "127.0.0.1"},
+    "client": {"port": "52873", "family": "ipv4", "host": "127.0.0.1"}
+}}
+
+
+SPICE_INITIALIZED
+-----------------
+
+Emitted after initial handshake and authentication takes place (if any)
+and the SPICE channel is up'n'running
+
+Data:
+
+- "server": Server information (json-object)
+  - "host": IP address (json-string)
+  - "port": port number (json-string)
+  - "family": address family (json-string, "ipv4" or "ipv6")
+  - "auth": authentication method (json-string, optional)
+- "client": Client information (json-object)
+  - "host": IP address (json-string)
+  - "port": port number (json-string)
+  - "family": address family (json-string, "ipv4" or "ipv6")
+  - "connection-id": spice connection id.  All channels with the same id
+                     belong to the same spice session (json-int)
+  - "channel-type": channel type.  "1" is the main control channel, filter for
+                    this one if you want track spice sessions only (json-int)
+  - "channel-id": channel id.  Usually "0", might be different needed when
+                  multiple channels of the same type exist, such as multiple
+                  display channels in a multihead setup (json-int)
+  - "tls": whevener the channel is encrypted (json-bool)
+
+Example:
+
+{ "timestamp": {"seconds": 1290688046, "microseconds": 417172},
+  "event": "SPICE_INITIALIZED",
+  "data": {"server": {"auth": "spice", "port": "5921",
+                      "family": "ipv4", "host": "127.0.0.1"},
+           "client": {"port": "49004", "family": "ipv4", "channel-type": 3,
+                      "connection-id": 1804289383, "host": "127.0.0.1",
+                      "channel-id": 0, "tls": true}
+}}
+
 
 WATCHDOG
 --------
@@ -428,3 +282,56 @@ Example:
 
 Note: If action is "reset", "shutdown", or "pause" the WATCHDOG event is
 followed respectively by the RESET, SHUTDOWN, or STOP events.
+
+
+BLOCK_JOB_COMPLETED
+-------------------
+
+Emitted when a block job has completed.
+
+Data:
+
+- "type":     Job type ("stream" for image streaming, json-string)
+- "device":   Device name (json-string)
+- "len":      Maximum progress value (json-int)
+- "offset":   Current progress value (json-int)
+              On success this is equal to len.
+              On failure this is less than len.
+- "speed":    Rate limit, bytes per second (json-int)
+- "error":    Error message (json-string, optional)
+              Only present on failure.  This field contains a human-readable
+              error message.  There are no semantics other than that streaming
+              has failed and clients should not try to interpret the error
+              string.
+
+Example:
+
+{ "event": "BLOCK_JOB_COMPLETED",
+     "data": { "type": "stream", "device": "virtio-disk0",
+               "len": 10737418240, "offset": 10737418240,
+               "speed": 0 },
+     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }
+
+
+BLOCK_JOB_CANCELLED
+-------------------
+
+Emitted when a block job has been cancelled.
+
+Data:
+
+- "type":     Job type ("stream" for image streaming, json-string)
+- "device":   Device name (json-string)
+- "len":      Maximum progress value (json-int)
+- "offset":   Current progress value (json-int)
+              On success this is equal to len.
+              On failure this is less than len.
+- "speed":    Rate limit, bytes per second (json-int)
+
+Example:
+
+{ "event": "BLOCK_JOB_CANCELLED",
+     "data": { "type": "stream", "device": "virtio-disk0",
+               "len": 10737418240, "offset": 134217728,
+               "speed": 0 },
+     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }

QMP/qmp-shell

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

QMP/qmp-spec.txt

@@ -106,11 +106,14 @@ completed because of an error condition.
 
 The format is:
 
-{ "error": { "class": json-string, "desc": json-string }, "id": json-value }
+{ "error": { "class": json-string, "data": json-object, "desc": json-string },
+  "id": json-value }
 
  Where,
 
-- The "class" member contains the error class name (eg. "GenericError")
+- The "class" member contains the error class name (eg. "ServiceUnavailable")
+- The "data" member contains specific error data and is defined in a
+  per-command basis, it will be an empty json-object if the error has no data
 - The "desc" member is a human-readable error message. Clients should
   not attempt to parse this message.
 - The "id" member contains the transaction identification associated with
@@ -170,7 +173,8 @@ S: {"return": {"enabled": true, "present": true}, "id": "example"}
 ------------------
 
 C: { "execute": }
-S: {"error": {"class": "GenericError", "desc": "Invalid JSON syntax" } }
+S: {"error": {"class": "JSONParsing", "desc": "Invalid JSON syntax", "data":
+{}}}
 
 3.5 Powerdown event
 -------------------

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 @@
-1.3.1
+1.1.2

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.h"
-#include "qemu-queue.h"
-#include "qemu_socket.h"
-
-struct AioHandler
-{
-    GPollFD pfd;
-    IOHandler *io_read;
-    IOHandler *io_write;
-    AioFlushHandler *io_flush;
-    int deleted;
-    void *opaque;
-    QLIST_ENTRY(AioHandler) node;
-};
-
-static AioHandler *find_aio_handler(AioContext *ctx, int fd)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->pfd.fd == fd)
-            if (!node->deleted)
-                return node;
-    }
-
-    return NULL;
-}
-
-void aio_set_fd_handler(AioContext *ctx,
-                        int fd,
-                        IOHandler *io_read,
-                        IOHandler *io_write,
-                        AioFlushHandler *io_flush,
-                        void *opaque)
-{
-    AioHandler *node;
-
-    node = find_aio_handler(ctx, fd);
-
-    /* Are we deleting the fd handler? */
-    if (!io_read && !io_write) {
-        if (node) {
-            g_source_remove_poll(&ctx->source, &node->pfd);
-
-            /* If the lock is held, just mark the node as deleted */
-            if (ctx->walking_handlers) {
-                node->deleted = 1;
-                node->pfd.revents = 0;
-            } else {
-                /* Otherwise, delete it for real.  We can't just mark it as
-                 * deleted because deleted nodes are only cleaned up after
-                 * releasing the walking_handlers lock.
-                 */
-                QLIST_REMOVE(node, node);
-                g_free(node);
-            }
-        }
-    } else {
-        if (node == NULL) {
-            /* Alloc and insert if it's not already there */
-            node = g_malloc0(sizeof(AioHandler));
-            node->pfd.fd = fd;
-            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
-
-            g_source_add_poll(&ctx->source, &node->pfd);
-        }
-        /* Update handler with latest information */
-        node->io_read = io_read;
-        node->io_write = io_write;
-        node->io_flush = io_flush;
-        node->opaque = opaque;
-
-        node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP : 0);
-        node->pfd.events |= (io_write ? G_IO_OUT : 0);
-    }
-
-    aio_notify(ctx);
-}
-
-void aio_set_event_notifier(AioContext *ctx,
-                            EventNotifier *notifier,
-                            EventNotifierHandler *io_read,
-                            AioFlushEventNotifierHandler *io_flush)
-{
-    aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
-                       (IOHandler *)io_read, NULL,
-                       (AioFlushHandler *)io_flush, notifier);
-}
-
-bool aio_pending(AioContext *ctx)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        int revents;
-
-        /*
-         * FIXME: right now we cannot get G_IO_HUP and G_IO_ERR because
-         * main-loop.c is still select based (due to the slirp legacy).
-         * If main-loop.c ever switches to poll, G_IO_ERR should be
-         * tested too.  Dispatching G_IO_ERR to both handlers should be
-         * okay, since handlers need to be ready for spurious wakeups.
-         */
-        revents = node->pfd.revents & node->pfd.events;
-        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
-            return true;
-        }
-        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
-            return true;
-        }
-    }
-
-    return false;
-}
-
-bool aio_poll(AioContext *ctx, bool blocking)
-{
-    static struct timeval tv0;
-    AioHandler *node;
-    fd_set rdfds, wrfds;
-    int max_fd = -1;
-    int ret;
-    bool busy, progress;
-
-    progress = false;
-
-    /*
-     * If there are callbacks left that have been queued, we need to call then.
-     * Do not call select in this case, because it is possible that the caller
-     * does not need a complete flush (as is the case for qemu_aio_wait loops).
-     */
-    if (aio_bh_poll(ctx)) {
-        blocking = false;
-        progress = true;
-    }
-
-    /*
-     * Then dispatch any pending callbacks from the GSource.
-     *
-     * We have to walk very carefully in case qemu_aio_set_fd_handler is
-     * called while we're walking.
-     */
-    node = QLIST_FIRST(&ctx->aio_handlers);
-    while (node) {
-        AioHandler *tmp;
-        int revents;
-
-        ctx->walking_handlers++;
-
-        revents = node->pfd.revents & node->pfd.events;
-        node->pfd.revents = 0;
-
-        /* See comment in aio_pending.  */
-        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
-            node->io_read(node->opaque);
-            progress = true;
-        }
-        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
-            node->io_write(node->opaque);
-            progress = true;
-        }
-
-        tmp = node;
-        node = QLIST_NEXT(node, node);
-
-        ctx->walking_handlers--;
-
-        if (!ctx->walking_handlers && tmp->deleted) {
-            QLIST_REMOVE(tmp, node);
-            g_free(tmp);
-        }
-    }
-
-    if (progress && !blocking) {
-        return true;
-    }
-
-    ctx->walking_handlers++;
-
-    FD_ZERO(&rdfds);
-    FD_ZERO(&wrfds);
-
-    /* fill fd sets */
-    busy = false;
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        /* If there aren't pending AIO operations, don't invoke callbacks.
-         * Otherwise, if there are no AIO requests, qemu_aio_wait() would
-         * wait indefinitely.
-         */
-        if (!node->deleted && node->io_flush) {
-            if (node->io_flush(node->opaque) == 0) {
-                continue;
-            }
-            busy = true;
-        }
-        if (!node->deleted && node->io_read) {
-            FD_SET(node->pfd.fd, &rdfds);
-            max_fd = MAX(max_fd, node->pfd.fd + 1);
-        }
-        if (!node->deleted && node->io_write) {
-            FD_SET(node->pfd.fd, &wrfds);
-            max_fd = MAX(max_fd, node->pfd.fd + 1);
-        }
-    }
-
-    ctx->walking_handlers--;
-
-    /* No AIO operations?  Get us out of here */
-    if (!busy) {
-        return progress;
-    }
-
-    /* wait until next event */
-    ret = select(max_fd, &rdfds, &wrfds, NULL, blocking ? NULL : &tv0);
-
-    /* if we have any readable fds, dispatch event */
-    if (ret > 0) {
-        /* we have to walk very carefully in case
-         * qemu_aio_set_fd_handler is called while we're walking */
-        node = QLIST_FIRST(&ctx->aio_handlers);
-        while (node) {
-            AioHandler *tmp;
-
-            ctx->walking_handlers++;
-
-            if (!node->deleted &&
-                FD_ISSET(node->pfd.fd, &rdfds) &&
-                node->io_read) {
-                node->io_read(node->opaque);
-                progress = true;
-            }
-            if (!node->deleted &&
-                FD_ISSET(node->pfd.fd, &wrfds) &&
-                node->io_write) {
-                node->io_write(node->opaque);
-                progress = true;
-            }
-
-            tmp = node;
-            node = QLIST_NEXT(node, node);
-
-            ctx->walking_handlers--;
-
-            if (!ctx->walking_handlers && tmp->deleted) {
-                QLIST_REMOVE(tmp, node);
-                g_free(tmp);
-            }
-        }
-    }
-
-    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.h"
-#include "qemu-queue.h"
-#include "qemu_socket.h"
-
-struct AioHandler {
-    EventNotifier *e;
-    EventNotifierHandler *io_notify;
-    AioFlushEventNotifierHandler *io_flush;
-    GPollFD pfd;
-    int deleted;
-    QLIST_ENTRY(AioHandler) node;
-};
-
-void aio_set_event_notifier(AioContext *ctx,
-                            EventNotifier *e,
-                            EventNotifierHandler *io_notify,
-                            AioFlushEventNotifierHandler *io_flush)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->e == e && !node->deleted) {
-            break;
-        }
-    }
-
-    /* Are we deleting the fd handler? */
-    if (!io_notify) {
-        if (node) {
-            g_source_remove_poll(&ctx->source, &node->pfd);
-
-            /* If the lock is held, just mark the node as deleted */
-            if (ctx->walking_handlers) {
-                node->deleted = 1;
-                node->pfd.revents = 0;
-            } else {
-                /* Otherwise, delete it for real.  We can't just mark it as
-                 * deleted because deleted nodes are only cleaned up after
-                 * releasing the walking_handlers lock.
-                 */
-                QLIST_REMOVE(node, node);
-                g_free(node);
-            }
-        }
-    } else {
-        if (node == NULL) {
-            /* Alloc and insert if it's not already there */
-            node = g_malloc0(sizeof(AioHandler));
-            node->e = e;
-            node->pfd.fd = (uintptr_t)event_notifier_get_handle(e);
-            node->pfd.events = G_IO_IN;
-            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
-
-            g_source_add_poll(&ctx->source, &node->pfd);
-        }
-        /* Update handler with latest information */
-        node->io_notify = io_notify;
-        node->io_flush = io_flush;
-    }
-
-    aio_notify(ctx);
-}
-
-bool aio_pending(AioContext *ctx)
-{
-    AioHandler *node;
-
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        if (node->pfd.revents && node->io_notify) {
-            return true;
-        }
-    }
-
-    return false;
-}
-
-bool aio_poll(AioContext *ctx, bool blocking)
-{
-    AioHandler *node;
-    HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
-    bool busy, progress;
-    int count;
-
-    progress = false;
-
-    /*
-     * If there are callbacks left that have been queued, we need to call then.
-     * Do not call select in this case, because it is possible that the caller
-     * does not need a complete flush (as is the case for qemu_aio_wait loops).
-     */
-    if (aio_bh_poll(ctx)) {
-        blocking = false;
-        progress = true;
-    }
-
-    /*
-     * Then dispatch any pending callbacks from the GSource.
-     *
-     * We have to walk very carefully in case qemu_aio_set_fd_handler is
-     * called while we're walking.
-     */
-    node = QLIST_FIRST(&ctx->aio_handlers);
-    while (node) {
-        AioHandler *tmp;
-
-        ctx->walking_handlers++;
-
-        if (node->pfd.revents && node->io_notify) {
-            node->pfd.revents = 0;
-            node->io_notify(node->e);
-            progress = true;
-        }
-
-        tmp = node;
-        node = QLIST_NEXT(node, node);
-
-        ctx->walking_handlers--;
-
-        if (!ctx->walking_handlers && tmp->deleted) {
-            QLIST_REMOVE(tmp, node);
-            g_free(tmp);
-        }
-    }
-
-    if (progress && !blocking) {
-        return true;
-    }
-
-    ctx->walking_handlers++;
-
-    /* fill fd sets */
-    busy = false;
-    count = 0;
-    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
-        /* If there aren't pending AIO operations, don't invoke callbacks.
-         * Otherwise, if there are no AIO requests, qemu_aio_wait() would
-         * wait indefinitely.
-         */
-        if (!node->deleted && node->io_flush) {
-            if (node->io_flush(node->e) == 0) {
-                continue;
-            }
-            busy = true;
-        }
-        if (!node->deleted && node->io_notify) {
-            events[count++] = event_notifier_get_handle(node->e);
-        }
-    }
-
-    ctx->walking_handlers--;
-
-    /* No AIO operations?  Get us out of here */
-    if (!busy) {
-        return progress;
-    }
-
-    /* wait until next event */
-    while (count > 0) {
-        int timeout = blocking ? INFINITE : 0;
-        int ret = WaitForMultipleObjects(count, events, FALSE, timeout);
-
-        /* if we have any signaled events, dispatch event */
-        if ((DWORD) (ret - WAIT_OBJECT_0) >= count) {
-            break;
-        }
-
-        blocking = false;
-
-        /* we have to walk very carefully in case
-         * qemu_aio_set_fd_handler is called while we're walking */
-        node = QLIST_FIRST(&ctx->aio_handlers);
-        while (node) {
-            AioHandler *tmp;
-
-            ctx->walking_handlers++;
-
-            if (!node->deleted &&
-                event_notifier_get_handle(node->e) == events[ret - WAIT_OBJECT_0] &&
-                node->io_notify) {
-                node->io_notify(node->e);
-                progress = true;
-            }
-
-            tmp = node;
-            node = QLIST_NEXT(node, node);
-
-            ctx->walking_handlers--;
-
-            if (!ctx->walking_handlers && tmp->deleted) {
-                QLIST_REMOVE(tmp, node);
-                g_free(tmp);
-            }
-        }
-
-        /* Try again, but only call each handler once.  */
-        events[ret - WAIT_OBJECT_0] = events[--count];
-    }
-
-    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;
+}

arch_init.c

@@ -31,8 +31,6 @@
 #include "config.h"
 #include "monitor.h"
 #include "sysemu.h"
-#include "bitops.h"
-#include "bitmap.h"
 #include "arch_init.h"
 #include "audio/audio.h"
 #include "hw/pc.h"
@@ -45,17 +43,6 @@
 #include "hw/smbios.h"
 #include "exec-memory.h"
 #include "hw/pcspk.h"
-#include "qemu/page_cache.h"
-#include "qmp-commands.h"
-#include "trace.h"
-
-#ifdef DEBUG_ARCH_INIT
-#define DPRINTF(fmt, ...) \
-    do { fprintf(stdout, "arch_init: " fmt, ## __VA_ARGS__); } while (0)
-#else
-#define DPRINTF(fmt, ...) \
-    do { } while (0)
-#endif
 
 #ifdef TARGET_SPARC
 int graphic_width = 1024;
@@ -84,8 +71,6 @@ int graphic_depth = 15;
 #define QEMU_ARCH QEMU_ARCH_MICROBLAZE
 #elif defined(TARGET_MIPS)
 #define QEMU_ARCH QEMU_ARCH_MIPS
-#elif defined(TARGET_OPENRISC)
-#define QEMU_ARCH QEMU_ARCH_OPENRISC
 #elif defined(TARGET_PPC)
 #define QEMU_ARCH QEMU_ARCH_PPC
 #elif defined(TARGET_S390X)
@@ -96,8 +81,6 @@ int graphic_depth = 15;
 #define QEMU_ARCH QEMU_ARCH_SPARC
 #elif defined(TARGET_XTENSA)
 #define QEMU_ARCH QEMU_ARCH_XTENSA
-#elif defined(TARGET_UNICORE32)
-#define QEMU_ARCH QEMU_ARCH_UNICORE32
 #endif
 
 const uint32_t arch_type = QEMU_ARCH;
@@ -111,7 +94,6 @@ const uint32_t arch_type = QEMU_ARCH;
 #define RAM_SAVE_FLAG_PAGE     0x08
 #define RAM_SAVE_FLAG_EOS      0x10
 #define RAM_SAVE_FLAG_CONTINUE 0x20
-#define RAM_SAVE_FLAG_XBZRLE   0x40
 
 #ifdef __ALTIVEC__
 #include <altivec.h>
@@ -139,6 +121,7 @@ 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 */
@@ -178,287 +161,52 @@ static int is_dup_page(uint8_t *page)
     return 1;
 }
 
-/* struct contains XBZRLE cache and a static page
-   used by the compression */
-static struct {
-    /* buffer used for XBZRLE encoding */
-    uint8_t *encoded_buf;
-    /* buffer for storing page content */
-    uint8_t *current_buf;
-    /* buffer used for XBZRLE decoding */
-    uint8_t *decoded_buf;
-    /* Cache for XBZRLE */
-    PageCache *cache;
-} XBZRLE = {
-    .encoded_buf = NULL,
-    .current_buf = NULL,
-    .decoded_buf = NULL,
-    .cache = NULL,
-};
-
-
-int64_t xbzrle_cache_resize(int64_t new_size)
-{
-    if (XBZRLE.cache != NULL) {
-        return cache_resize(XBZRLE.cache, new_size / TARGET_PAGE_SIZE) *
-            TARGET_PAGE_SIZE;
-    }
-    return pow2floor(new_size);
-}
-
-/* accounting for migration statistics */
-typedef struct AccountingInfo {
-    uint64_t dup_pages;
-    uint64_t norm_pages;
-    uint64_t iterations;
-    uint64_t xbzrle_bytes;
-    uint64_t xbzrle_pages;
-    uint64_t xbzrle_cache_miss;
-    uint64_t xbzrle_overflows;
-} AccountingInfo;
-
-static AccountingInfo acct_info;
-
-static void acct_clear(void)
-{
-    memset(&acct_info, 0, sizeof(acct_info));
-}
-
-uint64_t dup_mig_bytes_transferred(void)
-{
-    return acct_info.dup_pages * TARGET_PAGE_SIZE;
-}
-
-uint64_t dup_mig_pages_transferred(void)
-{
-    return acct_info.dup_pages;
-}
-
-uint64_t norm_mig_bytes_transferred(void)
-{
-    return acct_info.norm_pages * TARGET_PAGE_SIZE;
-}
-
-uint64_t norm_mig_pages_transferred(void)
-{
-    return acct_info.norm_pages;
-}
-
-uint64_t xbzrle_mig_bytes_transferred(void)
-{
-    return acct_info.xbzrle_bytes;
-}
-
-uint64_t xbzrle_mig_pages_transferred(void)
-{
-    return acct_info.xbzrle_pages;
-}
-
-uint64_t xbzrle_mig_pages_cache_miss(void)
-{
-    return acct_info.xbzrle_cache_miss;
-}
-
-uint64_t xbzrle_mig_pages_overflow(void)
-{
-    return acct_info.xbzrle_overflows;
-}
-
-static void save_block_hdr(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
-        int cont, int flag)
-{
-        qemu_put_be64(f, offset | cont | flag);
-        if (!cont) {
-                qemu_put_byte(f, strlen(block->idstr));
-                qemu_put_buffer(f, (uint8_t *)block->idstr,
-                                strlen(block->idstr));
-        }
-
-}
-
-#define ENCODING_FLAG_XBZRLE 0x1
-
-static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
-                            ram_addr_t current_addr, RAMBlock *block,
-                            ram_addr_t offset, int cont, bool last_stage)
-{
-    int encoded_len = 0, bytes_sent = -1;
-    uint8_t *prev_cached_page;
-
-    if (!cache_is_cached(XBZRLE.cache, current_addr)) {
-        if (!last_stage) {
-            cache_insert(XBZRLE.cache, current_addr,
-                         g_memdup(current_data, TARGET_PAGE_SIZE));
-        }
-        acct_info.xbzrle_cache_miss++;
-        return -1;
-    }
-
-    prev_cached_page = get_cached_data(XBZRLE.cache, current_addr);
-
-    /* save current buffer into memory */
-    memcpy(XBZRLE.current_buf, current_data, TARGET_PAGE_SIZE);
-
-    /* XBZRLE encoding (if there is no overflow) */
-    encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
-                                       TARGET_PAGE_SIZE, XBZRLE.encoded_buf,
-                                       TARGET_PAGE_SIZE);
-    if (encoded_len == 0) {
-        DPRINTF("Skipping unmodified page\n");
-        return 0;
-    } else if (encoded_len == -1) {
-        DPRINTF("Overflow\n");
-        acct_info.xbzrle_overflows++;
-        /* update data in the cache */
-        memcpy(prev_cached_page, current_data, TARGET_PAGE_SIZE);
-        return -1;
-    }
-
-    /* we need to update the data in the cache, in order to get the same data */
-    if (!last_stage) {
-        memcpy(prev_cached_page, XBZRLE.current_buf, TARGET_PAGE_SIZE);
-    }
-
-    /* Send XBZRLE based compressed page */
-    save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_XBZRLE);
-    qemu_put_byte(f, ENCODING_FLAG_XBZRLE);
-    qemu_put_be16(f, encoded_len);
-    qemu_put_buffer(f, XBZRLE.encoded_buf, encoded_len);
-    bytes_sent = encoded_len + 1 + 2;
-    acct_info.xbzrle_pages++;
-    acct_info.xbzrle_bytes += bytes_sent;
-
-    return bytes_sent;
-}
-
 static RAMBlock *last_block;
 static ram_addr_t last_offset;
-static unsigned long *migration_bitmap;
-static uint64_t migration_dirty_pages;
 
-static inline bool migration_bitmap_test_and_reset_dirty(MemoryRegion *mr,
-                                                         ram_addr_t offset)
-{
-    bool ret;
-    int nr = (mr->ram_addr + offset) >> TARGET_PAGE_BITS;
-
-    ret = test_and_clear_bit(nr, migration_bitmap);
-
-    if (ret) {
-        migration_dirty_pages--;
-    }
-    return ret;
-}
-
-static inline bool migration_bitmap_set_dirty(MemoryRegion *mr,
-                                              ram_addr_t offset)
-{
-    bool ret;
-    int nr = (mr->ram_addr + offset) >> TARGET_PAGE_BITS;
-
-    ret = test_and_set_bit(nr, migration_bitmap);
-
-    if (!ret) {
-        migration_dirty_pages++;
-    }
-    return ret;
-}
-
-static void migration_bitmap_sync(void)
-{
-    RAMBlock *block;
-    ram_addr_t addr;
-    uint64_t num_dirty_pages_init = migration_dirty_pages;
-    MigrationState *s = migrate_get_current();
-    static int64_t start_time;
-    static int64_t num_dirty_pages_period;
-    int64_t end_time;
-
-    if (!start_time) {
-        start_time = qemu_get_clock_ms(rt_clock);
-    }
-
-    trace_migration_bitmap_sync_start();
-    memory_global_sync_dirty_bitmap(get_system_memory());
-
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
-        for (addr = 0; addr < block->length; addr += TARGET_PAGE_SIZE) {
-            if (memory_region_get_dirty(block->mr, addr, TARGET_PAGE_SIZE,
-                                        DIRTY_MEMORY_MIGRATION)) {
-                migration_bitmap_set_dirty(block->mr, addr);
-            }
-        }
-        memory_region_reset_dirty(block->mr, 0, block->length,
-                                  DIRTY_MEMORY_MIGRATION);
-    }
-    trace_migration_bitmap_sync_end(migration_dirty_pages
-                                    - num_dirty_pages_init);
-    num_dirty_pages_period += migration_dirty_pages - num_dirty_pages_init;
-    end_time = qemu_get_clock_ms(rt_clock);
-
-    /* more than 1 second = 1000 millisecons */
-    if (end_time > start_time + 1000) {
-        s->dirty_pages_rate = num_dirty_pages_period * 1000
-            / (end_time - start_time);
-        start_time = end_time;
-        num_dirty_pages_period = 0;
-    }
-}
-
-
-/*
- * ram_save_block: Writes a page of memory to the stream f
- *
- * Returns:  0: if the page hasn't changed
- *          -1: if there are no more dirty pages
- *           n: the amount of bytes written in other case
- */
-
-static int ram_save_block(QEMUFile *f, bool last_stage)
+static int ram_save_block(QEMUFile *f)
 {
     RAMBlock *block = last_block;
     ram_addr_t offset = last_offset;
-    int bytes_sent = -1;
+    int bytes_sent = 0;
     MemoryRegion *mr;
-    ram_addr_t current_addr;
 
     if (!block)
         block = QLIST_FIRST(&ram_list.blocks);
 
     do {
         mr = block->mr;
-        if (migration_bitmap_test_and_reset_dirty(mr, offset)) {
+        if (memory_region_get_dirty(mr, offset, TARGET_PAGE_SIZE,
+                                    DIRTY_MEMORY_MIGRATION)) {
             uint8_t *p;
             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;
 
             if (is_dup_page(p)) {
-                acct_info.dup_pages++;
-                save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_COMPRESS);
+                qemu_put_be64(f, offset | cont | RAM_SAVE_FLAG_COMPRESS);
+                if (!cont) {
+                    qemu_put_byte(f, strlen(block->idstr));
+                    qemu_put_buffer(f, (uint8_t *)block->idstr,
+                                    strlen(block->idstr));
+                }
                 qemu_put_byte(f, *p);
                 bytes_sent = 1;
-            } else if (migrate_use_xbzrle()) {
-                current_addr = block->offset + offset;
-                bytes_sent = save_xbzrle_page(f, p, current_addr, block,
-                                              offset, cont, last_stage);
-                if (!last_stage) {
-                    p = get_cached_data(XBZRLE.cache, current_addr);
+            } else {
+                qemu_put_be64(f, offset | cont | RAM_SAVE_FLAG_PAGE);
+                if (!cont) {
+                    qemu_put_byte(f, strlen(block->idstr));
+                    qemu_put_buffer(f, (uint8_t *)block->idstr,
+                                    strlen(block->idstr));
                 }
-            }
-
-            /* either we didn't send yet (we may have had XBZRLE overflow) */
-            if (bytes_sent == -1) {
-                save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
                 qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
                 bytes_sent = TARGET_PAGE_SIZE;
-                acct_info.norm_pages++;
             }
 
-            /* if page is unmodified, continue to the next */
-            if (bytes_sent != 0) {
-                break;
-            }
+            break;
         }
 
         offset += TARGET_PAGE_SIZE;
@@ -480,7 +228,20 @@ static uint64_t bytes_transferred;
 
 static ram_addr_t ram_save_remaining(void)
 {
-    return migration_dirty_pages;
+    RAMBlock *block;
+    ram_addr_t count = 0;
+
+    QLIST_FOREACH(block, &ram_list.blocks, next) {
+        ram_addr_t addr;
+        for (addr = 0; addr < block->length; addr += TARGET_PAGE_SIZE) {
+            if (memory_region_get_dirty(block->mr, addr, TARGET_PAGE_SIZE,
+                                        DIRTY_MEMORY_MIGRATION)) {
+                count++;
+            }
+        }
+    }
+
+    return count;
 }
 
 uint64_t ram_bytes_remaining(void)
@@ -533,117 +294,60 @@ static void sort_ram_list(void)
     g_free(blocks);
 }
 
-static void migration_end(void)
-{
-    if (migration_bitmap) {
-        memory_global_dirty_log_stop();
-        g_free(migration_bitmap);
-        migration_bitmap = NULL;
-    }
-
-    if (XBZRLE.cache) {
-        cache_fini(XBZRLE.cache);
-        g_free(XBZRLE.cache);
-        g_free(XBZRLE.encoded_buf);
-        g_free(XBZRLE.current_buf);
-        g_free(XBZRLE.decoded_buf);
-        XBZRLE.cache = NULL;
-    }
-}
-
-static void ram_migration_cancel(void *opaque)
-{
-    migration_end();
-}
-
-
-static void reset_ram_globals(void)
-{
-    last_block = NULL;
-    last_offset = 0;
-    sort_ram_list();
-}
-
-#define MAX_WAIT 50 /* ms, half buffered_file limit */
-
-static int ram_save_setup(QEMUFile *f, void *opaque)
-{
-    RAMBlock *block;
-    int64_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;
-
-    migration_bitmap = bitmap_new(ram_pages);
-    bitmap_set(migration_bitmap, 0, ram_pages);
-    migration_dirty_pages = ram_pages;
-
-    bytes_transferred = 0;
-    reset_ram_globals();
-
-    if (migrate_use_xbzrle()) {
-        XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
-                                  TARGET_PAGE_SIZE,
-                                  TARGET_PAGE_SIZE);
-        if (!XBZRLE.cache) {
-            DPRINTF("Error creating cache\n");
-            return -1;
-        }
-        XBZRLE.encoded_buf = g_malloc0(TARGET_PAGE_SIZE);
-        XBZRLE.current_buf = g_malloc(TARGET_PAGE_SIZE);
-        acct_clear();
-    }
-
-    memory_global_dirty_log_start();
-    migration_bitmap_sync();
-
-    qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
-
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
-        qemu_put_byte(f, strlen(block->idstr));
-        qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr));
-        qemu_put_be64(f, block->length);
-    }
-
-    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
-
-    return 0;
-}
-
-static int ram_save_iterate(QEMUFile *f, void *opaque)
+int ram_save_live(QEMUFile *f, int stage, void *opaque)
 {
+    ram_addr_t addr;
     uint64_t bytes_transferred_last;
     double bwidth = 0;
+    uint64_t expected_time = 0;
     int ret;
-    int i;
-    uint64_t expected_downtime;
-    MigrationState *s = migrate_get_current();
+
+    if (stage < 0) {
+        memory_global_dirty_log_stop();
+        return 0;
+    }
+
+    memory_global_sync_dirty_bitmap(get_system_memory());
+
+    if (stage == 1) {
+        RAMBlock *block;
+        bytes_transferred = 0;
+        last_block = NULL;
+        last_offset = 0;
+        sort_ram_list();
+
+        /* Make sure all dirty bits are set */
+        QLIST_FOREACH(block, &ram_list.blocks, next) {
+            for (addr = 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();
+
+        qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
+
+        QLIST_FOREACH(block, &ram_list.blocks, next) {
+            qemu_put_byte(f, strlen(block->idstr));
+            qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr));
+            qemu_put_be64(f, block->length);
+        }
+    }
 
     bytes_transferred_last = bytes_transferred;
     bwidth = qemu_get_clock_ns(rt_clock);
 
-    i = 0;
     while ((ret = qemu_file_rate_limit(f)) == 0) {
         int bytes_sent;
 
-        bytes_sent = ram_save_block(f, false);
-        /* no more blocks to sent */
-        if (bytes_sent < 0) {
+        bytes_sent = ram_save_block(f);
+        bytes_transferred += bytes_sent;
+        if (bytes_sent == 0) { /* no more blocks */
             break;
         }
-        bytes_transferred += bytes_sent;
-        acct_info.iterations++;
-        /* we want to check in the 1st loop, just in case it was the 1st time
-           and we had to sync the dirty bitmap.
-           qemu_get_clock_ns() is a bit expensive, so we only check each some
-           iterations
-        */
-        if ((i & 63) == 0) {
-            uint64_t t1 = (qemu_get_clock_ns(rt_clock) - bwidth) / 1000000;
-            if (t1 > MAX_WAIT) {
-                DPRINTF("big wait: %" PRIu64 " milliseconds, %d iterations\n",
-                        t1, i);
-                break;
-            }
-        }
-        i++;
     }
 
     if (ret < 0) {
@@ -653,92 +357,28 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
     bwidth = qemu_get_clock_ns(rt_clock) - bwidth;
     bwidth = (bytes_transferred - bytes_transferred_last) / bwidth;
 
-    /* if we haven't transferred anything this round, force
-     * expected_downtime to a very high value, but without
-     * crashing */
+    /* if we haven't transferred anything this round, force expected_time to a
+     * a very high value, but without crashing */
     if (bwidth == 0) {
         bwidth = 0.000001;
     }
 
-    qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
-
-    expected_downtime = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
-    DPRINTF("ram_save_live: expected(%" PRIu64 ") <= max(" PRIu64 ")?\n",
-            expected_downtime, migrate_max_downtime());
-
-    if (expected_downtime <= migrate_max_downtime()) {
-        migration_bitmap_sync();
-        expected_downtime = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
-        s->expected_downtime = expected_downtime / 1000000; /* ns -> ms */
-
-        return expected_downtime <= migrate_max_downtime();
-    }
-    return 0;
-}
-
-static int ram_save_complete(QEMUFile *f, void *opaque)
-{
-    migration_bitmap_sync();
-
     /* try transferring iterative blocks of memory */
-
-    /* flush all remaining blocks regardless of rate limiting */
-    while (true) {
+    if (stage == 3) {
         int bytes_sent;
 
-        bytes_sent = ram_save_block(f, true);
-        /* no more blocks to sent */
-        if (bytes_sent < 0) {
-            break;
+        /* flush all remaining blocks regardless of rate limiting */
+        while ((bytes_sent = ram_save_block(f)) != 0) {
+            bytes_transferred += bytes_sent;
         }
-        bytes_transferred += bytes_sent;
+        memory_global_dirty_log_stop();
     }
-    migration_end();
 
     qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
 
-    return 0;
-}
+    expected_time = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
 
-static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
-{
-    int ret, rc = 0;
-    unsigned int xh_len;
-    int xh_flags;
-
-    if (!XBZRLE.decoded_buf) {
-        XBZRLE.decoded_buf = g_malloc(TARGET_PAGE_SIZE);
-    }
-
-    /* extract RLE header */
-    xh_flags = qemu_get_byte(f);
-    xh_len = qemu_get_be16(f);
-
-    if (xh_flags != ENCODING_FLAG_XBZRLE) {
-        fprintf(stderr, "Failed to load XBZRLE page - wrong compression!\n");
-        return -1;
-    }
-
-    if (xh_len > TARGET_PAGE_SIZE) {
-        fprintf(stderr, "Failed to load XBZRLE page - len overflow!\n");
-        return -1;
-    }
-    /* load data and decode */
-    qemu_get_buffer(f, XBZRLE.decoded_buf, xh_len);
-
-    /* decode RLE */
-    ret = xbzrle_decode_buffer(XBZRLE.decoded_buf, xh_len, host,
-                               TARGET_PAGE_SIZE);
-    if (ret == -1) {
-        fprintf(stderr, "Failed to load XBZRLE page - decode error!\n");
-        rc = -1;
-    } else  if (ret > TARGET_PAGE_SIZE) {
-        fprintf(stderr, "Failed to load XBZRLE page - size %d exceeds %d!\n",
-                ret, TARGET_PAGE_SIZE);
-        abort();
-    }
-
-    return rc;
+    return (stage == 2) && (expected_time <= migrate_max_downtime());
 }
 
 static inline void *host_from_stream_offset(QEMUFile *f,
@@ -771,14 +411,11 @@ static inline void *host_from_stream_offset(QEMUFile *f,
     return NULL;
 }
 
-static int ram_load(QEMUFile *f, void *opaque, int version_id)
+int ram_load(QEMUFile *f, void *opaque, int version_id)
 {
     ram_addr_t addr;
-    int flags, ret = 0;
+    int flags;
     int error;
-    static uint64_t seq_iter;
-
-    seq_iter++;
 
     if (version_id < 4 || version_id > 4) {
         return -EINVAL;
@@ -808,10 +445,8 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
 
                     QLIST_FOREACH(block, &ram_list.blocks, next) {
                         if (!strncmp(id, block->idstr, sizeof(id))) {
-                            if (block->length != length) {
-                                ret =  -EINVAL;
-                                goto done;
-                            }
+                            if (block->length != length)
+                                return -EINVAL;
                             break;
                         }
                     }
@@ -819,8 +454,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                     if (!block) {
                         fprintf(stderr, "Unknown ramblock \"%s\", cannot "
                                 "accept migration\n", id);
-                        ret = -EINVAL;
-                        goto done;
+                        return -EINVAL;
                     }
 
                     total_ram_bytes -= length;
@@ -841,8 +475,7 @@ 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
@@ -850,46 +483,18 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
             void *host;
 
             host = host_from_stream_offset(f, addr, flags);
-            if (!host) {
-                return -EINVAL;
-            }
 
             qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
-        } else if (flags & RAM_SAVE_FLAG_XBZRLE) {
-            if (!migrate_use_xbzrle()) {
-                return -EINVAL;
-            }
-            void *host = host_from_stream_offset(f, addr, flags);
-            if (!host) {
-                return -EINVAL;
-            }
-
-            if (load_xbzrle(f, addr, host) < 0) {
-                ret = -EINVAL;
-                goto done;
-            }
         }
         error = qemu_file_get_error(f);
         if (error) {
-            ret = error;
-            goto done;
+            return error;
         }
     } while (!(flags & RAM_SAVE_FLAG_EOS));
 
-done:
-    DPRINTF("Completed load of VM with exit code %d seq iteration "
-            "%" PRIu64 "\n", ret, seq_iter);
-    return ret;
+    return 0;
 }
 
-SaveVMHandlers savevm_ram_handlers = {
-    .save_live_setup = ram_save_setup,
-    .save_live_iterate = ram_save_iterate,
-    .save_live_complete = ram_save_complete,
-    .load_state = ram_load,
-    .cancel = ram_migration_cancel,
-};
-
 #ifdef HAS_AUDIO
 struct soundhw {
     const char *name;
@@ -997,20 +602,15 @@ void select_soundhw(const char *optarg)
 {
     struct soundhw *c;
 
-    if (is_help_option(optarg)) {
+    if (*optarg == '?') {
     show_valid_cards:
 
-#ifdef HAS_AUDIO_CHOICE
         printf("Valid sound card names (comma separated):\n");
         for (c = soundhw; c->name; ++c) {
             printf ("%-11s %s\n", c->name, c->descr);
         }
         printf("\n-soundhw all will enable all of the above\n");
-#else
-        printf("Machine has no user-selectable audio hardware "
-               "(it may or may not have always-present audio hardware).\n");
-#endif
-        exit(!is_help_option(optarg));
+        exit(*optarg != '?');
     }
     else {
         size_t l;
@@ -1164,13 +764,3 @@ int xen_available(void)
     return 0;
 #endif
 }
-
-
-TargetInfo *qmp_query_target(Error **errp)
-{
-    TargetInfo *info = g_malloc0(sizeof(*info));
-
-    info->arch = TARGET_TYPE;
-
-    return info;
-}

arch_init.h

@@ -1,8 +1,6 @@
 #ifndef QEMU_ARCH_INIT_H
 #define QEMU_ARCH_INIT_H
 
-#include "qmp-commands.h"
-
 enum {
     QEMU_ARCH_ALL = -1,
     QEMU_ARCH_ALPHA = 1,
@@ -18,8 +16,6 @@ enum {
     QEMU_ARCH_SH4 = 1024,
     QEMU_ARCH_SPARC = 2048,
     QEMU_ARCH_XTENSA = 4096,
-    QEMU_ARCH_OPENRISC = 8192,
-    QEMU_ARCH_UNICORE32 = 0x4000,
 };
 
 extern const uint32_t arch_type;
@@ -34,6 +30,4 @@ int tcg_available(void);
 int kvm_available(void);
 int xen_available(void);
 
-CpuDefinitionInfoList *arch_query_cpu_definitions(Error **errp);
-
 #endif

arm-semi.c

@@ -166,20 +166,17 @@ static void arm_semi_flen_cb(CPUARMState *env, target_ulong ret, target_ulong er
 #endif
 }
 
-/* Read the input value from the argument block; fail the semihosting
- * call if the memory read fails.
- */
-#define GET_ARG(n) do {                                 \
-    if (get_user_ual(arg ## n, args + (n) * 4)) {       \
-        return (uint32_t)-1;                            \
-    }                                                   \
-} while (0)
-
+#define ARG(n)					\
+({						\
+    target_ulong __arg;				\
+    /* FIXME - handle get_user() failure */	\
+    get_user_ual(__arg, args + (n) * 4);	\
+    __arg;					\
+})
 #define SET_ARG(n, val) put_user_ual(val, args + (n) * 4)
 uint32_t do_arm_semihosting(CPUARMState *env)
 {
     target_ulong args;
-    target_ulong arg0, arg1, arg2, arg3;
     char * s;
     int nr;
     uint32_t ret;
@@ -194,39 +191,33 @@ uint32_t do_arm_semihosting(CPUARMState *env)
     args = env->regs[1];
     switch (nr) {
     case TARGET_SYS_OPEN:
-        GET_ARG(0);
-        GET_ARG(1);
-        GET_ARG(2);
-        s = lock_user_string(arg0);
-        if (!s) {
+        if (!(s = lock_user_string(ARG(0))))
             /* FIXME - should this error code be -TARGET_EFAULT ? */
             return (uint32_t)-1;
-        }
-        if (arg1 >= 12) {
-            unlock_user(s, arg0, 0);
+        if (ARG(1) >= 12) {
+            unlock_user(s, ARG(0), 0);
             return (uint32_t)-1;
         }
         if (strcmp(s, ":tt") == 0) {
-            int result_fileno = arg1 < 4 ? STDIN_FILENO : STDOUT_FILENO;
-            unlock_user(s, arg0, 0);
+            int result_fileno = ARG(1) < 4 ? STDIN_FILENO : STDOUT_FILENO;
+            unlock_user(s, ARG(0), 0);
             return result_fileno;
         }
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "open,%s,%x,1a4", arg0,
-                           (int)arg2+1, gdb_open_modeflags[arg1]);
+            gdb_do_syscall(arm_semi_cb, "open,%s,%x,1a4", ARG(0),
+			   (int)ARG(2)+1, gdb_open_modeflags[ARG(1)]);
             ret = env->regs[0];
         } else {
-            ret = set_swi_errno(ts, open(s, open_modeflags[arg1], 0644));
+            ret = set_swi_errno(ts, open(s, open_modeflags[ARG(1)], 0644));
         }
-        unlock_user(s, arg0, 0);
+        unlock_user(s, ARG(0), 0);
         return ret;
     case TARGET_SYS_CLOSE:
-        GET_ARG(0);
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "close,%x", arg0);
+            gdb_do_syscall(arm_semi_cb, "close,%x", ARG(0));
             return env->regs[0];
         } else {
-            return set_swi_errno(ts, close(arg0));
+            return set_swi_errno(ts, close(ARG(0)));
         }
     case TARGET_SYS_WRITEC:
         {
@@ -257,81 +248,67 @@ uint32_t do_arm_semihosting(CPUARMState *env)
         unlock_user(s, args, 0);
         return ret;
     case TARGET_SYS_WRITE:
-        GET_ARG(0);
-        GET_ARG(1);
-        GET_ARG(2);
-        len = arg2;
+        len = ARG(2);
         if (use_gdb_syscalls()) {
             arm_semi_syscall_len = len;
-            gdb_do_syscall(arm_semi_cb, "write,%x,%x,%x", arg0, arg1, len);
+            gdb_do_syscall(arm_semi_cb, "write,%x,%x,%x", ARG(0), ARG(1), len);
             return env->regs[0];
         } else {
-            s = lock_user(VERIFY_READ, arg1, len, 1);
-            if (!s) {
+            if (!(s = lock_user(VERIFY_READ, ARG(1), len, 1)))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
-            ret = set_swi_errno(ts, write(arg0, s, len));
-            unlock_user(s, arg1, 0);
+            ret = set_swi_errno(ts, write(ARG(0), s, len));
+            unlock_user(s, ARG(1), 0);
             if (ret == (uint32_t)-1)
                 return -1;
             return len - ret;
         }
     case TARGET_SYS_READ:
-        GET_ARG(0);
-        GET_ARG(1);
-        GET_ARG(2);
-        len = arg2;
+        len = ARG(2);
         if (use_gdb_syscalls()) {
             arm_semi_syscall_len = len;
-            gdb_do_syscall(arm_semi_cb, "read,%x,%x,%x", arg0, arg1, len);
+            gdb_do_syscall(arm_semi_cb, "read,%x,%x,%x", ARG(0), ARG(1), len);
             return env->regs[0];
         } else {
-            s = lock_user(VERIFY_WRITE, arg1, len, 0);
-            if (!s) {
+            if (!(s = lock_user(VERIFY_WRITE, ARG(1), len, 0)))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
-            do {
-                ret = set_swi_errno(ts, read(arg0, s, len));
-            } while (ret == -1 && errno == EINTR);
-            unlock_user(s, arg1, len);
+            do
+              ret = set_swi_errno(ts, read(ARG(0), s, len));
+            while (ret == -1 && errno == EINTR);
+            unlock_user(s, ARG(1), len);
             if (ret == (uint32_t)-1)
                 return -1;
             return len - ret;
         }
     case TARGET_SYS_READC:
-       /* XXX: Read from debug console. Not implemented.  */
+       /* XXX: Read from debug cosole. Not implemented.  */
         return 0;
     case TARGET_SYS_ISTTY:
-        GET_ARG(0);
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "isatty,%x", arg0);
+            gdb_do_syscall(arm_semi_cb, "isatty,%x", ARG(0));
             return env->regs[0];
         } else {
-            return isatty(arg0);
+            return isatty(ARG(0));
         }
     case TARGET_SYS_SEEK:
-        GET_ARG(0);
-        GET_ARG(1);
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "lseek,%x,%x,0", arg0, arg1);
+            gdb_do_syscall(arm_semi_cb, "lseek,%x,%x,0", ARG(0), ARG(1));
             return env->regs[0];
         } else {
-            ret = set_swi_errno(ts, lseek(arg0, arg1, SEEK_SET));
+            ret = set_swi_errno(ts, lseek(ARG(0), ARG(1), SEEK_SET));
             if (ret == (uint32_t)-1)
               return -1;
             return 0;
         }
     case TARGET_SYS_FLEN:
-        GET_ARG(0);
         if (use_gdb_syscalls()) {
             gdb_do_syscall(arm_semi_flen_cb, "fstat,%x,%x",
-                           arg0, env->regs[13]-64);
+			   ARG(0), env->regs[13]-64);
             return env->regs[0];
         } else {
             struct stat buf;
-            ret = set_swi_errno(ts, fstat(arg0, &buf));
+            ret = set_swi_errno(ts, fstat(ARG(0), &buf));
             if (ret == (uint32_t)-1)
                 return -1;
             return buf.st_size;
@@ -340,43 +317,35 @@ uint32_t do_arm_semihosting(CPUARMState *env)
         /* XXX: Not implemented.  */
         return -1;
     case TARGET_SYS_REMOVE:
-        GET_ARG(0);
-        GET_ARG(1);
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "unlink,%s", arg0, (int)arg1+1);
+            gdb_do_syscall(arm_semi_cb, "unlink,%s", ARG(0), (int)ARG(1)+1);
             ret = env->regs[0];
         } else {
-            s = lock_user_string(arg0);
-            if (!s) {
+            if (!(s = lock_user_string(ARG(0))))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
             ret =  set_swi_errno(ts, remove(s));
-            unlock_user(s, arg0, 0);
+            unlock_user(s, ARG(0), 0);
         }
         return ret;
     case TARGET_SYS_RENAME:
-        GET_ARG(0);
-        GET_ARG(1);
-        GET_ARG(2);
-        GET_ARG(3);
         if (use_gdb_syscalls()) {
             gdb_do_syscall(arm_semi_cb, "rename,%s,%s",
-                           arg0, (int)arg1+1, arg2, (int)arg3+1);
+                           ARG(0), (int)ARG(1)+1, ARG(2), (int)ARG(3)+1);
             return env->regs[0];
         } else {
             char *s2;
-            s = lock_user_string(arg0);
-            s2 = lock_user_string(arg2);
+            s = lock_user_string(ARG(0));
+            s2 = lock_user_string(ARG(2));
             if (!s || !s2)
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 ret = (uint32_t)-1;
             else
                 ret = set_swi_errno(ts, rename(s, s2));
             if (s2)
-                unlock_user(s2, arg2, 0);
+                unlock_user(s2, ARG(2), 0);
             if (s)
-                unlock_user(s, arg0, 0);
+                unlock_user(s, ARG(0), 0);
             return ret;
         }
     case TARGET_SYS_CLOCK:
@@ -384,19 +353,15 @@ uint32_t do_arm_semihosting(CPUARMState *env)
     case TARGET_SYS_TIME:
         return set_swi_errno(ts, time(NULL));
     case TARGET_SYS_SYSTEM:
-        GET_ARG(0);
-        GET_ARG(1);
         if (use_gdb_syscalls()) {
-            gdb_do_syscall(arm_semi_cb, "system,%s", arg0, (int)arg1+1);
+            gdb_do_syscall(arm_semi_cb, "system,%s", ARG(0), (int)ARG(1)+1);
             return env->regs[0];
         } else {
-            s = lock_user_string(arg0);
-            if (!s) {
+            if (!(s = lock_user_string(ARG(0))))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
             ret = set_swi_errno(ts, system(s));
-            unlock_user(s, arg0, 0);
+            unlock_user(s, ARG(0), 0);
             return ret;
         }
     case TARGET_SYS_ERRNO:
@@ -410,24 +375,22 @@ uint32_t do_arm_semihosting(CPUARMState *env)
             /* Build a command-line from the original argv.
              *
              * The inputs are:
-             *     * arg0, pointer to a buffer of at least the size
-             *               specified in arg1.
-             *     * arg1, size of the buffer pointed to by arg0 in
+             *     * ARG(0), pointer to a buffer of at least the size
+             *               specified in ARG(1).
+             *     * ARG(1), size of the buffer pointed to by ARG(0) in
              *               bytes.
              *
              * The outputs are:
-             *     * arg0, pointer to null-terminated string of the
+             *     * ARG(0), pointer to null-terminated string of the
              *               command line.
-             *     * arg1, length of the string pointed to by arg0.
+             *     * ARG(1), length of the string pointed to by ARG(0).
              */
 
             char *output_buffer;
-            size_t input_size;
+            size_t input_size = ARG(1);
             size_t output_size;
             int status = 0;
-            GET_ARG(0);
-            GET_ARG(1);
-            input_size = arg1;
+
             /* Compute the size of the output string.  */
 #if !defined(CONFIG_USER_ONLY)
             output_size = strlen(ts->boot_info->kernel_filename)
@@ -451,13 +414,10 @@ uint32_t do_arm_semihosting(CPUARMState *env)
             }
 
             /* Adjust the command-line length.  */
-            if (SET_ARG(1, output_size - 1)) {
-                /* Couldn't write back to argument block */
-                return -1;
-            }
+            SET_ARG(1, output_size - 1);
 
             /* Lock the buffer on the ARM side.  */
-            output_buffer = lock_user(VERIFY_WRITE, arg0, output_size, 0);
+            output_buffer = lock_user(VERIFY_WRITE, ARG(0), output_size, 0);
             if (!output_buffer) {
                 return -1;
             }
@@ -489,7 +449,7 @@ uint32_t do_arm_semihosting(CPUARMState *env)
         out:
 #endif
             /* Unlock the buffer on the ARM side.  */
-            unlock_user(output_buffer, arg0, output_size);
+            unlock_user(output_buffer, ARG(0), output_size);
 
             return status;
         }
@@ -497,7 +457,6 @@ uint32_t do_arm_semihosting(CPUARMState *env)
         {
             uint32_t *ptr;
             uint32_t limit;
-            GET_ARG(0);
 
 #ifdef CONFIG_USER_ONLY
             /* Some C libraries assume the heap immediately follows .bss, so
@@ -518,29 +477,25 @@ uint32_t do_arm_semihosting(CPUARMState *env)
                 ts->heap_limit = limit;
             }
 
-            ptr = lock_user(VERIFY_WRITE, arg0, 16, 0);
-            if (!ptr) {
+            if (!(ptr = lock_user(VERIFY_WRITE, ARG(0), 16, 0)))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
             ptr[0] = tswap32(ts->heap_base);
             ptr[1] = tswap32(ts->heap_limit);
             ptr[2] = tswap32(ts->stack_base);
             ptr[3] = tswap32(0); /* Stack limit.  */
-            unlock_user(ptr, arg0, 16);
+            unlock_user(ptr, ARG(0), 16);
 #else
             limit = ram_size;
-            ptr = lock_user(VERIFY_WRITE, arg0, 16, 0);
-            if (!ptr) {
+            if (!(ptr = lock_user(VERIFY_WRITE, ARG(0), 16, 0)))
                 /* FIXME - should this error code be -TARGET_EFAULT ? */
                 return (uint32_t)-1;
-            }
             /* TODO: Make this use the limit of the loaded application.  */
             ptr[0] = tswap32(limit / 2);
             ptr[1] = tswap32(limit);
             ptr[2] = tswap32(limit); /* Stack base */
             ptr[3] = tswap32(0); /* Stack limit.  */
-            unlock_user(ptr, arg0, 16);
+            unlock_user(ptr, ARG(0), 16);
 #endif
             return 0;
         }

async.c

@@ -26,11 +26,13 @@
 #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)
@@ -117,106 +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);
-}
-
-void aio_flush(AioContext *ctx)
-{
-    while (aio_poll(ctx, true));
-}

audio/Makefile.objs

@@ -1,14 +0,0 @@
-common-obj-y = audio.o noaudio.o wavaudio.o mixeng.o
-common-obj-$(CONFIG_SDL) += sdlaudio.o
-common-obj-$(CONFIG_OSS) += ossaudio.o
-common-obj-$(CONFIG_SPICE) += spiceaudio.o
-common-obj-$(CONFIG_COREAUDIO) += coreaudio.o
-common-obj-$(CONFIG_ALSA) += alsaaudio.o
-common-obj-$(CONFIG_DSOUND) += dsoundaudio.o
-common-obj-$(CONFIG_FMOD) += fmodaudio.o
-common-obj-$(CONFIG_ESD) += esdaudio.o
-common-obj-$(CONFIG_PA) += paaudio.o
-common-obj-$(CONFIG_WINWAVE) += winwaveaudio.o
-common-obj-$(CONFIG_AUDIO_PT_INT) += audio_pt_int.o
-common-obj-$(CONFIG_AUDIO_WIN_INT) += audio_win_int.o
-common-obj-y += wavcapture.o

audio/audio.c

@@ -818,7 +818,6 @@ static int audio_attach_capture (HWVoiceOut *hw)
         sw->active = hw->enabled;
         sw->conv = noop_conv;
         sw->ratio = ((int64_t) hw_cap->info.freq << 32) / sw->info.freq;
-        sw->vol = nominal_volume;
         sw->rate = st_rate_start (sw->info.freq, hw_cap->info.freq);
         if (!sw->rate) {
             dolog ("Could not start rate conversion for `%s'\n", SW_NAME (sw));

audio/audio_template.h

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

audio/winwaveaudio.c

@@ -72,7 +72,7 @@ static void winwave_log_mmresult (MMRESULT mr)
         break;
 
     case MMSYSERR_NOMEM:
-        str = "Unable to allocate or lock memory";
+        str = "Unable to allocate or locl memory";
         break;
 
     case WAVERR_SYNC:

backends/Makefile.objs

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

backends/rng-egd.c

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

backends/rng-random.c

@@ -1,161 +0,0 @@
-/*
- * QEMU Random Number Generator Backend
- *
- * Copyright IBM, Corp. 2012
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include "qemu/rng-random.h"
-#include "qemu/rng.h"
-#include "qerror.h"
-#include "main-loop.h"
-
-struct RndRandom
-{
-    RngBackend parent;
-
-    int fd;
-    char *filename;
-
-    EntropyReceiveFunc *receive_func;
-    void *opaque;
-    size_t size;
-};
-
-/**
- * A simple and incomplete backend to request entropy from /dev/random.
- *
- * This backend exposes an additional "filename" property that can be used to
- * set the filename to use to open the backend.
- */
-
-static void entropy_available(void *opaque)
-{
-    RndRandom *s = RNG_RANDOM(opaque);
-    uint8_t buffer[s->size];
-    ssize_t len;
-
-    len = read(s->fd, buffer, s->size);
-    g_assert(len != -1);
-
-    s->receive_func(s->opaque, buffer, len);
-    s->receive_func = NULL;
-
-    qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
-}
-
-static void rng_random_request_entropy(RngBackend *b, size_t size,
-                                        EntropyReceiveFunc *receive_entropy,
-                                        void *opaque)
-{
-    RndRandom *s = RNG_RANDOM(b);
-
-    if (s->receive_func) {
-        s->receive_func(s->opaque, NULL, 0);
-    }
-
-    s->receive_func = receive_entropy;
-    s->opaque = opaque;
-    s->size = size;
-
-    qemu_set_fd_handler(s->fd, entropy_available, NULL, s);
-}
-
-static void rng_random_opened(RngBackend *b, Error **errp)
-{
-    RndRandom *s = RNG_RANDOM(b);
-
-    if (s->filename == NULL) {
-        error_set(errp, QERR_INVALID_PARAMETER_VALUE,
-                  "filename", "a valid filename");
-    } else {
-        s->fd = open(s->filename, O_RDONLY | O_NONBLOCK);
-
-        if (s->fd == -1) {
-            error_set(errp, QERR_OPEN_FILE_FAILED, s->filename);
-        }
-    }
-}
-
-static char *rng_random_get_filename(Object *obj, Error **errp)
-{
-    RndRandom *s = RNG_RANDOM(obj);
-
-    if (s->filename) {
-        return g_strdup(s->filename);
-    }
-
-    return NULL;
-}
-
-static void rng_random_set_filename(Object *obj, const char *filename,
-                                 Error **errp)
-{
-    RngBackend *b = RNG_BACKEND(obj);
-    RndRandom *s = RNG_RANDOM(obj);
-
-    if (b->opened) {
-        error_set(errp, QERR_PERMISSION_DENIED);
-        return;
-    }
-
-    if (s->filename) {
-        g_free(s->filename);
-    }
-
-    s->filename = g_strdup(filename);
-}
-
-static void rng_random_init(Object *obj)
-{
-    RndRandom *s = RNG_RANDOM(obj);
-
-    object_property_add_str(obj, "filename",
-                            rng_random_get_filename,
-                            rng_random_set_filename,
-                            NULL);
-
-    s->filename = g_strdup("/dev/random");
-}
-
-static void rng_random_finalize(Object *obj)
-{
-    RndRandom *s = RNG_RANDOM(obj);
-
-    qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
-
-    if (s->fd != -1) {
-        close(s->fd);
-    }
-
-    g_free(s->filename);
-}
-
-static void rng_random_class_init(ObjectClass *klass, void *data)
-{
-    RngBackendClass *rbc = RNG_BACKEND_CLASS(klass);
-
-    rbc->request_entropy = rng_random_request_entropy;
-    rbc->opened = rng_random_opened;
-}
-
-static TypeInfo rng_random_info = {
-    .name = TYPE_RNG_RANDOM,
-    .parent = TYPE_RNG_BACKEND,
-    .instance_size = sizeof(RndRandom),
-    .class_init = rng_random_class_init,
-    .instance_init = rng_random_init,
-    .instance_finalize = rng_random_finalize,
-};
-
-static void register_types(void)
-{
-    type_register_static(&rng_random_info);
-}
-
-type_init(register_types);

backends/rng.c

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

balloon.c

@@ -30,7 +30,6 @@
 #include "balloon.h"
 #include "trace.h"
 #include "qmp-commands.h"
-#include "qjson.h"
 
 static QEMUBalloonEvent *balloon_event_fn;
 static QEMUBalloonStatus *balloon_stat_fn;
@@ -81,19 +80,6 @@ static int qemu_balloon_status(BalloonInfo *info)
     return 1;
 }
 
-void qemu_balloon_changed(int64_t actual)
-{
-    QObject *data;
-
-    data = qobject_from_jsonf("{ 'actual': %" PRId64 " }",
-                              actual);
-
-    monitor_protocol_event(QEVENT_BALLOON_CHANGE, data);
-
-    qobject_decref(data);
-}
-
-
 BalloonInfo *qmp_query_balloon(Error **errp)
 {
     BalloonInfo *info;

balloon.h

@@ -24,6 +24,4 @@ int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
 			     QEMUBalloonStatus *stat_func, void *opaque);
 void qemu_remove_balloon_handler(void *opaque);
 
-void qemu_balloon_changed(int64_t actual);
-
 #endif

bitops.h

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

block-migration.c

@@ -423,23 +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;
         }
     }
@@ -447,10 +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,
@@ -461,7 +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);
@@ -478,7 +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)
@@ -524,8 +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) {
@@ -543,24 +536,34 @@ static void blk_mig_cleanup(void)
     }
 }
 
-static void block_migration_cancel(void *opaque)
-{
-    blk_mig_cleanup();
-}
-
-static int block_save_setup(QEMUFile *f, void *opaque)
+static int block_save_live(QEMUFile *f, int stage, void *opaque)
 {
     int ret;
 
-    DPRINTF("Enter save live setup submitted %d transferred %d\n",
-            block_mig_state.submitted, block_mig_state.transferred);
+    DPRINTF("Enter save live stage %d submitted %d transferred %d\n",
+            stage, block_mig_state.submitted, block_mig_state.transferred);
 
-    init_blk_migration(f);
+    if (stage < 0) {
+        blk_mig_cleanup();
+        return 0;
+    }
 
-    /* start track dirty blocks */
-    set_dirty_tracking(1);
+    if (block_mig_state.blk_enable != 1) {
+        /* no need to migrate storage */
+        qemu_put_be64(f, BLK_MIG_FLAG_EOS);
+        return 1;
+    }
 
-    ret = flush_blks(f);
+    if (stage == 1) {
+        init_blk_migration(f);
+
+        /* start track dirty blocks */
+        set_dirty_tracking(1);
+    }
+
+    flush_blks(f);
+
+    ret = qemu_file_get_error(f);
     if (ret) {
         blk_mig_cleanup();
         return ret;
@@ -568,95 +571,56 @@ static int block_save_setup(QEMUFile *f, void *opaque)
 
     blk_mig_reset_dirty_cursor();
 
-    qemu_put_be64(f, BLK_MIG_FLAG_EOS);
-
-    return 0;
-}
-
-static int block_save_iterate(QEMUFile *f, void *opaque)
-{
-    int ret;
-
-    DPRINTF("Enter save live iterate submitted %d transferred %d\n",
-            block_mig_state.submitted, block_mig_state.transferred);
-
-    ret = flush_blks(f);
-    if (ret) {
-        blk_mig_cleanup();
-        return ret;
-    }
-
-    blk_mig_reset_dirty_cursor();
-
-    /* control the rate of transfer */
-    while ((block_mig_state.submitted +
-            block_mig_state.read_done) * BLOCK_SIZE <
-           qemu_file_get_rate_limit(f)) {
-        if (block_mig_state.bulk_completed == 0) {
-            /* first finish the bulk phase */
-            if (blk_mig_save_bulked_block(f) == 0) {
-                /* finished saving bulk on all devices */
-                block_mig_state.bulk_completed = 1;
-            }
-        } else {
-            ret = blk_mig_save_dirty_block(f, 1);
-            if (ret != 0) {
-                /* no more dirty blocks */
-                break;
+    if (stage == 2) {
+        /* control the rate of transfer */
+        while ((block_mig_state.submitted +
+                block_mig_state.read_done) * BLOCK_SIZE <
+               qemu_file_get_rate_limit(f)) {
+            if (block_mig_state.bulk_completed == 0) {
+                /* first finish the bulk phase */
+                if (blk_mig_save_bulked_block(f) == 0) {
+                    /* finished saving bulk on all devices */
+                    block_mig_state.bulk_completed = 1;
+                }
+            } else {
+                if (blk_mig_save_dirty_block(f, 1) == 0) {
+                    /* no more dirty blocks */
+                    break;
+                }
             }
         }
-    }
-    if (ret) {
-        blk_mig_cleanup();
-        return ret;
+
+        flush_blks(f);
+
+        ret = qemu_file_get_error(f);
+        if (ret) {
+            blk_mig_cleanup();
+            return ret;
+        }
     }
 
-    ret = flush_blks(f);
-    if (ret) {
+    if (stage == 3) {
+        /* we know for sure that save bulk is completed and
+           all async read completed */
+        assert(block_mig_state.submitted == 0);
+
+        while (blk_mig_save_dirty_block(f, 0) != 0);
         blk_mig_cleanup();
-        return ret;
+
+        /* report completion */
+        qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
+
+        ret = qemu_file_get_error(f);
+        if (ret) {
+            return ret;
+        }
+
+        DPRINTF("Block migration completed\n");
     }
 
     qemu_put_be64(f, BLK_MIG_FLAG_EOS);
 
-    return is_stage2_completed();
-}
-
-static int block_save_complete(QEMUFile *f, void *opaque)
-{
-    int ret;
-
-    DPRINTF("Enter save live complete submitted %d transferred %d\n",
-            block_mig_state.submitted, block_mig_state.transferred);
-
-    ret = flush_blks(f);
-    if (ret) {
-        blk_mig_cleanup();
-        return ret;
-    }
-
-    blk_mig_reset_dirty_cursor();
-
-    /* we know for sure that save bulk is completed and
-       all async read completed */
-    assert(block_mig_state.submitted == 0);
-
-    do {
-        ret = blk_mig_save_dirty_block(f, 0);
-    } while (ret == 0);
-
-    blk_mig_cleanup();
-    if (ret) {
-        return ret;
-    }
-    /* report completion */
-    qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
-
-    DPRINTF("Block migration completed\n");
-
-    qemu_put_be64(f, BLK_MIG_FLAG_EOS);
-
-    return 0;
+    return ((stage == 2) && is_stage2_completed());
 }
 
 static int block_load(QEMUFile *f, void *opaque, int version_id)
@@ -736,35 +700,20 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
     return 0;
 }
 
-static void block_set_params(const MigrationParams *params, void *opaque)
+static void block_set_params(int blk_enable, int shared_base, void *opaque)
 {
-    block_mig_state.blk_enable = params->blk;
-    block_mig_state.shared_base = params->shared;
+    block_mig_state.blk_enable = blk_enable;
+    block_mig_state.shared_base = shared_base;
 
     /* shared base means that blk_enable = 1 */
-    block_mig_state.blk_enable |= params->shared;
+    block_mig_state.blk_enable |= shared_base;
 }
 
-static bool block_is_active(void *opaque)
-{
-    return block_mig_state.blk_enable == 1;
-}
-
-SaveVMHandlers savevm_block_handlers = {
-    .set_params = block_set_params,
-    .save_live_setup = block_save_setup,
-    .save_live_iterate = block_save_iterate,
-    .save_live_complete = block_save_complete,
-    .load_state = block_load,
-    .cancel = block_migration_cancel,
-    .is_active = block_is_active,
-};
-
 void blk_mig_init(void)
 {
     QSIMPLEQ_INIT(&block_mig_state.bmds_list);
     QSIMPLEQ_INIT(&block_mig_state.blk_list);
 
-    register_savevm_live(NULL, "block", 0, 1, &savevm_block_handlers,
-                         &block_mig_state);
+    register_savevm_live(NULL, "block", 0, 1, block_set_params,
+                         block_save_live, NULL, block_load, &block_mig_state);
 }

block.h

@@ -6,11 +6,9 @@
 #include "qemu-option.h"
 #include "qemu-coroutine.h"
 #include "qobject.h"
-#include "qapi-types.h"
 
 /* block.c */
 typedef struct BlockDriver BlockDriver;
-typedef struct BlockJob BlockJob;
 
 typedef struct BlockDriverInfo {
     /* in bytes, 0 if irrelevant */
@@ -81,8 +79,6 @@ typedef struct BlockDevOps {
 #define BDRV_O_NO_FLUSH    0x0200 /* disable flushing on this disk */
 #define BDRV_O_COPY_ON_READ 0x0400 /* copy read backing sectors into image */
 #define BDRV_O_INCOMING    0x0800  /* consistency hint for incoming migration */
-#define BDRV_O_CHECK       0x1000  /* open solely for consistency check */
-#define BDRV_O_ALLOW_RDWR  0x2000  /* allow reopen to change from r/o to r/w */
 
 #define BDRV_O_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH)
 
@@ -91,23 +87,21 @@ typedef struct BlockDevOps {
 #define BDRV_SECTOR_MASK   ~(BDRV_SECTOR_SIZE - 1)
 
 typedef enum {
-    BDRV_ACTION_REPORT, BDRV_ACTION_IGNORE, BDRV_ACTION_STOP
+    BLOCK_ERR_REPORT, BLOCK_ERR_IGNORE, BLOCK_ERR_STOP_ENOSPC,
+    BLOCK_ERR_STOP_ANY
 } BlockErrorAction;
 
-typedef QSIMPLEQ_HEAD(BlockReopenQueue, BlockReopenQueueEntry) BlockReopenQueue;
-
-typedef struct BDRVReopenState {
-    BlockDriverState *bs;
-    int flags;
-    void *opaque;
-} BDRVReopenState;
-
+typedef enum {
+    BDRV_ACTION_REPORT, BDRV_ACTION_IGNORE, BDRV_ACTION_STOP
+} BlockQMPEventAction;
 
 void bdrv_iostatus_enable(BlockDriverState *bs);
 void bdrv_iostatus_reset(BlockDriverState *bs);
 void bdrv_iostatus_disable(BlockDriverState *bs);
 bool bdrv_iostatus_is_enabled(const BlockDriverState *bs);
 void bdrv_iostatus_set_err(BlockDriverState *bs, int error);
+void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
+                               BlockQMPEventAction action, int is_read);
 void bdrv_info_print(Monitor *mon, const QObject *data);
 void bdrv_info(Monitor *mon, QObject **ret_data);
 void bdrv_stats_print(Monitor *mon, const QObject *data);
@@ -128,24 +122,13 @@ int bdrv_create(BlockDriver *drv, const char* filename,
 int bdrv_create_file(const char* filename, QEMUOptionParameter *options);
 BlockDriverState *bdrv_new(const char *device_name);
 void bdrv_make_anon(BlockDriverState *bs);
-void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old);
 void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top);
 void bdrv_delete(BlockDriverState *bs);
 int bdrv_parse_cache_flags(const char *mode, int *flags);
 int bdrv_file_open(BlockDriverState **pbs, const char *filename, int flags);
-int bdrv_open_backing_file(BlockDriverState *bs);
 int bdrv_open(BlockDriverState *bs, const char *filename, int flags,
               BlockDriver *drv);
-BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
-                                    BlockDriverState *bs, int flags);
-int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp);
-int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp);
-int bdrv_reopen_prepare(BDRVReopenState *reopen_state,
-                        BlockReopenQueue *queue, Error **errp);
-void bdrv_reopen_commit(BDRVReopenState *reopen_state);
-void bdrv_reopen_abort(BDRVReopenState *reopen_state);
 void bdrv_close(BlockDriverState *bs);
-void bdrv_add_close_notifier(BlockDriverState *bs, Notifier *notify);
 int bdrv_attach_dev(BlockDriverState *bs, void *dev);
 void bdrv_attach_dev_nofail(BlockDriverState *bs, void *dev);
 void bdrv_detach_dev(BlockDriverState *bs, void *dev);
@@ -158,8 +141,6 @@ bool bdrv_dev_is_tray_open(BlockDriverState *bs);
 bool bdrv_dev_is_medium_locked(BlockDriverState *bs);
 int bdrv_read(BlockDriverState *bs, int64_t sector_num,
               uint8_t *buf, int nb_sectors);
-int bdrv_read_unthrottled(BlockDriverState *bs, int64_t sector_num,
-                          uint8_t *buf, int nb_sectors);
 int bdrv_write(BlockDriverState *bs, int64_t sector_num,
                const uint8_t *buf, int nb_sectors);
 int bdrv_pread(BlockDriverState *bs, int64_t offset,
@@ -184,44 +165,28 @@ int coroutine_fn bdrv_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
     int nb_sectors);
 int coroutine_fn bdrv_co_is_allocated(BlockDriverState *bs, int64_t sector_num,
     int nb_sectors, int *pnum);
-int coroutine_fn bdrv_co_is_allocated_above(BlockDriverState *top,
-                                            BlockDriverState *base,
-                                            int64_t sector_num,
-                                            int nb_sectors, int *pnum);
 BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
     const char *backing_file);
-int bdrv_get_backing_file_depth(BlockDriverState *bs);
 int bdrv_truncate(BlockDriverState *bs, int64_t offset);
 int64_t bdrv_getlength(BlockDriverState *bs);
 int64_t bdrv_get_allocated_file_size(BlockDriverState *bs);
 void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr);
+void bdrv_guess_geometry(BlockDriverState *bs, int *pcyls, int *pheads, int *psecs);
 int bdrv_commit(BlockDriverState *bs);
 int bdrv_commit_all(void);
 int bdrv_change_backing_file(BlockDriverState *bs,
     const char *backing_file, const char *backing_fmt);
 void bdrv_register(BlockDriver *bdrv);
-int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top,
-                           BlockDriverState *base);
-BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
-                                    BlockDriverState *bs);
-BlockDriverState *bdrv_find_base(BlockDriverState *bs);
 
 
 typedef struct BdrvCheckResult {
     int corruptions;
     int leaks;
     int check_errors;
-    int corruptions_fixed;
-    int leaks_fixed;
     BlockFragInfo bfi;
 } BdrvCheckResult;
 
-typedef enum {
-    BDRV_FIX_LEAKS    = 1,
-    BDRV_FIX_ERRORS   = 2,
-} BdrvCheckMode;
-
-int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix);
+int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res);
 
 /* async block I/O */
 typedef void BlockDriverDirtyHandler(BlockDriverState *bs, int64_t sector,
@@ -279,21 +244,47 @@ int bdrv_has_zero_init(BlockDriverState *bs);
 int bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
                       int *pnum);
 
-void bdrv_set_on_error(BlockDriverState *bs, BlockdevOnError on_read_error,
-                       BlockdevOnError on_write_error);
-BlockdevOnError bdrv_get_on_error(BlockDriverState *bs, bool is_read);
-BlockErrorAction bdrv_get_error_action(BlockDriverState *bs, bool is_read, int error);
-void bdrv_error_action(BlockDriverState *bs, BlockErrorAction action,
-                       bool is_read, int error);
+#define BIOS_ATA_TRANSLATION_AUTO   0
+#define BIOS_ATA_TRANSLATION_NONE   1
+#define BIOS_ATA_TRANSLATION_LBA    2
+#define BIOS_ATA_TRANSLATION_LARGE  3
+#define BIOS_ATA_TRANSLATION_RECHS  4
+
+void bdrv_set_geometry_hint(BlockDriverState *bs,
+                            int cyls, int heads, int secs);
+void bdrv_set_translation_hint(BlockDriverState *bs, int translation);
+void bdrv_get_geometry_hint(BlockDriverState *bs,
+                            int *pcyls, int *pheads, int *psecs);
+typedef enum FDriveType {
+    FDRIVE_DRV_144  = 0x00,   /* 1.44 MB 3"5 drive      */
+    FDRIVE_DRV_288  = 0x01,   /* 2.88 MB 3"5 drive      */
+    FDRIVE_DRV_120  = 0x02,   /* 1.2  MB 5"25 drive     */
+    FDRIVE_DRV_NONE = 0x03,   /* No drive connected     */
+} FDriveType;
+
+typedef enum FDriveRate {
+    FDRIVE_RATE_500K = 0x00,  /* 500 Kbps */
+    FDRIVE_RATE_300K = 0x01,  /* 300 Kbps */
+    FDRIVE_RATE_250K = 0x02,  /* 250 Kbps */
+    FDRIVE_RATE_1M   = 0x03,  /*   1 Mbps */
+} FDriveRate;
+
+void bdrv_get_floppy_geometry_hint(BlockDriverState *bs, int *nb_heads,
+                                   int *max_track, int *last_sect,
+                                   FDriveType drive_in, FDriveType *drive,
+                                   FDriveRate *rate);
+int bdrv_get_translation_hint(BlockDriverState *bs);
+void bdrv_set_on_error(BlockDriverState *bs, BlockErrorAction on_read_error,
+                       BlockErrorAction on_write_error);
+BlockErrorAction bdrv_get_on_error(BlockDriverState *bs, int is_read);
 int bdrv_is_read_only(BlockDriverState *bs);
 int bdrv_is_sg(BlockDriverState *bs);
 int bdrv_enable_write_cache(BlockDriverState *bs);
-void bdrv_set_enable_write_cache(BlockDriverState *bs, bool wce);
 int bdrv_is_inserted(BlockDriverState *bs);
 int bdrv_media_changed(BlockDriverState *bs);
 void bdrv_lock_medium(BlockDriverState *bs, bool locked);
 void bdrv_eject(BlockDriverState *bs, bool eject_flag);
-const char *bdrv_get_format_name(BlockDriverState *bs);
+void bdrv_get_format(BlockDriverState *bs, char *buf, int buf_size);
 BlockDriverState *bdrv_find(const char *name);
 BlockDriverState *bdrv_next(BlockDriverState *bs);
 void bdrv_iterate(void (*it)(void *opaque, BlockDriverState *bs),
@@ -305,7 +296,6 @@ int bdrv_query_missing_keys(void);
 void bdrv_iterate_format(void (*it)(void *opaque, const char *name),
                          void *opaque);
 const char *bdrv_get_device_name(BlockDriverState *bs);
-int bdrv_get_flags(BlockDriverState *bs);
 int bdrv_write_compressed(BlockDriverState *bs, int64_t sector_num,
                           const uint8_t *buf, int nb_sectors);
 int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi);
@@ -315,8 +305,6 @@ 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);
@@ -354,9 +342,8 @@ void *qemu_blockalign(BlockDriverState *bs, size_t size);
 
 void bdrv_set_dirty_tracking(BlockDriverState *bs, int enable);
 int bdrv_get_dirty(BlockDriverState *bs, int64_t sector);
-void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors);
-void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors);
-int64_t bdrv_get_next_dirty(BlockDriverState *bs, int64_t sector);
+void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector,
+                      int nr_sectors);
 int64_t bdrv_get_dirty_count(BlockDriverState *bs);
 
 void bdrv_enable_copy_on_read(BlockDriverState *bs);
@@ -395,7 +382,9 @@ typedef enum {
     BLKDBG_L2_ALLOC_COW_READ,
     BLKDBG_L2_ALLOC_WRITE,
 
+    BLKDBG_READ,
     BLKDBG_READ_AIO,
+    BLKDBG_READ_BACKING,
     BLKDBG_READ_BACKING_AIO,
     BLKDBG_READ_COMPRESSED,
 
@@ -431,4 +420,43 @@ typedef enum {
 #define BLKDBG_EVENT(bs, evt) bdrv_debug_event(bs, evt)
 void bdrv_debug_event(BlockDriverState *bs, BlkDebugEvent event);
 
+
+/* Convenience for block device models */
+
+typedef struct BlockConf {
+    BlockDriverState *bs;
+    uint16_t physical_block_size;
+    uint16_t logical_block_size;
+    uint16_t min_io_size;
+    uint32_t opt_io_size;
+    int32_t bootindex;
+    uint32_t discard_granularity;
+} BlockConf;
+
+static inline unsigned int get_physical_block_exp(BlockConf *conf)
+{
+    unsigned int exp = 0, size;
+
+    for (size = conf->physical_block_size;
+        size > conf->logical_block_size;
+        size >>= 1) {
+        exp++;
+    }
+
+    return exp;
+}
+
+#define DEFINE_BLOCK_PROPERTIES(_state, _conf)                          \
+    DEFINE_PROP_DRIVE("drive", _state, _conf.bs),                       \
+    DEFINE_PROP_BLOCKSIZE("logical_block_size", _state,                 \
+                          _conf.logical_block_size, 512),               \
+    DEFINE_PROP_BLOCKSIZE("physical_block_size", _state,                \
+                          _conf.physical_block_size, 512),              \
+    DEFINE_PROP_UINT16("min_io_size", _state, _conf.min_io_size, 0),  \
+    DEFINE_PROP_UINT32("opt_io_size", _state, _conf.opt_io_size, 0),    \
+    DEFINE_PROP_INT32("bootindex", _state, _conf.bootindex, -1),        \
+    DEFINE_PROP_UINT32("discard_granularity", _state, \
+                       _conf.discard_granularity, 0)
+
 #endif
+

block/Makefile.objs

@@ -1,20 +0,0 @@
-block-obj-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
-block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
-block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
-block-obj-y += qed-check.o
-block-obj-y += parallels.o blkdebug.o blkverify.o
-block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
-block-obj-$(CONFIG_POSIX) += raw-posix.o
-block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
-
-ifeq ($(CONFIG_POSIX),y)
-block-obj-y += nbd.o sheepdog.o
-block-obj-$(CONFIG_LIBISCSI) += iscsi.o
-block-obj-$(CONFIG_CURL) += curl.o
-block-obj-$(CONFIG_RBD) += rbd.o
-block-obj-$(CONFIG_GLUSTERFS) += gluster.o
-endif
-
-common-obj-y += stream.o
-common-obj-y += commit.o
-common-obj-y += mirror.o

block/blkdebug.c

@@ -26,11 +26,24 @@
 #include "block_int.h"
 #include "module.h"
 
-typedef struct BDRVBlkdebugState {
+typedef struct BlkdebugVars {
     int state;
-    int new_state;
-    QLIST_HEAD(, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
-    QSIMPLEQ_HEAD(, BlkdebugRule) active_rules;
+
+    /* If inject_errno != 0, an error is injected for requests */
+    int inject_errno;
+
+    /* Decides if all future requests fail (false) or only the next one and
+     * after the next request inject_errno is reset to 0 (true) */
+    bool inject_once;
+
+    /* Decides if aio_readv/writev fails right away (true) or returns an error
+     * return value only in the callback (false) */
+    bool inject_immediately;
+} BlkdebugVars;
+
+typedef struct BDRVBlkdebugState {
+    BlkdebugVars vars;
+    QLIST_HEAD(list, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
 } BDRVBlkdebugState;
 
 typedef struct BlkdebugAIOCB {
@@ -41,7 +54,7 @@ typedef struct BlkdebugAIOCB {
 
 static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb);
 
-static const AIOCBInfo blkdebug_aiocb_info = {
+static AIOPool blkdebug_aio_pool = {
     .aiocb_size = sizeof(BlkdebugAIOCB),
     .cancel     = blkdebug_aio_cancel,
 };
@@ -60,14 +73,12 @@ typedef struct BlkdebugRule {
             int error;
             int immediately;
             int once;
-            int64_t sector;
         } inject;
         struct {
             int new_state;
         } set_state;
     } options;
     QLIST_ENTRY(BlkdebugRule) next;
-    QSIMPLEQ_ENTRY(BlkdebugRule) active_next;
 } BlkdebugRule;
 
 static QemuOptsList inject_error_opts = {
@@ -86,10 +97,6 @@ static QemuOptsList inject_error_opts = {
             .name = "errno",
             .type = QEMU_OPT_NUMBER,
         },
-        {
-            .name = "sector",
-            .type = QEMU_OPT_NUMBER,
-        },
         {
             .name = "once",
             .type = QEMU_OPT_BOOL,
@@ -140,7 +147,9 @@ static const char *event_names[BLKDBG_EVENT_MAX] = {
     [BLKDBG_L2_ALLOC_COW_READ]              = "l2_alloc.cow_read",
     [BLKDBG_L2_ALLOC_WRITE]                 = "l2_alloc.write",
 
+    [BLKDBG_READ]                           = "read",
     [BLKDBG_READ_AIO]                       = "read_aio",
+    [BLKDBG_READ_BACKING]                   = "read_backing",
     [BLKDBG_READ_BACKING_AIO]               = "read_backing_aio",
     [BLKDBG_READ_COMPRESSED]                = "read_compressed",
 
@@ -219,7 +228,6 @@ static int add_rule(QemuOpts *opts, void *opaque)
         rule->options.inject.once  = qemu_opt_get_bool(opts, "once", 0);
         rule->options.inject.immediately =
             qemu_opt_get_bool(opts, "immediately", 0);
-        rule->options.inject.sector = qemu_opt_get_number(opts, "sector", -1);
         break;
 
     case ACTION_SET_STATE:
@@ -294,7 +302,7 @@ static int blkdebug_open(BlockDriverState *bs, const char *filename, int flags)
     filename = c + 1;
 
     /* Set initial state */
-    s->state = 1;
+    s->vars.state = 1;
 
     /* Open the backing file */
     ret = bdrv_file_open(&bs->file, filename, flags);
@@ -320,22 +328,22 @@ static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb)
 }
 
 static BlockDriverAIOCB *inject_error(BlockDriverState *bs,
-    BlockDriverCompletionFunc *cb, void *opaque, BlkdebugRule *rule)
+    BlockDriverCompletionFunc *cb, void *opaque)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    int error = rule->options.inject.error;
+    int error = s->vars.inject_errno;
     struct BlkdebugAIOCB *acb;
     QEMUBH *bh;
 
-    if (rule->options.inject.once) {
-        QSIMPLEQ_INIT(&s->active_rules);
+    if (s->vars.inject_once) {
+        s->vars.inject_errno = 0;
     }
 
-    if (rule->options.inject.immediately) {
+    if (s->vars.inject_immediately) {
         return NULL;
     }
 
-    acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&blkdebug_aio_pool, bs, cb, opaque);
     acb->ret = -error;
 
     bh = qemu_bh_new(error_callback_bh, acb);
@@ -350,21 +358,14 @@ static BlockDriverAIOCB *blkdebug_aio_readv(BlockDriverState *bs,
     BlockDriverCompletionFunc *cb, void *opaque)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugRule *rule = NULL;
 
-    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        if (rule->options.inject.sector == -1 ||
-            (rule->options.inject.sector >= sector_num &&
-             rule->options.inject.sector < sector_num + nb_sectors)) {
-            break;
-        }
+    if (s->vars.inject_errno) {
+        return inject_error(bs, cb, opaque);
     }
 
-    if (rule && rule->options.inject.error) {
-        return inject_error(bs, cb, opaque, rule);
-    }
-
-    return bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    BlockDriverAIOCB *acb =
+        bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    return acb;
 }
 
 static BlockDriverAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
@@ -372,21 +373,14 @@ static BlockDriverAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
     BlockDriverCompletionFunc *cb, void *opaque)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugRule *rule = NULL;
 
-    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        if (rule->options.inject.sector == -1 ||
-            (rule->options.inject.sector >= sector_num &&
-             rule->options.inject.sector < sector_num + nb_sectors)) {
-            break;
-        }
+    if (s->vars.inject_errno) {
+        return inject_error(bs, cb, opaque);
     }
 
-    if (rule && rule->options.inject.error) {
-        return inject_error(bs, cb, opaque, rule);
-    }
-
-    return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    BlockDriverAIOCB *acb =
+        bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
+    return acb;
 }
 
 static void blkdebug_close(BlockDriverState *bs)
@@ -403,52 +397,42 @@ static void blkdebug_close(BlockDriverState *bs)
     }
 }
 
-static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
-    bool injected)
+static void process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
+    BlkdebugVars *old_vars)
 {
     BDRVBlkdebugState *s = bs->opaque;
+    BlkdebugVars *vars = &s->vars;
 
     /* Only process rules for the current state */
-    if (rule->state && rule->state != s->state) {
-        return injected;
+    if (rule->state && rule->state != old_vars->state) {
+        return;
     }
 
     /* Take the action */
     switch (rule->action) {
     case ACTION_INJECT_ERROR:
-        if (!injected) {
-            QSIMPLEQ_INIT(&s->active_rules);
-            injected = true;
-        }
-        QSIMPLEQ_INSERT_HEAD(&s->active_rules, rule, active_next);
+        vars->inject_errno       = rule->options.inject.error;
+        vars->inject_once        = rule->options.inject.once;
+        vars->inject_immediately = rule->options.inject.immediately;
         break;
 
     case ACTION_SET_STATE:
-        s->new_state = rule->options.set_state.new_state;
+        vars->state              = rule->options.set_state.new_state;
         break;
     }
-    return injected;
 }
 
 static void blkdebug_debug_event(BlockDriverState *bs, BlkDebugEvent event)
 {
     BDRVBlkdebugState *s = bs->opaque;
     struct BlkdebugRule *rule;
-    bool injected;
+    BlkdebugVars old_vars = s->vars;
 
     assert((int)event >= 0 && event < BLKDBG_EVENT_MAX);
 
-    injected = false;
-    s->new_state = s->state;
     QLIST_FOREACH(rule, &s->rules[event], next) {
-        injected = process_rule(bs, rule, injected);
+        process_rule(bs, rule, &old_vars);
     }
-    s->state = s->new_state;
-}
-
-static int64_t blkdebug_getlength(BlockDriverState *bs)
-{
-    return bdrv_getlength(bs->file);
 }
 
 static BlockDriver bdrv_blkdebug = {
@@ -459,7 +443,6 @@ static BlockDriver bdrv_blkdebug = {
 
     .bdrv_file_open     = blkdebug_open,
     .bdrv_close         = blkdebug_close,
-    .bdrv_getlength     = blkdebug_getlength,
 
     .bdrv_aio_readv     = blkdebug_aio_readv,
     .bdrv_aio_writev    = blkdebug_aio_writev,

block/blkverify.c

@@ -48,7 +48,7 @@ static void blkverify_aio_cancel(BlockDriverAIOCB *blockacb)
     }
 }
 
-static const AIOCBInfo blkverify_aiocb_info = {
+static AIOPool blkverify_aio_pool = {
     .aiocb_size         = sizeof(BlkverifyAIOCB),
     .cancel             = blkverify_aio_cancel,
 };
@@ -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/commit.c

@@ -1,259 +0,0 @@
-/*
- * Live block commit
- *
- * Copyright Red Hat, Inc. 2012
- *
- * Authors:
- *  Jeff Cody   <jcody@redhat.com>
- *  Based on stream.c by Stefan Hajnoczi
- *
- * This work is licensed under the terms of the GNU LGPL, version 2 or later.
- * See the COPYING.LIB file in the top-level directory.
- *
- */
-
-#include "trace.h"
-#include "block_int.h"
-#include "blockjob.h"
-#include "qemu/ratelimit.h"
-
-enum {
-    /*
-     * Size of data buffer for populating the image file.  This should be large
-     * enough to process multiple clusters in a single call, so that populating
-     * contiguous regions of the image is efficient.
-     */
-    COMMIT_BUFFER_SIZE = 512 * 1024, /* in bytes */
-};
-
-#define SLICE_TIME 100000000ULL /* ns */
-
-typedef struct CommitBlockJob {
-    BlockJob common;
-    RateLimit limit;
-    BlockDriverState *active;
-    BlockDriverState *top;
-    BlockDriverState *base;
-    BlockdevOnError on_error;
-    int base_flags;
-    int orig_overlay_flags;
-} CommitBlockJob;
-
-static int coroutine_fn commit_populate(BlockDriverState *bs,
-                                        BlockDriverState *base,
-                                        int64_t sector_num, int nb_sectors,
-                                        void *buf)
-{
-    int ret = 0;
-
-    ret = bdrv_read(bs, sector_num, buf, nb_sectors);
-    if (ret) {
-        return ret;
-    }
-
-    ret = bdrv_write(base, sector_num, buf, nb_sectors);
-    if (ret) {
-        return ret;
-    }
-
-    return 0;
-}
-
-static void coroutine_fn commit_run(void *opaque)
-{
-    CommitBlockJob *s = opaque;
-    BlockDriverState *active = s->active;
-    BlockDriverState *top = s->top;
-    BlockDriverState *base = s->base;
-    BlockDriverState *overlay_bs = NULL;
-    int64_t sector_num, end;
-    int ret = 0;
-    int n = 0;
-    void *buf;
-    int bytes_written = 0;
-    int64_t base_len;
-
-    ret = s->common.len = bdrv_getlength(top);
-
-
-    if (s->common.len < 0) {
-        goto exit_restore_reopen;
-    }
-
-    ret = base_len = bdrv_getlength(base);
-    if (base_len < 0) {
-        goto exit_restore_reopen;
-    }
-
-    if (base_len < s->common.len) {
-        ret = bdrv_truncate(base, s->common.len);
-        if (ret) {
-            goto exit_restore_reopen;
-        }
-    }
-
-    overlay_bs = bdrv_find_overlay(active, top);
-
-    end = s->common.len >> BDRV_SECTOR_BITS;
-    buf = qemu_blockalign(top, COMMIT_BUFFER_SIZE);
-
-    for (sector_num = 0; sector_num < end; sector_num += n) {
-        uint64_t delay_ns = 0;
-        bool copy;
-
-wait:
-        /* Note that even when no rate limit is applied we need to yield
-         * with no pending I/O here so that qemu_aio_flush() returns.
-         */
-        block_job_sleep_ns(&s->common, rt_clock, delay_ns);
-        if (block_job_is_cancelled(&s->common)) {
-            break;
-        }
-        /* Copy if allocated above the base */
-        ret = bdrv_co_is_allocated_above(top, base, sector_num,
-                                         COMMIT_BUFFER_SIZE / BDRV_SECTOR_SIZE,
-                                         &n);
-        copy = (ret == 1);
-        trace_commit_one_iteration(s, sector_num, n, ret);
-        if (copy) {
-            if (s->common.speed) {
-                delay_ns = ratelimit_calculate_delay(&s->limit, n);
-                if (delay_ns > 0) {
-                    goto wait;
-                }
-            }
-            ret = commit_populate(top, base, sector_num, n, buf);
-            bytes_written += n * BDRV_SECTOR_SIZE;
-        }
-        if (ret < 0) {
-            if (s->on_error == BLOCKDEV_ON_ERROR_STOP ||
-                s->on_error == BLOCKDEV_ON_ERROR_REPORT||
-                (s->on_error == BLOCKDEV_ON_ERROR_ENOSPC && ret == -ENOSPC)) {
-                goto exit_free_buf;
-            } else {
-                n = 0;
-                continue;
-            }
-        }
-        /* Publish progress */
-        s->common.offset += n * BDRV_SECTOR_SIZE;
-    }
-
-    ret = 0;
-
-    if (!block_job_is_cancelled(&s->common) && sector_num == end) {
-        /* success */
-        ret = bdrv_drop_intermediate(active, top, base);
-    }
-
-exit_free_buf:
-    qemu_vfree(buf);
-
-exit_restore_reopen:
-    /* restore base open flags here if appropriate (e.g., change the base back
-     * to r/o). These reopens do not need to be atomic, since we won't abort
-     * even on failure here */
-    if (s->base_flags != bdrv_get_flags(base)) {
-        bdrv_reopen(base, s->base_flags, NULL);
-    }
-    if (s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
-        bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
-    }
-
-    block_job_completed(&s->common, ret);
-}
-
-static void commit_set_speed(BlockJob *job, int64_t speed, Error **errp)
-{
-    CommitBlockJob *s = container_of(job, CommitBlockJob, common);
-
-    if (speed < 0) {
-        error_set(errp, QERR_INVALID_PARAMETER, "speed");
-        return;
-    }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
-}
-
-static BlockJobType commit_job_type = {
-    .instance_size = sizeof(CommitBlockJob),
-    .job_type      = "commit",
-    .set_speed     = commit_set_speed,
-};
-
-void commit_start(BlockDriverState *bs, BlockDriverState *base,
-                  BlockDriverState *top, int64_t speed,
-                  BlockdevOnError on_error, BlockDriverCompletionFunc *cb,
-                  void *opaque, Error **errp)
-{
-    CommitBlockJob *s;
-    BlockReopenQueue *reopen_queue = NULL;
-    int orig_overlay_flags;
-    int orig_base_flags;
-    BlockDriverState *overlay_bs;
-    Error *local_err = NULL;
-
-    if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
-         on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
-        error_set(errp, QERR_INVALID_PARAMETER_COMBINATION);
-        return;
-    }
-
-    /* Once we support top == active layer, remove this check */
-    if (top == bs) {
-        error_setg(errp,
-                   "Top image as the active layer is currently unsupported");
-        return;
-    }
-
-    if (top == base) {
-        error_setg(errp, "Invalid files for merge: top and base are the same");
-        return;
-    }
-
-    overlay_bs = bdrv_find_overlay(bs, top);
-
-    if (overlay_bs == NULL) {
-        error_setg(errp, "Could not find overlay image for %s:", top->filename);
-        return;
-    }
-
-    orig_base_flags    = bdrv_get_flags(base);
-    orig_overlay_flags = bdrv_get_flags(overlay_bs);
-
-    /* convert base & overlay_bs to r/w, if necessary */
-    if (!(orig_base_flags & BDRV_O_RDWR)) {
-        reopen_queue = bdrv_reopen_queue(reopen_queue, base,
-                                         orig_base_flags | BDRV_O_RDWR);
-    }
-    if (!(orig_overlay_flags & BDRV_O_RDWR)) {
-        reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs,
-                                         orig_overlay_flags | BDRV_O_RDWR);
-    }
-    if (reopen_queue) {
-        bdrv_reopen_multiple(reopen_queue, &local_err);
-        if (local_err != NULL) {
-            error_propagate(errp, local_err);
-            return;
-        }
-    }
-
-
-    s = block_job_create(&commit_job_type, bs, speed, cb, opaque, errp);
-    if (!s) {
-        return;
-    }
-
-    s->base   = base;
-    s->top    = top;
-    s->active = bs;
-
-    s->base_flags          = orig_base_flags;
-    s->orig_overlay_flags  = orig_overlay_flags;
-
-    s->on_error = on_error;
-    s->common.co = qemu_coroutine_create(commit_run);
-
-    trace_commit_start(bs, base, top, s, s->common.co, opaque);
-    qemu_coroutine_enter(s->common.co, s);
-}

block/curl.c

@@ -140,8 +140,8 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
             continue;
 
         if ((s->buf_off >= acb->end)) {
-            qemu_iovec_from_buf(acb->qiov, 0, s->orig_buf + acb->start,
-                                acb->end - acb->start);
+            qemu_iovec_from_buffer(acb->qiov, s->orig_buf + acb->start,
+                                   acb->end - acb->start);
             acb->common.cb(acb->common.opaque, 0);
             qemu_aio_release(acb);
             s->acb[i] = NULL;
@@ -176,7 +176,7 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
         {
             char *buf = state->orig_buf + (start - state->buf_start);
 
-            qemu_iovec_from_buf(acb->qiov, 0, buf, len);
+            qemu_iovec_from_buffer(acb->qiov, buf, len);
             acb->common.cb(acb->common.opaque, 0);
 
             return FIND_RET_OK;
@@ -438,7 +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,
 };
@@ -505,7 +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;
@@ -542,7 +542,8 @@ static void curl_close(BlockDriverState *bs)
     }
     if (s->multi)
         curl_multi_cleanup(s->multi);
-    g_free(s->url);
+    if (s->url)
+        free(s->url);
 }
 
 static int64_t curl_getlength(BlockDriverState *bs)

block/gluster.c

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

block/iscsi.c

@@ -35,10 +35,6 @@
 #include <iscsi/iscsi.h>
 #include <iscsi/scsi-lowlevel.h>
 
-#ifdef __linux__
-#include <scsi/sg.h>
-#include <hw/scsi-defs.h>
-#endif
 
 typedef struct IscsiLun {
     struct iscsi_context *iscsi;
@@ -60,11 +56,15 @@ typedef struct IscsiAIOCB {
     int canceled;
     size_t read_size;
     size_t read_offset;
-#ifdef __linux__
-    sg_io_hdr_t *ioh;
-#endif
 } IscsiAIOCB;
 
+struct IscsiTask {
+    IscsiLun *iscsilun;
+    BlockDriverState *bs;
+    int status;
+    int complete;
+};
+
 static void
 iscsi_bh_cb(void *p)
 {
@@ -126,7 +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,
 };
@@ -160,6 +160,12 @@ iscsi_set_events(IscsiLun *iscsilun)
 
     }
 
+    /* If we just added an event, the callback might be delayed
+     * unless we call qemu_notify_event().
+     */
+    if (ev & ~iscsilun->events) {
+        qemu_notify_event();
+    }
     iscsilun->events = ev;
 }
 
@@ -227,7 +233,7 @@ iscsi_aio_writev(BlockDriverState *bs, int64_t sector_num,
     uint64_t lba;
     struct iscsi_data data;
 
-    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;
@@ -241,7 +247,8 @@ iscsi_aio_writev(BlockDriverState *bs, int64_t sector_num,
     /* this will allow us to get rid of 'buf' completely */
     size = nb_sectors * BDRV_SECTOR_SIZE;
     acb->buf = g_malloc(size);
-    qemu_iovec_to_buf(acb->qiov, 0, acb->buf, size);
+    qemu_iovec_to_buffer(acb->qiov, acb->buf);
+
 
     acb->task = malloc(sizeof(struct scsi_task));
     if (acb->task == NULL) {
@@ -255,6 +262,10 @@ 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);
@@ -318,7 +329,7 @@ iscsi_aio_readv(BlockDriverState *bs, int64_t sector_num,
 
     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;
@@ -373,7 +384,7 @@ iscsi_aio_readv(BlockDriverState *bs, int64_t sector_num,
         *(uint16_t *)&acb->task->cdb[7] = htons(num_sectors);
         break;
     }
-
+    
     if (iscsi_scsi_command_async(iscsi, iscsilun->lun, acb->task,
                                  iscsi_aio_read16_cb,
                                  NULL,
@@ -423,7 +434,7 @@ 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;
@@ -476,7 +487,7 @@ 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;
@@ -502,150 +513,6 @@ iscsi_aio_discard(BlockDriverState *bs,
     return &acb->common;
 }
 
-#ifdef __linux__
-static void
-iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
-                     void *command_data, void *opaque)
-{
-    IscsiAIOCB *acb = opaque;
-
-    if (acb->canceled != 0) {
-        return;
-    }
-
-    acb->status = 0;
-    if (status < 0) {
-        error_report("Failed to ioctl(SG_IO) to iSCSI lun. %s",
-                     iscsi_get_error(iscsi));
-        acb->status = -EIO;
-    }
-
-    acb->ioh->driver_status = 0;
-    acb->ioh->host_status   = 0;
-    acb->ioh->resid         = 0;
-
-#define SG_ERR_DRIVER_SENSE    0x08
-
-    if (status == SCSI_STATUS_CHECK_CONDITION && acb->task->datain.size >= 2) {
-        int ss;
-
-        acb->ioh->driver_status |= SG_ERR_DRIVER_SENSE;
-
-        acb->ioh->sb_len_wr = acb->task->datain.size - 2;
-        ss = (acb->ioh->mx_sb_len >= acb->ioh->sb_len_wr) ?
-             acb->ioh->mx_sb_len : acb->ioh->sb_len_wr;
-        memcpy(acb->ioh->sbp, &acb->task->datain.data[2], ss);
-    }
-
-    iscsi_schedule_bh(acb);
-}
-
-static BlockDriverAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
-        unsigned long int req, void *buf,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    IscsiLun *iscsilun = bs->opaque;
-    struct iscsi_context *iscsi = iscsilun->iscsi;
-    struct iscsi_data data;
-    IscsiAIOCB *acb;
-
-    assert(req == SG_IO);
-
-    acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
-
-    acb->iscsilun = iscsilun;
-    acb->canceled    = 0;
-    acb->bh          = NULL;
-    acb->status      = -EINPROGRESS;
-    acb->buf         = NULL;
-    acb->ioh         = buf;
-
-    acb->task = malloc(sizeof(struct scsi_task));
-    if (acb->task == NULL) {
-        error_report("iSCSI: Failed to allocate task for scsi command. %s",
-                     iscsi_get_error(iscsi));
-        qemu_aio_release(acb);
-        return NULL;
-    }
-    memset(acb->task, 0, sizeof(struct scsi_task));
-
-    switch (acb->ioh->dxfer_direction) {
-    case SG_DXFER_TO_DEV:
-        acb->task->xfer_dir = SCSI_XFER_WRITE;
-        break;
-    case SG_DXFER_FROM_DEV:
-        acb->task->xfer_dir = SCSI_XFER_READ;
-        break;
-    default:
-        acb->task->xfer_dir = SCSI_XFER_NONE;
-        break;
-    }
-
-    acb->task->cdb_size = acb->ioh->cmd_len;
-    memcpy(&acb->task->cdb[0], acb->ioh->cmdp, acb->ioh->cmd_len);
-    acb->task->expxferlen = acb->ioh->dxfer_len;
-
-    if (acb->task->xfer_dir == SCSI_XFER_WRITE) {
-        data.data = acb->ioh->dxferp;
-        data.size = acb->ioh->dxfer_len;
-    }
-    if (iscsi_scsi_command_async(iscsi, iscsilun->lun, acb->task,
-                                 iscsi_aio_ioctl_cb,
-                                 (acb->task->xfer_dir == SCSI_XFER_WRITE) ?
-                                     &data : NULL,
-                                 acb) != 0) {
-        scsi_free_scsi_task(acb->task);
-        qemu_aio_release(acb);
-        return NULL;
-    }
-
-    /* tell libiscsi to read straight into the buffer we got from ioctl */
-    if (acb->task->xfer_dir == SCSI_XFER_READ) {
-        scsi_task_add_data_in_buffer(acb->task,
-                                     acb->ioh->dxfer_len,
-                                     acb->ioh->dxferp);
-    }
-
-    iscsi_set_events(iscsilun);
-
-    return &acb->common;
-}
-
-
-static void ioctl_cb(void *opaque, int status)
-{
-    int *p_status = opaque;
-    *p_status = status;
-}
-
-static int iscsi_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
-{
-    IscsiLun *iscsilun = bs->opaque;
-    int status;
-
-    switch (req) {
-    case SG_GET_VERSION_NUM:
-        *(int *)buf = 30000;
-        break;
-    case SG_GET_SCSI_ID:
-        ((struct sg_scsi_id *)buf)->scsi_type = iscsilun->type;
-        break;
-    case SG_IO:
-        status = -EINPROGRESS;
-        iscsi_aio_ioctl(bs, req, buf, ioctl_cb, &status);
-
-        while (status == -EINPROGRESS) {
-            qemu_aio_wait();
-        }
-
-        return 0;
-    default:
-        return -1;
-    }
-    return 0;
-}
-#endif
-
 static int64_t
 iscsi_getlength(BlockDriverState *bs)
 {
@@ -658,6 +525,158 @@ iscsi_getlength(BlockDriverState *bs)
     return len;
 }
 
+static void
+iscsi_readcapacity16_cb(struct iscsi_context *iscsi, int status,
+                        void *command_data, void *opaque)
+{
+    struct IscsiTask *itask = opaque;
+    struct scsi_readcapacity16 *rc16;
+    struct scsi_task *task = command_data;
+
+    if (status != 0) {
+        error_report("iSCSI: Failed to read capacity of iSCSI lun. %s",
+                     iscsi_get_error(iscsi));
+        itask->status   = 1;
+        itask->complete = 1;
+        scsi_free_scsi_task(task);
+        return;
+    }
+
+    rc16 = scsi_datain_unmarshall(task);
+    if (rc16 == NULL) {
+        error_report("iSCSI: Failed to unmarshall readcapacity16 data.");
+        itask->status   = 1;
+        itask->complete = 1;
+        scsi_free_scsi_task(task);
+        return;
+    }
+
+    itask->iscsilun->block_size = rc16->block_length;
+    itask->iscsilun->num_blocks = rc16->returned_lba + 1;
+    itask->bs->total_sectors    = itask->iscsilun->num_blocks *
+                               itask->iscsilun->block_size / BDRV_SECTOR_SIZE ;
+
+    itask->status   = 0;
+    itask->complete = 1;
+    scsi_free_scsi_task(task);
+}
+
+static void
+iscsi_readcapacity10_cb(struct iscsi_context *iscsi, int status,
+                        void *command_data, void *opaque)
+{
+    struct IscsiTask *itask = opaque;
+    struct scsi_readcapacity10 *rc10;
+    struct scsi_task *task = command_data;
+
+    if (status != 0) {
+        error_report("iSCSI: Failed to read capacity of iSCSI lun. %s",
+                     iscsi_get_error(iscsi));
+        itask->status   = 1;
+        itask->complete = 1;
+        scsi_free_scsi_task(task);
+        return;
+    }
+
+    rc10 = scsi_datain_unmarshall(task);
+    if (rc10 == NULL) {
+        error_report("iSCSI: Failed to unmarshall readcapacity10 data.");
+        itask->status   = 1;
+        itask->complete = 1;
+        scsi_free_scsi_task(task);
+        return;
+    }
+
+    itask->iscsilun->block_size = rc10->block_size;
+    itask->iscsilun->num_blocks = rc10->lba + 1;
+    itask->bs->total_sectors    = itask->iscsilun->num_blocks *
+                               itask->iscsilun->block_size / BDRV_SECTOR_SIZE ;
+
+    itask->status   = 0;
+    itask->complete = 1;
+    scsi_free_scsi_task(task);
+}
+
+static void
+iscsi_inquiry_cb(struct iscsi_context *iscsi, int status, void *command_data,
+                 void *opaque)
+{
+    struct IscsiTask *itask = opaque;
+    struct scsi_task *task = command_data;
+    struct scsi_inquiry_standard *inq;
+
+    if (status != 0) {
+        itask->status   = 1;
+        itask->complete = 1;
+        scsi_free_scsi_task(task);
+        return;
+    }
+
+    inq = scsi_datain_unmarshall(task);
+    if (inq == NULL) {
+        error_report("iSCSI: Failed to unmarshall inquiry data.");
+        itask->status   = 1;
+        itask->complete = 1;
+        scsi_free_scsi_task(task);
+        return;
+    }
+
+    itask->iscsilun->type = inq->periperal_device_type;
+
+    scsi_free_scsi_task(task);
+
+    switch (itask->iscsilun->type) {
+    case TYPE_DISK:
+        task = iscsi_readcapacity16_task(iscsi, itask->iscsilun->lun,
+                                   iscsi_readcapacity16_cb, opaque);
+        if (task == NULL) {
+            error_report("iSCSI: failed to send readcapacity16 command.");
+            itask->status   = 1;
+            itask->complete = 1;
+            return;
+        }
+        break;
+    case TYPE_ROM:
+        task = iscsi_readcapacity10_task(iscsi, itask->iscsilun->lun,
+                                   0, 0,
+                                   iscsi_readcapacity10_cb, opaque);
+        if (task == NULL) {
+            error_report("iSCSI: failed to send readcapacity16 command.");
+            itask->status   = 1;
+            itask->complete = 1;
+            return;
+        }
+        break;
+    default:
+        itask->status   = 0;
+        itask->complete = 1;
+    }
+}
+
+static void
+iscsi_connect_cb(struct iscsi_context *iscsi, int status, void *command_data,
+                 void *opaque)
+{
+    struct IscsiTask *itask = opaque;
+    struct scsi_task *task;
+
+    if (status != 0) {
+        itask->status   = 1;
+        itask->complete = 1;
+        return;
+    }
+
+    task = iscsi_inquiry_task(iscsi, itask->iscsilun->lun,
+                              0, 0, 36,
+                              iscsi_inquiry_cb, opaque);
+    if (task == NULL) {
+        error_report("iSCSI: failed to send inquiry command.");
+        itask->status   = 1;
+        itask->complete = 1;
+        return;
+    }
+}
+
 static int parse_chap(struct iscsi_context *iscsi, const char *target)
 {
     QemuOptsList *list;
@@ -739,26 +758,26 @@ static char *parse_initiator_name(const char *target)
     QemuOptsList *list;
     QemuOpts *opts;
     const char *name = NULL;
-    const char *iscsi_name = qemu_get_vm_name();
 
     list = qemu_find_opts("iscsi");
-    if (list) {
-        opts = qemu_opts_find(list, target);
+    if (!list) {
+        return g_strdup("iqn.2008-11.org.linux-kvm");
+    }
+
+    opts = qemu_opts_find(list, target);
+    if (opts == NULL) {
+        opts = QTAILQ_FIRST(&list->head);
         if (!opts) {
-            opts = QTAILQ_FIRST(&list->head);
-        }
-        if (opts) {
-            name = qemu_opt_get(opts, "initiator-name");
+            return g_strdup("iqn.2008-11.org.linux-kvm");
         }
     }
 
-    if (name) {
-        return g_strdup(name);
-    } else {
-        return g_strdup_printf("iqn.2008-11.org.linux-kvm%s%s",
-                               iscsi_name ? ":" : "",
-                               iscsi_name ? iscsi_name : "");
+    name = qemu_opt_get(opts, "initiator-name");
+    if (!name) {
+        return g_strdup("iqn.2008-11.org.linux-kvm");
     }
+
+    return g_strdup(name);
 }
 
 /*
@@ -770,10 +789,7 @@ static int iscsi_open(BlockDriverState *bs, const char *filename, int flags)
     IscsiLun *iscsilun = bs->opaque;
     struct iscsi_context *iscsi = NULL;
     struct iscsi_url *iscsi_url = NULL;
-    struct scsi_task *task = NULL;
-    struct scsi_inquiry_standard *inq = NULL;
-    struct scsi_readcapacity10 *rc10 = NULL;
-    struct scsi_readcapacity16 *rc16 = NULL;
+    struct IscsiTask task;
     char *initiator_name = NULL;
     int ret;
 
@@ -786,9 +802,10 @@ static int iscsi_open(BlockDriverState *bs, const char *filename, int flags)
 
     iscsi_url = iscsi_parse_full_url(iscsi, filename);
     if (iscsi_url == NULL) {
-        error_report("Failed to parse URL : %s", filename);
+        error_report("Failed to parse URL : %s %s", filename,
+                     iscsi_get_error(iscsi));
         ret = -EINVAL;
-        goto out;
+        goto failed;
     }
 
     memset(iscsilun, 0, sizeof(IscsiLun));
@@ -799,13 +816,13 @@ static int iscsi_open(BlockDriverState *bs, const char *filename, int flags)
     if (iscsi == NULL) {
         error_report("iSCSI: Failed to create iSCSI context.");
         ret = -ENOMEM;
-        goto out;
+        goto failed;
     }
 
     if (iscsi_set_targetname(iscsi, iscsi_url->target)) {
         error_report("iSCSI: Failed to set target name.");
         ret = -EINVAL;
-        goto out;
+        goto failed;
     }
 
     if (iscsi_url->user != NULL) {
@@ -814,7 +831,7 @@ static int iscsi_open(BlockDriverState *bs, const char *filename, int flags)
         if (ret != 0) {
             error_report("Failed to set initiator username and password");
             ret = -EINVAL;
-            goto out;
+            goto failed;
         }
     }
 
@@ -822,13 +839,13 @@ static int iscsi_open(BlockDriverState *bs, const char *filename, int flags)
     if (parse_chap(iscsi, iscsi_url->target) != 0) {
         error_report("iSCSI: Failed to set CHAP user/password");
         ret = -EINVAL;
-        goto out;
+        goto failed;
     }
 
     if (iscsi_set_session_type(iscsi, ISCSI_SESSION_NORMAL) != 0) {
         error_report("iSCSI: Failed to set session type to normal.");
         ret = -EINVAL;
-        goto out;
+        goto failed;
     }
 
     iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
@@ -836,108 +853,49 @@ static int iscsi_open(BlockDriverState *bs, const char *filename, int flags)
     /* check if we got HEADER_DIGEST via the options */
     parse_header_digest(iscsi, iscsi_url->target);
 
-    if (iscsi_full_connect_sync(iscsi, iscsi_url->portal, iscsi_url->lun) != 0) {
-        error_report("iSCSI: Failed to connect to LUN : %s",
-            iscsi_get_error(iscsi));
-        ret = -EINVAL;
-        goto out;
-    }
+    task.iscsilun = iscsilun;
+    task.status = 0;
+    task.complete = 0;
+    task.bs = bs;
 
     iscsilun->iscsi = iscsi;
     iscsilun->lun   = iscsi_url->lun;
 
-    task = iscsi_inquiry_sync(iscsi, iscsilun->lun, 0, 0, 36);
-
-    if (task == NULL || task->status != SCSI_STATUS_GOOD) {
-        error_report("iSCSI: failed to send inquiry command.");
+    if (iscsi_full_connect_async(iscsi, iscsi_url->portal, iscsi_url->lun,
+                                 iscsi_connect_cb, &task)
+        != 0) {
+        error_report("iSCSI: Failed to start async connect.");
         ret = -EINVAL;
-        goto out;
+        goto failed;
     }
 
-    inq = scsi_datain_unmarshall(task);
-    if (inq == NULL) {
-        error_report("iSCSI: Failed to unmarshall inquiry data.");
+    while (!task.complete) {
+        iscsi_set_events(iscsilun);
+        qemu_aio_wait();
+    }
+    if (task.status != 0) {
+        error_report("iSCSI: Failed to connect to LUN : %s",
+                     iscsi_get_error(iscsi));
         ret = -EINVAL;
-        goto out;
+        goto failed;
     }
 
-    iscsilun->type = inq->periperal_device_type;
-
-    scsi_free_scsi_task(task);
-
-    switch (iscsilun->type) {
-    case TYPE_DISK:
-        task = iscsi_readcapacity16_sync(iscsi, iscsilun->lun);
-        if (task == NULL || task->status != SCSI_STATUS_GOOD) {
-            error_report("iSCSI: failed to send readcapacity16 command.");
-            ret = -EINVAL;
-            goto out;
-        }
-        rc16 = scsi_datain_unmarshall(task);
-        if (rc16 == NULL) {
-            error_report("iSCSI: Failed to unmarshall readcapacity16 data.");
-            ret = -EINVAL;
-            goto out;
-        }
-        iscsilun->block_size = rc16->block_length;
-        iscsilun->num_blocks = rc16->returned_lba + 1;
-        break;
-    case TYPE_ROM:
-        task = iscsi_readcapacity10_sync(iscsi, iscsilun->lun, 0, 0);
-        if (task == NULL || task->status != SCSI_STATUS_GOOD) {
-            error_report("iSCSI: failed to send readcapacity10 command.");
-            ret = -EINVAL;
-            goto out;
-        }
-        rc10 = scsi_datain_unmarshall(task);
-        if (rc10 == NULL) {
-            error_report("iSCSI: Failed to unmarshall readcapacity10 data.");
-            ret = -EINVAL;
-            goto out;
-        }
-        iscsilun->block_size = rc10->block_size;
-        if (rc10->lba == 0) {
-            /* blank disk loaded */
-            iscsilun->num_blocks = 0;
-        } else {
-            iscsilun->num_blocks = rc10->lba + 1;
-        }
-        break;
-    default:
-        break;
+    if (iscsi_url != NULL) {
+        iscsi_destroy_url(iscsi_url);
     }
+    return 0;
 
-    bs->total_sectors    = iscsilun->num_blocks *
-                           iscsilun->block_size / BDRV_SECTOR_SIZE ;
-
-    /* Medium changer or tape. We dont have any emulation for this so this must
-     * be sg ioctl compatible. We force it to be sg, otherwise qemu will try
-     * to read from the device to guess the image format.
-     */
-    if (iscsilun->type == TYPE_MEDIUM_CHANGER ||
-        iscsilun->type == TYPE_TAPE) {
-        bs->sg = 1;
-    }
-
-    ret = 0;
-
-out:
+failed:
     if (initiator_name != NULL) {
         g_free(initiator_name);
     }
     if (iscsi_url != NULL) {
         iscsi_destroy_url(iscsi_url);
     }
-    if (task != NULL) {
-        scsi_free_scsi_task(task);
-    }
-
-    if (ret) {
-        if (iscsi != NULL) {
-            iscsi_destroy_context(iscsi);
-        }
-        memset(iscsilun, 0, sizeof(IscsiLun));
+    if (iscsi != NULL) {
+        iscsi_destroy_context(iscsi);
     }
+    memset(iscsilun, 0, sizeof(IscsiLun));
     return ret;
 }
 
@@ -951,11 +909,6 @@ static void iscsi_close(BlockDriverState *bs)
     memset(iscsilun, 0, sizeof(IscsiLun));
 }
 
-static int iscsi_has_zero_init(BlockDriverState *bs)
-{
-    return 0;
-}
-
 static BlockDriver bdrv_iscsi = {
     .format_name     = "iscsi",
     .protocol_name   = "iscsi",
@@ -971,12 +924,6 @@ static BlockDriver bdrv_iscsi = {
     .bdrv_aio_flush  = iscsi_aio_flush,
 
     .bdrv_aio_discard = iscsi_aio_discard,
-    .bdrv_has_zero_init = iscsi_has_zero_init,
-
-#ifdef __linux__
-    .bdrv_ioctl       = iscsi_ioctl,
-    .bdrv_aio_ioctl   = iscsi_aio_ioctl,
-#endif
 };
 
 static void iscsi_block_init(void)

block/mirror.c

@@ -1,322 +0,0 @@
-/*
- * Image mirroring
- *
- * Copyright Red Hat, Inc. 2012
- *
- * Authors:
- *  Paolo Bonzini  <pbonzini@redhat.com>
- *
- * This work is licensed under the terms of the GNU LGPL, version 2 or later.
- * See the COPYING.LIB file in the top-level directory.
- *
- */
-
-#include "trace.h"
-#include "blockjob.h"
-#include "block_int.h"
-#include "qemu/ratelimit.h"
-
-enum {
-    /*
-     * Size of data buffer for populating the image file.  This should be large
-     * enough to process multiple clusters in a single call, so that populating
-     * contiguous regions of the image is efficient.
-     */
-    BLOCK_SIZE = 512 * BDRV_SECTORS_PER_DIRTY_CHUNK, /* in bytes */
-};
-
-#define SLICE_TIME 100000000ULL /* ns */
-
-typedef struct MirrorBlockJob {
-    BlockJob common;
-    RateLimit limit;
-    BlockDriverState *target;
-    MirrorSyncMode mode;
-    BlockdevOnError on_source_error, on_target_error;
-    bool synced;
-    bool should_complete;
-    int64_t sector_num;
-    uint8_t *buf;
-} MirrorBlockJob;
-
-static BlockErrorAction mirror_error_action(MirrorBlockJob *s, bool read,
-                                            int error)
-{
-    s->synced = false;
-    if (read) {
-        return block_job_error_action(&s->common, s->common.bs,
-                                      s->on_source_error, true, error);
-    } else {
-        return block_job_error_action(&s->common, s->target,
-                                      s->on_target_error, false, error);
-    }
-}
-
-static int coroutine_fn mirror_iteration(MirrorBlockJob *s,
-                                         BlockErrorAction *p_action)
-{
-    BlockDriverState *source = s->common.bs;
-    BlockDriverState *target = s->target;
-    QEMUIOVector qiov;
-    int ret, nb_sectors;
-    int64_t end;
-    struct iovec iov;
-
-    end = s->common.len >> BDRV_SECTOR_BITS;
-    s->sector_num = bdrv_get_next_dirty(source, s->sector_num);
-    nb_sectors = MIN(BDRV_SECTORS_PER_DIRTY_CHUNK, end - s->sector_num);
-    bdrv_reset_dirty(source, s->sector_num, nb_sectors);
-
-    /* Copy the dirty cluster.  */
-    iov.iov_base = s->buf;
-    iov.iov_len  = nb_sectors * 512;
-    qemu_iovec_init_external(&qiov, &iov, 1);
-
-    trace_mirror_one_iteration(s, s->sector_num, nb_sectors);
-    ret = bdrv_co_readv(source, s->sector_num, nb_sectors, &qiov);
-    if (ret < 0) {
-        *p_action = mirror_error_action(s, true, -ret);
-        goto fail;
-    }
-    ret = bdrv_co_writev(target, s->sector_num, nb_sectors, &qiov);
-    if (ret < 0) {
-        *p_action = mirror_error_action(s, false, -ret);
-        s->synced = false;
-        goto fail;
-    }
-    return 0;
-
-fail:
-    /* Try again later.  */
-    bdrv_set_dirty(source, s->sector_num, nb_sectors);
-    return ret;
-}
-
-static void coroutine_fn mirror_run(void *opaque)
-{
-    MirrorBlockJob *s = opaque;
-    BlockDriverState *bs = s->common.bs;
-    int64_t sector_num, end;
-    int ret = 0;
-    int n;
-
-    if (block_job_is_cancelled(&s->common)) {
-        goto immediate_exit;
-    }
-
-    s->common.len = bdrv_getlength(bs);
-    if (s->common.len < 0) {
-        block_job_completed(&s->common, s->common.len);
-        return;
-    }
-
-    end = s->common.len >> BDRV_SECTOR_BITS;
-    s->buf = qemu_blockalign(bs, BLOCK_SIZE);
-
-    if (s->mode != MIRROR_SYNC_MODE_NONE) {
-        /* First part, loop on the sectors and initialize the dirty bitmap.  */
-        BlockDriverState *base;
-        base = s->mode == MIRROR_SYNC_MODE_FULL ? NULL : bs->backing_hd;
-        for (sector_num = 0; sector_num < end; ) {
-            int64_t next = (sector_num | (BDRV_SECTORS_PER_DIRTY_CHUNK - 1)) + 1;
-            ret = bdrv_co_is_allocated_above(bs, base,
-                                             sector_num, next - sector_num, &n);
-
-            if (ret < 0) {
-                goto immediate_exit;
-            }
-
-            assert(n > 0);
-            if (ret == 1) {
-                bdrv_set_dirty(bs, sector_num, n);
-                sector_num = next;
-            } else {
-                sector_num += n;
-            }
-        }
-    }
-
-    s->sector_num = -1;
-    for (;;) {
-        uint64_t delay_ns;
-        int64_t cnt;
-        bool should_complete;
-
-        cnt = bdrv_get_dirty_count(bs);
-        if (cnt != 0) {
-            BlockErrorAction action = BDRV_ACTION_REPORT;
-            ret = mirror_iteration(s, &action);
-            if (ret < 0 && action == BDRV_ACTION_REPORT) {
-                goto immediate_exit;
-            }
-            cnt = bdrv_get_dirty_count(bs);
-        }
-
-        should_complete = false;
-        if (cnt == 0) {
-            trace_mirror_before_flush(s);
-            ret = bdrv_flush(s->target);
-            if (ret < 0) {
-                if (mirror_error_action(s, false, -ret) == BDRV_ACTION_REPORT) {
-                    goto immediate_exit;
-                }
-            } else {
-                /* We're out of the streaming phase.  From now on, if the job
-                 * is cancelled we will actually complete all pending I/O and
-                 * report completion.  This way, block-job-cancel will leave
-                 * the target in a consistent state.
-                 */
-                s->common.offset = end * BDRV_SECTOR_SIZE;
-                if (!s->synced) {
-                    block_job_ready(&s->common);
-                    s->synced = true;
-                }
-
-                should_complete = s->should_complete ||
-                    block_job_is_cancelled(&s->common);
-                cnt = bdrv_get_dirty_count(bs);
-            }
-        }
-
-        if (cnt == 0 && should_complete) {
-            /* The dirty bitmap is not updated while operations are pending.
-             * If we're about to exit, wait for pending operations before
-             * calling bdrv_get_dirty_count(bs), or we may exit while the
-             * source has dirty data to copy!
-             *
-             * Note that I/O can be submitted by the guest while
-             * mirror_populate runs.
-             */
-            trace_mirror_before_drain(s, cnt);
-            bdrv_drain_all();
-            cnt = bdrv_get_dirty_count(bs);
-        }
-
-        ret = 0;
-        trace_mirror_before_sleep(s, cnt, s->synced);
-        if (!s->synced) {
-            /* Publish progress */
-            s->common.offset = end * BDRV_SECTOR_SIZE - cnt * BLOCK_SIZE;
-
-            if (s->common.speed) {
-                delay_ns = ratelimit_calculate_delay(&s->limit, BDRV_SECTORS_PER_DIRTY_CHUNK);
-            } else {
-                delay_ns = 0;
-            }
-
-            /* Note that even when no rate limit is applied we need to yield
-             * with no pending I/O here so that qemu_aio_flush() returns.
-             */
-            block_job_sleep_ns(&s->common, rt_clock, delay_ns);
-            if (block_job_is_cancelled(&s->common)) {
-                break;
-            }
-        } else if (!should_complete) {
-            delay_ns = (cnt == 0 ? SLICE_TIME : 0);
-            block_job_sleep_ns(&s->common, rt_clock, delay_ns);
-        } else if (cnt == 0) {
-            /* The two disks are in sync.  Exit and report successful
-             * completion.
-             */
-            assert(QLIST_EMPTY(&bs->tracked_requests));
-            s->common.cancelled = false;
-            break;
-        }
-    }
-
-immediate_exit:
-    g_free(s->buf);
-    bdrv_set_dirty_tracking(bs, false);
-    bdrv_iostatus_disable(s->target);
-    if (s->should_complete && ret == 0) {
-        if (bdrv_get_flags(s->target) != bdrv_get_flags(s->common.bs)) {
-            bdrv_reopen(s->target, bdrv_get_flags(s->common.bs), NULL);
-        }
-        bdrv_swap(s->target, s->common.bs);
-    }
-    bdrv_close(s->target);
-    bdrv_delete(s->target);
-    block_job_completed(&s->common, ret);
-}
-
-static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
-{
-    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-
-    if (speed < 0) {
-        error_set(errp, QERR_INVALID_PARAMETER, "speed");
-        return;
-    }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
-}
-
-static void mirror_iostatus_reset(BlockJob *job)
-{
-    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-
-    bdrv_iostatus_reset(s->target);
-}
-
-static void mirror_complete(BlockJob *job, Error **errp)
-{
-    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
-    int ret;
-
-    ret = bdrv_open_backing_file(s->target);
-    if (ret < 0) {
-        char backing_filename[PATH_MAX];
-        bdrv_get_full_backing_filename(s->target, backing_filename,
-                                       sizeof(backing_filename));
-        error_set(errp, QERR_OPEN_FILE_FAILED, backing_filename);
-        return;
-    }
-    if (!s->synced) {
-        error_set(errp, QERR_BLOCK_JOB_NOT_READY, job->bs->device_name);
-        return;
-    }
-
-    s->should_complete = true;
-    block_job_resume(job);
-}
-
-static BlockJobType mirror_job_type = {
-    .instance_size = sizeof(MirrorBlockJob),
-    .job_type      = "mirror",
-    .set_speed     = mirror_set_speed,
-    .iostatus_reset= mirror_iostatus_reset,
-    .complete      = mirror_complete,
-};
-
-void mirror_start(BlockDriverState *bs, BlockDriverState *target,
-                  int64_t speed, MirrorSyncMode mode,
-                  BlockdevOnError on_source_error,
-                  BlockdevOnError on_target_error,
-                  BlockDriverCompletionFunc *cb,
-                  void *opaque, Error **errp)
-{
-    MirrorBlockJob *s;
-
-    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
-         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
-        !bdrv_iostatus_is_enabled(bs)) {
-        error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
-        return;
-    }
-
-    s = block_job_create(&mirror_job_type, bs, speed, cb, opaque, errp);
-    if (!s) {
-        return;
-    }
-
-    s->on_source_error = on_source_error;
-    s->on_target_error = on_target_error;
-    s->target = target;
-    s->mode = mode;
-    bdrv_set_dirty_tracking(bs, true);
-    bdrv_set_enable_write_cache(s->target, true);
-    bdrv_set_on_error(s->target, on_target_error, on_target_error);
-    bdrv_iostatus_enable(s->target);
-    s->common.co = qemu_coroutine_create(mirror_run);
-    trace_mirror_start(bs, s, s->common.co, opaque);
-    qemu_coroutine_enter(s->common.co, s);
-}

block/nbd.c

@@ -28,7 +28,6 @@
 
 #include "qemu-common.h"
 #include "nbd.h"
-#include "uri.h"
 #include "block_int.h"
 #include "module.h"
 #include "qemu_socket.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);
     }
 
@@ -261,7 +196,7 @@ static void nbd_restart_write(void *opaque)
 }
 
 static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
-                               QEMUIOVector *qiov, int offset)
+                               struct iovec *iov, int offset)
 {
     int rc, ret;
 
@@ -270,9 +205,8 @@ static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
     qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write,
                             nbd_have_request, s);
     rc = nbd_send_request(s->sock, request);
-    if (rc >= 0 && qiov) {
-        ret = qemu_co_sendv(s->sock, qiov->iov, qiov->niov,
-                            offset, request->len);
+    if (rc >= 0 && iov) {
+        ret = qemu_co_sendv(s->sock, iov, request->len, offset);
         if (ret != request->len) {
             return -EIO;
         }
@@ -286,7 +220,7 @@ static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
 
 static void nbd_co_receive_reply(BDRVNBDState *s, struct nbd_request *request,
                                  struct nbd_reply *reply,
-                                 QEMUIOVector *qiov, int offset)
+                                 struct iovec *iov, int offset)
 {
     int ret;
 
@@ -297,9 +231,8 @@ static void nbd_co_receive_reply(BDRVNBDState *s, struct nbd_request *request,
     if (reply->handle != request->handle) {
         reply->error = EIO;
     } else {
-        if (qiov && reply->error == 0) {
-            ret = qemu_co_recvv(s->sock, qiov->iov, qiov->niov,
-                                offset, request->len);
+        if (iov && reply->error == 0) {
+            ret = qemu_co_recvv(s->sock, iov, request->len, offset);
             if (ret != request->len) {
                 reply->error = EIO;
             }
@@ -327,7 +260,7 @@ 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);
@@ -385,7 +318,7 @@ 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;
     }
@@ -416,7 +349,7 @@ static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
     if (ret < 0) {
         reply.error = -ret;
     } else {
-        nbd_co_receive_reply(s, &request, &reply, qiov, offset);
+        nbd_co_receive_reply(s, &request, &reply, qiov->iov, offset);
     }
     nbd_coroutine_end(s, &request);
     return -reply.error;
@@ -441,7 +374,7 @@ static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
     request.len = nb_sectors * 512;
 
     nbd_coroutine_start(s, &request);
-    ret = nbd_co_send_request(s, &request, qiov, offset);
+    ret = nbd_co_send_request(s, &request, qiov->iov, offset);
     if (ret < 0) {
         reply.error = -ret;
     } else {
@@ -563,48 +496,20 @@ static int64_t nbd_getlength(BlockDriverState *bs)
 
 static BlockDriver bdrv_nbd = {
     .format_name         = "nbd",
+    .instance_size       = sizeof(BDRVNBDState),
+    .bdrv_file_open      = nbd_open,
+    .bdrv_co_readv       = nbd_co_readv,
+    .bdrv_co_writev      = nbd_co_writev,
+    .bdrv_close          = nbd_close,
+    .bdrv_co_flush_to_os = nbd_co_flush,
+    .bdrv_co_discard     = nbd_co_discard,
+    .bdrv_getlength      = nbd_getlength,
     .protocol_name       = "nbd",
-    .instance_size       = sizeof(BDRVNBDState),
-    .bdrv_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/qcow.c

@@ -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;
@@ -549,7 +540,7 @@ done:
     qemu_co_mutex_unlock(&s->lock);
 
     if (qiov->niov > 1) {
-        qemu_iovec_from_buf(qiov, 0, orig_buf, qiov->size);
+        qemu_iovec_from_buffer(qiov, orig_buf, qiov->size);
         qemu_vfree(orig_buf);
     }
 
@@ -578,7 +569,7 @@ static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
 
     if (qiov->niov > 1) {
         buf = orig_buf = qemu_blockalign(bs, qiov->size);
-        qemu_iovec_to_buf(qiov, 0, buf, qiov->size);
+        qemu_iovec_to_buffer(qiov, buf);
     } else {
         orig_buf = NULL;
         buf = (uint8_t *)qiov->iov->iov_base;
@@ -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

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

block/qcow2-cluster.c

@@ -540,6 +540,7 @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
         if (l2_offset) {
             qcow2_free_clusters(bs, l2_offset, s->l2_size * sizeof(uint64_t));
         }
+        l2_offset = s->l1_table[l1_index] & L1E_OFFSET_MASK;
     }
 
     /* find the cluster offset for the given disk offset */
@@ -642,10 +643,11 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
     }
 
     if (m->nb_available & (s->cluster_sectors - 1)) {
+        uint64_t end = m->nb_available & ~(uint64_t)(s->cluster_sectors - 1);
         cow = true;
         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));
+        ret = copy_sectors(bs, start_sect + end, cluster_offset + (end << 9),
+                m->nb_available - end, s->cluster_sectors);
         qemu_co_mutex_lock(&s->lock);
         if (ret < 0)
             goto err;
@@ -662,10 +664,7 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
         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);
-    }
+    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;
@@ -950,16 +949,8 @@ again:
 
         /* save info needed for meta data update */
         if (nb_clusters > 0) {
-            /*
-             * requested_sectors: Number of sectors from the start of the first
-             * newly allocated cluster to the end of the (possibly shortened
-             * before) write request.
-             *
-             * avail_sectors: Number of sectors from the start of the first
-             * newly allocated to the end of the last newly allocated cluster.
-             */
             int requested_sectors = n_end - keep_clusters * s->cluster_sectors;
-            int avail_sectors = nb_clusters
+            int avail_sectors = (keep_clusters + nb_clusters)
                                 << (s->cluster_bits - BDRV_SECTOR_BITS);
 
             *m = (QCowL2Meta) {

block/qcow2-refcount.c

@@ -301,8 +301,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
     uint64_t last_table_size;
     uint64_t blocks_clusters;
     do {
-        uint64_t table_clusters =
-            size_to_clusters(s, table_size * sizeof(uint64_t));
+        uint64_t table_clusters = size_to_clusters(s, table_size);
         blocks_clusters = 1 +
             ((table_clusters + refcount_block_clusters - 1)
             / refcount_block_clusters);
@@ -628,11 +627,10 @@ int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size)
     BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_ALLOC_BYTES);
     assert(size > 0 && size <= s->cluster_size);
     if (s->free_byte_offset == 0) {
-        offset = qcow2_alloc_clusters(bs, s->cluster_size);
-        if (offset < 0) {
-            return offset;
+        s->free_byte_offset = qcow2_alloc_clusters(bs, s->cluster_size);
+        if (s->free_byte_offset < 0) {
+            return s->free_byte_offset;
         }
-        s->free_byte_offset = offset;
     }
  redo:
     free_in_cluster = s->cluster_size -
@@ -728,6 +726,13 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
     int64_t old_offset, old_l2_offset;
     int i, j, l1_modified = 0, nb_csectors, refcount;
     int ret;
+    bool old_l2_writethrough, old_refcount_writethrough;
+
+    /* Switch caches to writeback mode during update */
+    old_l2_writethrough =
+        qcow2_cache_set_writethrough(bs, s->l2_table_cache, false);
+    old_refcount_writethrough =
+        qcow2_cache_set_writethrough(bs, s->refcount_block_cache, false);
 
     l2_table = NULL;
     l1_table = NULL;
@@ -851,6 +856,11 @@ fail:
         qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
     }
 
+    /* Enable writethrough cache mode again */
+    qcow2_cache_set_writethrough(bs, s->l2_table_cache, old_l2_writethrough);
+    qcow2_cache_set_writethrough(bs, s->refcount_block_cache,
+        old_refcount_writethrough);
+
     /* Update L1 only if it isn't deleted anyway (addend = -1) */
     if (addend >= 0 && l1_modified) {
         for(i = 0; i < l1_size; i++)
@@ -1112,12 +1122,11 @@ fail:
  * Returns 0 if no errors are found, the number of errors in case the image is
  * detected as corrupted, and -errno when an internal error occurred.
  */
-int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
-                          BdrvCheckMode fix)
+int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res)
 {
     BDRVQcowState *s = bs->opaque;
-    int64_t size, i;
-    int nb_clusters, refcount1, refcount2;
+    int64_t size;
+    int nb_clusters, refcount1, refcount2, i;
     QCowSnapshot *sn;
     uint16_t *refcount_table;
     int ret;
@@ -1161,15 +1170,14 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
 
         /* Refcount blocks are cluster aligned */
         if (offset & (s->cluster_size - 1)) {
-            fprintf(stderr, "ERROR refcount block %" PRId64 " is not "
+            fprintf(stderr, "ERROR refcount block %d is not "
                 "cluster aligned; refcount table entry corrupted\n", i);
             res->corruptions++;
             continue;
         }
 
         if (cluster >= nb_clusters) {
-            fprintf(stderr, "ERROR refcount block %" PRId64
-                    " is outside image\n", i);
+            fprintf(stderr, "ERROR refcount block %d is outside image\n", i);
             res->corruptions++;
             continue;
         }
@@ -1178,8 +1186,7 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
             inc_refcounts(bs, res, refcount_table, nb_clusters,
                 offset, s->cluster_size);
             if (refcount_table[cluster] != 1) {
-                fprintf(stderr, "ERROR refcount block %" PRId64
-                    " refcount=%d\n",
+                fprintf(stderr, "ERROR refcount block %d refcount=%d\n",
                     i, refcount_table[cluster]);
                 res->corruptions++;
             }
@@ -1190,7 +1197,7 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
     for(i = 0; i < nb_clusters; i++) {
         refcount1 = get_refcount(bs, i);
         if (refcount1 < 0) {
-            fprintf(stderr, "Can't get refcount for cluster %" PRId64 ": %s\n",
+            fprintf(stderr, "Can't get refcount for cluster %d: %s\n",
                 i, strerror(-refcount1));
             res->check_errors++;
             continue;
@@ -1198,31 +1205,9 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
 
         refcount2 = refcount_table[i];
         if (refcount1 != refcount2) {
-
-            /* Check if we're allowed to fix the mismatch */
-            int *num_fixed = NULL;
-            if (refcount1 > refcount2 && (fix & BDRV_FIX_LEAKS)) {
-                num_fixed = &res->leaks_fixed;
-            } else if (refcount1 < refcount2 && (fix & BDRV_FIX_ERRORS)) {
-                num_fixed = &res->corruptions_fixed;
-            }
-
-            fprintf(stderr, "%s cluster %" PRId64 " refcount=%d reference=%d\n",
-                   num_fixed != NULL     ? "Repairing" :
-                   refcount1 < refcount2 ? "ERROR" :
-                                           "Leaked",
+            fprintf(stderr, "%s cluster %d refcount=%d reference=%d\n",
+                   refcount1 < refcount2 ? "ERROR" : "Leaked",
                    i, refcount1, refcount2);
-
-            if (num_fixed) {
-                ret = update_refcount(bs, i << s->cluster_bits, 1,
-                                      refcount2 - refcount1);
-                if (ret >= 0) {
-                    (*num_fixed)++;
-                    continue;
-                }
-            }
-
-            /* And if we couldn't, print an error */
             if (refcount1 < refcount2) {
                 res->corruptions++;
             } else {

block/qcow2-snapshot.c

@@ -405,7 +405,7 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
 #ifdef DEBUG_ALLOC
     {
       BdrvCheckResult result = {0};
-      qcow2_check_refcounts(bs, &result, 0);
+      qcow2_check_refcounts(bs, &result);
     }
 #endif
     return 0;
@@ -522,7 +522,7 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
 #ifdef DEBUG_ALLOC
     {
         BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result, 0);
+        qcow2_check_refcounts(bs, &result);
     }
 #endif
     return 0;
@@ -582,7 +582,7 @@ int qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id)
 #ifdef DEBUG_ALLOC
     {
         BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result, 0);
+        qcow2_check_refcounts(bs, &result);
     }
 #endif
     return 0;

block/qcow2.c

@@ -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
@@ -215,82 +214,13 @@ static void report_unsupported_feature(BlockDriverState *bs,
     }
 }
 
-/*
- * Sets the dirty bit and flushes afterwards if necessary.
- *
- * The incompatible_features bit is only set if the image file header was
- * updated successfully.  Therefore it is not required to check the return
- * value of this function.
- */
-static int qcow2_mark_dirty(BlockDriverState *bs)
-{
-    BDRVQcowState *s = bs->opaque;
-    uint64_t val;
-    int ret;
-
-    assert(s->qcow_version >= 3);
-
-    if (s->incompatible_features & QCOW2_INCOMPAT_DIRTY) {
-        return 0; /* already dirty */
-    }
-
-    val = cpu_to_be64(s->incompatible_features | QCOW2_INCOMPAT_DIRTY);
-    ret = bdrv_pwrite(bs->file, offsetof(QCowHeader, incompatible_features),
-                      &val, sizeof(val));
-    if (ret < 0) {
-        return ret;
-    }
-    ret = bdrv_flush(bs->file);
-    if (ret < 0) {
-        return ret;
-    }
-
-    /* Only treat image as dirty if the header was updated successfully */
-    s->incompatible_features |= QCOW2_INCOMPAT_DIRTY;
-    return 0;
-}
-
-/*
- * Clears the dirty bit and flushes before if necessary.  Only call this
- * function when there are no pending requests, it does not guard against
- * concurrent requests dirtying the image.
- */
-static int qcow2_mark_clean(BlockDriverState *bs)
-{
-    BDRVQcowState *s = bs->opaque;
-
-    if (s->incompatible_features & QCOW2_INCOMPAT_DIRTY) {
-        int ret = bdrv_flush(bs);
-        if (ret < 0) {
-            return ret;
-        }
-
-        s->incompatible_features &= ~QCOW2_INCOMPAT_DIRTY;
-        return qcow2_update_header(bs);
-    }
-    return 0;
-}
-
-static int qcow2_check(BlockDriverState *bs, BdrvCheckResult *result,
-                       BdrvCheckMode fix)
-{
-    int ret = qcow2_check_refcounts(bs, result, fix);
-    if (ret < 0) {
-        return ret;
-    }
-
-    if (fix && result->check_errors == 0 && result->corruptions == 0) {
-        return qcow2_mark_clean(bs);
-    }
-    return ret;
-}
-
 static int qcow2_open(BlockDriverState *bs, int flags)
 {
     BDRVQcowState *s = bs->opaque;
     int len, i, ret = 0;
     QCowHeader header;
     uint64_t ext_end;
+    bool writethrough;
 
     ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
     if (ret < 0) {
@@ -358,13 +288,12 @@ static int qcow2_open(BlockDriverState *bs, int flags)
     s->compatible_features      = header.compatible_features;
     s->autoclear_features       = header.autoclear_features;
 
-    if (s->incompatible_features & ~QCOW2_INCOMPAT_MASK) {
+    if (s->incompatible_features != 0) {
         void *feature_table = NULL;
         qcow2_read_extensions(bs, header.header_length, ext_end,
                               &feature_table);
         report_unsupported_feature(bs, feature_table,
-                                   s->incompatible_features &
-                                   ~QCOW2_INCOMPAT_MASK);
+                                   s->incompatible_features);
         ret = -ENOTSUP;
         goto fail;
     }
@@ -430,8 +359,10 @@ static int qcow2_open(BlockDriverState *bs, int flags)
     }
 
     /* alloc L2 table/refcount block cache */
-    s->l2_table_cache = qcow2_cache_create(bs, L2_CACHE_SIZE);
-    s->refcount_block_cache = qcow2_cache_create(bs, REFCOUNT_CACHE_SIZE);
+    writethrough = ((flags & BDRV_O_CACHE_WB) == 0);
+    s->l2_table_cache = qcow2_cache_create(bs, L2_CACHE_SIZE, writethrough);
+    s->refcount_block_cache = qcow2_cache_create(bs, REFCOUNT_CACHE_SIZE,
+        writethrough);
 
     s->cluster_cache = g_malloc(s->cluster_size);
     /* one more sector for decompressed data alignment */
@@ -484,21 +415,10 @@ static int qcow2_open(BlockDriverState *bs, int flags)
     /* Initialise locks */
     qemu_co_mutex_init(&s->lock);
 
-    /* Repair image if dirty */
-    if (!(flags & BDRV_O_CHECK) && !bs->read_only &&
-        (s->incompatible_features & QCOW2_INCOMPAT_DIRTY)) {
-        BdrvCheckResult result = {0};
-
-        ret = qcow2_check(bs, &result, BDRV_FIX_ERRORS);
-        if (ret < 0) {
-            goto fail;
-        }
-    }
-
 #ifdef DEBUG_ALLOC
     {
         BdrvCheckResult result = {0};
-        qcow2_check_refcounts(bs, &result, 0);
+        qcow2_check_refcounts(bs, &result);
     }
 #endif
     return ret;
@@ -559,14 +479,6 @@ static int qcow2_set_key(BlockDriverState *bs, const char *key)
     return 0;
 }
 
-/* We have nothing to do for QCOW2 reopen, stubs just return
- * success */
-static int qcow2_reopen_prepare(BDRVReopenState *state,
-                                BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 static int coroutine_fn qcow2_co_is_allocated(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *pnum)
 {
@@ -599,7 +511,7 @@ int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov,
     else
         n1 = bs->total_sectors - sector_num;
 
-    qemu_iovec_memset(qiov, 512 * n1, 0, 512 * (nb_sectors - n1));
+    qemu_iovec_memset_skip(qiov, 0, 512 * (nb_sectors - n1), 512 * n1);
 
     return n1;
 }
@@ -638,7 +550,7 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
         index_in_cluster = sector_num & (s->cluster_sectors - 1);
 
         qemu_iovec_reset(&hd_qiov);
-        qemu_iovec_concat(&hd_qiov, qiov, bytes_done,
+        qemu_iovec_copy(&hd_qiov, qiov, bytes_done,
             cur_nr_sectors * 512);
 
         switch (ret) {
@@ -660,7 +572,7 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
                 }
             } else {
                 /* Note: in this case, no need to wait */
-                qemu_iovec_memset(&hd_qiov, 0, 0, 512 * cur_nr_sectors);
+                qemu_iovec_memset(&hd_qiov, 0, 512 * cur_nr_sectors);
             }
             break;
 
@@ -669,7 +581,7 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
                 ret = -EIO;
                 goto fail;
             }
-            qemu_iovec_memset(&hd_qiov, 0, 0, 512 * cur_nr_sectors);
+            qemu_iovec_memset(&hd_qiov, 0, 512 * cur_nr_sectors);
             break;
 
         case QCOW2_CLUSTER_COMPRESSED:
@@ -679,7 +591,7 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
                 goto fail;
             }
 
-            qemu_iovec_from_buf(&hd_qiov, 0,
+            qemu_iovec_from_buffer(&hd_qiov,
                 s->cluster_cache + index_in_cluster * 512,
                 512 * cur_nr_sectors);
             break;
@@ -719,8 +631,11 @@ static coroutine_fn int qcow2_co_readv(BlockDriverState *bs, int64_t sector_num,
             if (s->crypt_method) {
                 qcow2_encrypt_sectors(s, sector_num,  cluster_data,
                     cluster_data, cur_nr_sectors, 0, &s->aes_decrypt_key);
-                qemu_iovec_from_buf(qiov, bytes_done,
-                    cluster_data, 512 * cur_nr_sectors);
+                qemu_iovec_reset(&hd_qiov);
+                qemu_iovec_copy(&hd_qiov, qiov, bytes_done,
+                    cur_nr_sectors * 512);
+                qemu_iovec_from_buffer(&hd_qiov, cluster_data,
+                    512 * cur_nr_sectors);
             }
             break;
 
@@ -805,16 +720,11 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
             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);
-        qemu_iovec_concat(&hd_qiov, qiov, bytes_done,
+        qemu_iovec_copy(&hd_qiov, qiov, bytes_done,
             cur_nr_sectors * 512);
 
         if (s->crypt_method) {
@@ -825,7 +735,7 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
 
             assert(hd_qiov.size <=
                    QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size);
-            qemu_iovec_to_buf(&hd_qiov, 0, cluster_data, hd_qiov.size);
+            qemu_iovec_to_buffer(&hd_qiov, cluster_data);
 
             qcow2_encrypt_sectors(s, sector_num, cluster_data,
                 cluster_data, cur_nr_sectors, 1, &s->aes_encrypt_key);
@@ -881,8 +791,6 @@ static void qcow2_close(BlockDriverState *bs)
     qcow2_cache_flush(bs, s->l2_table_cache);
     qcow2_cache_flush(bs, s->refcount_block_cache);
 
-    qcow2_mark_clean(bs);
-
     qcow2_cache_destroy(bs, s->l2_table_cache);
     qcow2_cache_destroy(bs, s->refcount_block_cache);
 
@@ -1047,16 +955,7 @@ int qcow2_update_header(BlockDriverState *bs)
 
     /* Feature table */
     Qcow2Feature features[] = {
-        {
-            .type = QCOW2_FEAT_TYPE_INCOMPATIBLE,
-            .bit  = QCOW2_INCOMPAT_DIRTY_BITNR,
-            .name = "dirty bit",
-        },
-        {
-            .type = QCOW2_FEAT_TYPE_COMPATIBLE,
-            .bit  = QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR,
-            .name = "lazy refcounts",
-        },
+        /* no feature defined yet */
     };
 
     ret = header_ext_add(buf, QCOW2_EXT_MAGIC_FEATURE_TABLE,
@@ -1096,7 +995,6 @@ int qcow2_update_header(BlockDriverState *bs)
             goto fail;
         }
 
-        /* Using strncpy is ok here, since buf is not NUL-terminated. */
         strncpy(buf, bs->backing_file, buflen);
 
         header->backing_file_offset = cpu_to_be64(buf - ((char*) header));
@@ -1240,11 +1138,6 @@ static int qcow2_create2(const char *filename, int64_t total_size,
         header.crypt_method = cpu_to_be32(QCOW_CRYPT_NONE);
     }
 
-    if (flags & BLOCK_FLAG_LAZY_REFCOUNTS) {
-        header.compatible_features |=
-            cpu_to_be64(QCOW2_COMPAT_LAZY_REFCOUNTS);
-    }
-
     ret = bdrv_pwrite(bs, 0, &header, sizeof(header));
     if (ret < 0) {
         goto out;
@@ -1358,8 +1251,6 @@ static int qcow2_create(const char *filename, QEMUOptionParameter *options)
                     options->value.s);
                 return -EINVAL;
             }
-        } else if (!strcmp(options->name, BLOCK_OPT_LAZY_REFCOUNTS)) {
-            flags |= options->value.n ? BLOCK_FLAG_LAZY_REFCOUNTS : 0;
         }
         options++;
     }
@@ -1370,12 +1261,6 @@ static int qcow2_create(const char *filename, QEMUOptionParameter *options)
         return -EINVAL;
     }
 
-    if (version < 3 && (flags & BLOCK_FLAG_LAZY_REFCOUNTS)) {
-        fprintf(stderr, "Lazy refcounts only supported with compatibility "
-                "level 1.1 and above (use compat=1.1 or greater)\n");
-        return -EINVAL;
-    }
-
     return qcow2_create2(filename, sectors, backing_file, backing_fmt, flags,
                          cluster_size, prealloc, options, version);
 }
@@ -1562,12 +1447,10 @@ static coroutine_fn int qcow2_co_flush_to_os(BlockDriverState *bs)
         return ret;
     }
 
-    if (qcow2_need_accurate_refcounts(s)) {
-        ret = qcow2_cache_flush(bs, s->refcount_block_cache);
-        if (ret < 0) {
-            qemu_co_mutex_unlock(&s->lock);
-            return ret;
-        }
+    ret = qcow2_cache_flush(bs, s->refcount_block_cache);
+    if (ret < 0) {
+        qemu_co_mutex_unlock(&s->lock);
+        return ret;
     }
     qemu_co_mutex_unlock(&s->lock);
 
@@ -1587,6 +1470,12 @@ static int qcow2_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     return 0;
 }
 
+
+static int qcow2_check(BlockDriverState *bs, BdrvCheckResult *result)
+{
+    return qcow2_check_refcounts(bs, result);
+}
+
 #if 0
 static void dump_refcounts(BlockDriverState *bs)
 {
@@ -1675,11 +1564,6 @@ static QEMUOptionParameter qcow2_create_options[] = {
         .type = OPT_STRING,
         .help = "Preallocation mode (allowed values: off, metadata)"
     },
-    {
-        .name = BLOCK_OPT_LAZY_REFCOUNTS,
-        .type = OPT_FLAG,
-        .help = "Postpone refcount updates",
-    },
     { NULL }
 };
 
@@ -1689,7 +1573,6 @@ 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

@@ -110,22 +110,6 @@ enum {
     QCOW2_FEAT_TYPE_AUTOCLEAR       = 2,
 };
 
-/* Incompatible feature bits */
-enum {
-    QCOW2_INCOMPAT_DIRTY_BITNR   = 0,
-    QCOW2_INCOMPAT_DIRTY         = 1 << QCOW2_INCOMPAT_DIRTY_BITNR,
-
-    QCOW2_INCOMPAT_MASK          = QCOW2_INCOMPAT_DIRTY,
-};
-
-/* Compatible feature bits */
-enum {
-    QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR = 0,
-    QCOW2_COMPAT_LAZY_REFCOUNTS       = 1 << QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR,
-
-    QCOW2_COMPAT_FEAT_MASK            = QCOW2_COMPAT_LAZY_REFCOUNTS,
-};
-
 typedef struct Qcow2Feature {
     uint8_t type;
     uint8_t bit;
@@ -253,11 +237,6 @@ static inline int qcow2_get_cluster_type(uint64_t l2_entry)
     }
 }
 
-/* Check whether refcounts are eager or lazy */
-static inline bool qcow2_need_accurate_refcounts(BDRVQcowState *s)
-{
-    return !(s->incompatible_features & QCOW2_INCOMPAT_DIRTY);
-}
 
 // FIXME Need qcow2_ prefix to global functions
 
@@ -282,8 +261,7 @@ void qcow2_free_any_clusters(BlockDriverState *bs,
 int qcow2_update_snapshot_refcount(BlockDriverState *bs,
     int64_t l1_table_offset, int l1_size, int addend);
 
-int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
-                          BdrvCheckMode fix);
+int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res);
 
 /* qcow2-cluster.c functions */
 int qcow2_grow_l1_table(BlockDriverState *bs, int min_size, bool exact_size);
@@ -318,8 +296,11 @@ void qcow2_free_snapshots(BlockDriverState *bs);
 int qcow2_read_snapshots(BlockDriverState *bs);
 
 /* qcow2-cache.c functions */
-Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables);
+Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables,
+    bool writethrough);
 int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c);
+bool qcow2_cache_set_writethrough(BlockDriverState *bs, Qcow2Cache *c,
+    bool enable);
 
 void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table);
 int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c);

block/qed-check.c

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

block/qed-table.c

@@ -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

@@ -30,7 +30,7 @@ static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
     }
 }
 
-static const AIOCBInfo qed_aiocb_info = {
+static AIOPool qed_aio_pool = {
     .aiocb_size         = sizeof(QEDAIOCB),
     .cancel             = qed_aio_cancel,
 };
@@ -89,7 +89,7 @@ static void qed_header_cpu_to_le(const QEDHeader *cpu, QEDHeader *le)
     le->backing_filename_size = cpu_to_le32(cpu->backing_filename_size);
 }
 
-int qed_write_header_sync(BDRVQEDState *s)
+static int qed_write_header_sync(BDRVQEDState *s)
 {
     QEDHeader le;
     int ret;
@@ -477,7 +477,7 @@ static int bdrv_qed_open(BlockDriverState *bs, int flags)
     }
 
     /* If image was not closed cleanly, check consistency */
-    if (!(flags & BDRV_O_CHECK) && (s->header.features & QED_F_NEED_CHECK)) {
+    if (s->header.features & QED_F_NEED_CHECK) {
         /* Read-only images cannot be fixed.  There is no risk of corruption
          * since write operations are not possible.  Therefore, allow
          * potentially inconsistent images to be opened read-only.  This can
@@ -491,6 +491,13 @@ static int bdrv_qed_open(BlockDriverState *bs, int flags)
             if (ret) {
                 goto out;
             }
+            if (!result.corruptions && !result.check_errors) {
+                /* Ensure fixes reach storage before clearing check bit */
+                bdrv_flush(s->bs);
+
+                s->header.features &= ~QED_F_NEED_CHECK;
+                qed_write_header_sync(s);
+            }
         }
     }
 
@@ -505,14 +512,6 @@ out:
     return ret;
 }
 
-/* We have nothing to do for QED reopen, stubs just return
- * success */
-static int bdrv_qed_reopen_prepare(BDRVReopenState *state,
-                                   BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 static void bdrv_qed_close(BlockDriverState *bs)
 {
     BDRVQEDState *s = bs->opaque;
@@ -737,7 +736,7 @@ static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
     /* Zero all sectors if reading beyond the end of the backing file */
     if (pos >= backing_length ||
         pos + qiov->size > backing_length) {
-        qemu_iovec_memset(qiov, 0, 0, qiov->size);
+        qemu_iovec_memset(qiov, 0, qiov->size);
     }
 
     /* Complete now if there are no backing file sectors to read */
@@ -749,7 +748,7 @@ static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
     /* If the read straddles the end of the backing file, shorten it */
     size = MIN((uint64_t)backing_length - pos, qiov->size);
 
-    BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING_AIO);
+    BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING);
     bdrv_aio_readv(s->bs->backing_hd, pos / BDRV_SECTOR_SIZE,
                    qiov, size / BDRV_SECTOR_SIZE, cb, opaque);
 }
@@ -1132,7 +1131,7 @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len)
 
     acb->cur_nclusters = qed_bytes_to_clusters(s,
             qed_offset_into_cluster(s, acb->cur_pos) + len);
-    qemu_iovec_concat(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+    qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
 
     if (acb->flags & QED_AIOCB_ZERO) {
         /* Skip ahead if the clusters are already zero */
@@ -1178,7 +1177,7 @@ static void qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len)
 
     /* Calculate the I/O vector */
     acb->cur_cluster = offset;
-    qemu_iovec_concat(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+    qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
 
     /* Do the actual write */
     qed_aio_write_main(acb, 0);
@@ -1248,11 +1247,11 @@ static void qed_aio_read_data(void *opaque, int ret,
         goto err;
     }
 
-    qemu_iovec_concat(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
+    qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
 
     /* Handle zero cluster and backing file reads */
     if (ret == QED_CLUSTER_ZERO) {
-        qemu_iovec_memset(&acb->cur_qiov, 0, 0, acb->cur_qiov.size);
+        qemu_iovec_memset(&acb->cur_qiov, 0, acb->cur_qiov.size);
         qed_aio_next_io(acb, 0);
         return;
     } else if (ret != QED_CLUSTER_FOUND) {
@@ -1311,7 +1310,7 @@ static BlockDriverAIOCB *qed_aio_setup(BlockDriverState *bs,
                                        BlockDriverCompletionFunc *cb,
                                        void *opaque, int flags)
 {
-    QEDAIOCB *acb = qemu_aio_get(&qed_aiocb_info, bs, cb, opaque);
+    QEDAIOCB *acb = qemu_aio_get(&qed_aio_pool, bs, cb, opaque);
 
     trace_qed_aio_setup(bs->opaque, acb, sector_num, nb_sectors,
                         opaque, flags);
@@ -1371,21 +1370,10 @@ static int coroutine_fn bdrv_qed_co_write_zeroes(BlockDriverState *bs,
                                                  int nb_sectors)
 {
     BlockDriverAIOCB *blockacb;
-    BDRVQEDState *s = bs->opaque;
     QEDWriteZeroesCB cb = { .done = false };
     QEMUIOVector qiov;
     struct iovec iov;
 
-    /* Refuse if there are untouched backing file sectors */
-    if (bs->backing_hd) {
-        if (qed_offset_into_cluster(s, sector_num * BDRV_SECTOR_SIZE) != 0) {
-            return -ENOTSUP;
-        }
-        if (qed_offset_into_cluster(s, nb_sectors * BDRV_SECTOR_SIZE) != 0) {
-            return -ENOTSUP;
-        }
-    }
-
     /* Zero writes start without an I/O buffer.  If a buffer becomes necessary
      * then it will be allocated during request processing.
      */
@@ -1529,12 +1517,11 @@ static void bdrv_qed_invalidate_cache(BlockDriverState *bs)
     bdrv_qed_open(bs, bs->open_flags);
 }
 
-static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result,
-                          BdrvCheckMode fix)
+static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result)
 {
     BDRVQEDState *s = bs->opaque;
 
-    return qed_check(s, result, !!fix);
+    return qed_check(s, result, false);
 }
 
 static QEMUOptionParameter qed_create_options[] = {
@@ -1572,7 +1559,6 @@ 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

@@ -210,11 +210,6 @@ typedef struct {
 void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque);
 void gencb_complete(void *opaque, int ret);
 
-/**
- * Header functions
- */
-int qed_write_header_sync(BDRVQEDState *s);
-
 /**
  * L2 cache functions
  */

block/raw-posix-aio.h

@@ -1,5 +1,5 @@
 /*
- * Declarations for AIO in the raw protocol
+ * QEMU Posix block I/O backend AIO support
  *
  * Copyright IBM, Corp. 2008
  *
@@ -12,8 +12,8 @@
  * Contributions after 2012-01-13 are licensed under the terms of the
  * GNU GPL, version 2 or (at your option) any later version.
  */
-#ifndef QEMU_RAW_AIO_H
-#define QEMU_RAW_AIO_H
+#ifndef QEMU_RAW_POSIX_AIO_H
+#define QEMU_RAW_POSIX_AIO_H
 
 /* AIO request types */
 #define QEMU_AIO_READ         0x0001
@@ -27,22 +27,19 @@
 #define QEMU_AIO_MISALIGNED   0x1000
 
 
+/* posix-aio-compat.c - thread pool based implementation */
+int paio_init(void);
+BlockDriverAIOCB *paio_submit(BlockDriverState *bs, int fd,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockDriverCompletionFunc *cb, void *opaque, int type);
+BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd,
+        unsigned long int req, void *buf,
+        BlockDriverCompletionFunc *cb, void *opaque);
+
 /* linux-aio.c - Linux native implementation */
-#ifdef CONFIG_LINUX_AIO
 void *laio_init(void);
 BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
         BlockDriverCompletionFunc *cb, void *opaque, int type);
-#endif
 
-#ifdef _WIN32
-typedef struct QEMUWin32AIOState QEMUWin32AIOState;
-QEMUWin32AIOState *win32_aio_init(void);
-int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile);
-BlockDriverAIOCB *win32_aio_submit(BlockDriverState *bs,
-        QEMUWin32AIOState *aio, HANDLE hfile,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockDriverCompletionFunc *cb, void *opaque, int type);
-#endif
-
-#endif /* QEMU_RAW_AIO_H */
+#endif /* QEMU_RAW_POSIX_AIO_H */

block/raw-posix.c

@@ -27,10 +27,7 @@
 #include "qemu-log.h"
 #include "block_int.h"
 #include "module.h"
-#include "trace.h"
-#include "thread-pool.h"
-#include "iov.h"
-#include "raw-aio.h"
+#include "block/raw-posix-aio.h"
 
 #if defined(__APPLE__) && (__MACH__)
 #include <paths.h>
@@ -55,10 +52,6 @@
 #include <sys/param.h>
 #include <linux/cdrom.h>
 #include <linux/fd.h>
-#include <linux/fs.h>
-#endif
-#ifdef CONFIG_FIEMAP
-#include <linux/fiemap.h>
 #endif
 #if defined (__FreeBSD__) || defined(__FreeBSD_kernel__)
 #include <sys/disk.h>
@@ -136,36 +129,16 @@ 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
 } 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;
-    size_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
@@ -208,57 +181,6 @@ 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)
 {
@@ -270,8 +192,20 @@ 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);
@@ -282,13 +216,45 @@ 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;
-    }
+    /*
+     * 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
+    }
 
 #ifdef CONFIG_XFS
     if (platform_test_xfs_fd(s->fd)) {
@@ -297,6 +263,12 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
 #endif
 
     return 0;
+
+out_free_buf:
+    qemu_vfree(s->aligned_buf);
+out_close:
+    close(fd);
+    return -errno;
 }
 
 static int raw_open(BlockDriverState *bs, const char *filename, int flags)
@@ -307,113 +279,6 @@ 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_ASYNC | O_NONBLOCK;
-#ifdef O_NOATIME
-    fcntl_flags |= O_NOATIME;
-#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
         {
@@ -447,275 +312,6 @@ static int qiov_is_aligned(BlockDriverState *bs, QEMUIOVector *qiov)
     return 1;
 }
 
-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.
- */
-static ssize_t handle_aiocb_rw_linear(RawPosixAIOData *aiocb, char *buf)
-{
-    ssize_t offset = 0;
-    ssize_t len;
-
-    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;
-        }
-    }
-
-    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;
-}
-
-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;
-    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);
-}
-
-static BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd,
-        unsigned long int req, void *buf,
-        BlockDriverCompletionFunc *cb, void *opaque)
-{
-    RawPosixAIOData *acb = g_slice_new(RawPosixAIOData);
-
-    acb->bs = bs;
-    acb->aio_type = QEMU_AIO_IOCTL;
-    acb->aio_fildes = 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);
-}
-
 static BlockDriverAIOCB *raw_aio_submit(BlockDriverState *bs,
         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
         BlockDriverCompletionFunc *cb, void *opaque, int type)
@@ -730,7 +326,7 @@ 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 (s->aligned_buf) {
         if (!qiov_is_aligned(bs, qiov)) {
             type |= QEMU_AIO_MISALIGNED;
 #ifdef CONFIG_LINUX_AIO
@@ -776,8 +372,10 @@ static void raw_close(BlockDriverState *bs)
 {
     BDRVRawState *s = bs->opaque;
     if (s->fd >= 0) {
-        qemu_close(s->fd);
+        close(s->fd);
         s->fd = -1;
+        if (s->aligned_buf != NULL)
+            qemu_vfree(s->aligned_buf);
     }
 }
 
@@ -970,121 +568,21 @@ static int raw_create(const char *filename, QEMUOptionParameter *options)
         options++;
     }
 
-    fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
-                   0644);
+    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
+              0644);
     if (fd < 0) {
         result = -errno;
     } else {
         if (ftruncate(fd, total_size * BDRV_SECTOR_SIZE) != 0) {
             result = -errno;
         }
-        if (qemu_close(fd) != 0) {
+        if (close(fd) != 0) {
             result = -errno;
         }
     }
     return result;
 }
 
-/*
- * Returns true iff the specified sector is present in the disk image. Drivers
- * not implementing the functionality are assumed to not support backing files,
- * hence all their sectors are reported as allocated.
- *
- * If 'sector_num' is beyond the end of the disk image the return value is 0
- * and 'pnum' is set to 0.
- *
- * 'pnum' is set to the number of sectors (including and immediately following
- * the specified sector) that are known to be in the same
- * allocated/unallocated state.
- *
- * 'nb_sectors' is the max value 'pnum' should be set to.  If nb_sectors goes
- * beyond the end of the disk image it will be clamped.
- */
-static int coroutine_fn raw_co_is_allocated(BlockDriverState *bs,
-                                            int64_t sector_num,
-                                            int nb_sectors, int *pnum)
-{
-    off_t start, data, hole;
-    int ret;
-
-    ret = fd_open(bs);
-    if (ret < 0) {
-        return ret;
-    }
-
-    start = sector_num * BDRV_SECTOR_SIZE;
-
-#ifdef CONFIG_FIEMAP
-
-    BDRVRawState *s = bs->opaque;
-    struct {
-        struct fiemap fm;
-        struct fiemap_extent fe;
-    } f;
-
-    f.fm.fm_start = start;
-    f.fm.fm_length = (int64_t)nb_sectors * BDRV_SECTOR_SIZE;
-    f.fm.fm_flags = 0;
-    f.fm.fm_extent_count = 1;
-    f.fm.fm_reserved = 0;
-    if (ioctl(s->fd, FS_IOC_FIEMAP, &f) == -1) {
-        /* Assume everything is allocated.  */
-        *pnum = nb_sectors;
-        return 1;
-    }
-
-    if (f.fm.fm_mapped_extents == 0) {
-        /* No extents found, data is beyond f.fm.fm_start + f.fm.fm_length.
-         * f.fm.fm_start + f.fm.fm_length must be clamped to the file size!
-         */
-        off_t length = lseek(s->fd, 0, SEEK_END);
-        hole = f.fm.fm_start;
-        data = MIN(f.fm.fm_start + f.fm.fm_length, length);
-    } else {
-        data = f.fe.fe_logical;
-        hole = f.fe.fe_logical + f.fe.fe_length;
-    }
-
-#elif defined SEEK_HOLE && defined SEEK_DATA
-
-    BDRVRawState *s = bs->opaque;
-
-    hole = lseek(s->fd, start, SEEK_HOLE);
-    if (hole == -1) {
-        /* -ENXIO indicates that sector_num was past the end of the file.
-         * There is a virtual hole there.  */
-        assert(errno != -ENXIO);
-
-        /* Most likely EINVAL.  Assume everything is allocated.  */
-        *pnum = nb_sectors;
-        return 1;
-    }
-
-    if (hole > start) {
-        data = start;
-    } else {
-        /* On a hole.  We need another syscall to find its end.  */
-        data = lseek(s->fd, start, SEEK_DATA);
-        if (data == -1) {
-            data = lseek(s->fd, 0, SEEK_END);
-        }
-    }
-#else
-    *pnum = nb_sectors;
-    return 1;
-#endif
-
-    if (data <= start) {
-        /* On a data extent, compute sectors to the end of the extent.  */
-        *pnum = MIN(nb_sectors, (hole - start) / BDRV_SECTOR_SIZE);
-        return 1;
-    } else {
-        /* On a hole, compute sectors to the beginning of the next extent.  */
-        *pnum = MIN(nb_sectors, (data - start) / BDRV_SECTOR_SIZE);
-        return 0;
-    }
-}
-
 #ifdef CONFIG_XFS
 static int xfs_discard(BDRVRawState *s, int64_t sector_num, int nb_sectors)
 {
@@ -1133,13 +631,9 @@ 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,
@@ -1247,11 +741,11 @@ static int hdev_open(BlockDriverState *bs, const char *filename, int flags)
         if ( bsdPath[ 0 ] != '\0' ) {
             strcat(bsdPath,"s0");
             /* some CDs don't have a partition 0 */
-            fd = qemu_open(bsdPath, O_RDONLY | O_BINARY | O_LARGEFILE);
+            fd = open(bsdPath, O_RDONLY | O_BINARY | O_LARGEFILE);
             if (fd < 0) {
                 bsdPath[strlen(bsdPath)-1] = '1';
             } else {
-                qemu_close(fd);
+                close(fd);
             }
             filename = bsdPath;
         }
@@ -1290,7 +784,7 @@ static int fd_open(BlockDriverState *bs)
     last_media_present = (s->fd >= 0);
     if (s->fd >= 0 &&
         (get_clock() - s->fd_open_time) >= FD_OPEN_TIMEOUT) {
-        qemu_close(s->fd);
+        close(s->fd);
         s->fd = -1;
 #ifdef DEBUG_FLOPPY
         printf("Floppy closed\n");
@@ -1304,7 +798,7 @@ static int fd_open(BlockDriverState *bs)
 #endif
             return -EIO;
         }
-        s->fd = qemu_open(bs->filename, s->open_flags & ~O_NONBLOCK);
+        s->fd = open(bs->filename, s->open_flags & ~O_NONBLOCK);
         if (s->fd < 0) {
             s->fd_error_time = get_clock();
             s->fd_got_error = 1;
@@ -1378,7 +872,7 @@ static int hdev_create(const char *filename, QEMUOptionParameter *options)
         options++;
     }
 
-    fd = qemu_open(filename, O_WRONLY | O_BINARY);
+    fd = open(filename, O_WRONLY | O_BINARY);
     if (fd < 0)
         return -errno;
 
@@ -1389,7 +883,7 @@ static int hdev_create(const char *filename, QEMUOptionParameter *options)
     else if (lseek(fd, 0, SEEK_END) < total_size * BDRV_SECTOR_SIZE)
         ret = -ENOSPC;
 
-    qemu_close(fd);
+    close(fd);
     return ret;
 }
 
@@ -1405,9 +899,6 @@ 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,
@@ -1442,7 +933,7 @@ static int floppy_open(BlockDriverState *bs, const char *filename, int flags)
         return ret;
 
     /* close fd so that we can reopen it as needed */
-    qemu_close(s->fd);
+    close(s->fd);
     s->fd = -1;
     s->fd_media_changed = 1;
 
@@ -1456,12 +947,10 @@ static int floppy_probe_device(const char *filename)
     struct floppy_struct fdparam;
     struct stat st;
 
-    if (strstart(filename, "/dev/fd", NULL) &&
-        !strstart(filename, "/dev/fdset/", NULL)) {
+    if (strstart(filename, "/dev/fd", NULL))
         prio = 50;
-    }
 
-    fd = qemu_open(filename, O_RDONLY | O_NONBLOCK);
+    fd = open(filename, O_RDONLY | O_NONBLOCK);
     if (fd < 0) {
         goto out;
     }
@@ -1476,7 +965,7 @@ static int floppy_probe_device(const char *filename)
         prio = 100;
 
 outc:
-    qemu_close(fd);
+    close(fd);
 out:
     return prio;
 }
@@ -1511,14 +1000,14 @@ static void floppy_eject(BlockDriverState *bs, bool eject_flag)
     int fd;
 
     if (s->fd >= 0) {
-        qemu_close(s->fd);
+        close(s->fd);
         s->fd = -1;
     }
-    fd = qemu_open(bs->filename, s->open_flags | O_NONBLOCK);
+    fd = open(bs->filename, s->open_flags | O_NONBLOCK);
     if (fd >= 0) {
         if (ioctl(fd, FDEJECT, 0) < 0)
             perror("FDEJECT");
-        qemu_close(fd);
+        close(fd);
     }
 }
 
@@ -1529,9 +1018,6 @@ 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,
@@ -1567,7 +1053,7 @@ static int cdrom_probe_device(const char *filename)
     int prio = 0;
     struct stat st;
 
-    fd = qemu_open(filename, O_RDONLY | O_NONBLOCK);
+    fd = open(filename, O_RDONLY | O_NONBLOCK);
     if (fd < 0) {
         goto out;
     }
@@ -1582,7 +1068,7 @@ static int cdrom_probe_device(const char *filename)
         prio = 100;
 
 outc:
-    qemu_close(fd);
+    close(fd);
 out:
     return prio;
 }
@@ -1631,9 +1117,6 @@ 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,
@@ -1693,8 +1176,8 @@ static int cdrom_reopen(BlockDriverState *bs)
      * FreeBSD seems to not notice sometimes...
      */
     if (s->fd >= 0)
-        qemu_close(s->fd);
-    fd = qemu_open(bs->filename, s->open_flags, 0644);
+        close(s->fd);
+    fd = open(bs->filename, s->open_flags, 0644);
     if (fd < 0) {
         s->fd = -1;
         return -EIO;
@@ -1753,9 +1236,6 @@ 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,

block/raw-win32.c

@@ -25,10 +25,6 @@
 #include "qemu-timer.h"
 #include "block_int.h"
 #include "module.h"
-#include "raw-aio.h"
-#include "trace.h"
-#include "thread-pool.h"
-#include "iov.h"
 #include <windows.h>
 #include <winioctl.h>
 
@@ -36,130 +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)
@@ -384,13 +255,13 @@ static int raw_create(const char *filename, QEMUOptionParameter *options)
         options++;
     }
 
-    fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
-                   0644);
+    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
+              0644);
     if (fd < 0)
         return -EIO;
     set_sparse(fd);
     ftruncate(fd, total_size * 512);
-    qemu_close(fd);
+    close(fd);
     return 0;
 }
 
@@ -411,9 +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,
@@ -503,10 +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);
@@ -534,9 +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

@@ -9,25 +9,15 @@ 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)
 {
-    BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
     return bdrv_co_readv(bs->file, sector_num, nb_sectors, qiov);
 }
 
 static int coroutine_fn raw_co_writev(BlockDriverState *bs, int64_t sector_num,
                                       int nb_sectors, QEMUIOVector *qiov)
 {
-    BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
     return bdrv_co_writev(bs->file, sector_num, nb_sectors, qiov);
 }
 
@@ -35,13 +25,6 @@ static void raw_close(BlockDriverState *bs)
 {
 }
 
-static int coroutine_fn raw_co_is_allocated(BlockDriverState *bs,
-                                            int64_t sector_num,
-                                            int nb_sectors, int *pnum)
-{
-    return bdrv_co_is_allocated(bs->file, sector_num, nb_sectors, pnum);
-}
-
 static int64_t raw_getlength(BlockDriverState *bs)
 {
     return bdrv_getlength(bs->file);
@@ -123,11 +106,8 @@ static BlockDriver bdrv_raw = {
     .bdrv_open          = raw_open,
     .bdrv_close         = raw_close,
 
-    .bdrv_reopen_prepare  = raw_reopen_prepare,
-
     .bdrv_co_readv          = raw_co_readv,
     .bdrv_co_writev         = raw_co_writev,
-    .bdrv_co_is_allocated   = raw_co_is_allocated,
     .bdrv_co_discard        = raw_co_discard,
 
     .bdrv_probe         = raw_probe,

block/rbd.c

@@ -69,7 +69,7 @@ typedef enum {
 typedef struct RBDAIOCB {
     BlockDriverAIOCB common;
     QEMUBH *bh;
-    int64_t ret;
+    int ret;
     QEMUIOVector *qiov;
     char *bounce;
     RBDAIOCmd cmd;
@@ -86,7 +86,7 @@ typedef struct RADOSCB {
     int done;
     int64_t size;
     char *buf;
-    int64_t ret;
+    int ret;
 } RADOSCB;
 
 #define RBD_FD_READ 0
@@ -476,19 +476,6 @@ static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags)
         s->snap = g_strdup(snap_buf);
     }
 
-    /*
-     * Fallback to more conservative semantics if setting cache
-     * options fails. Ignore errors from setting rbd_cache because the
-     * only possible error is that the option does not exist, and
-     * librbd defaults to no caching. If write through caching cannot
-     * be set up, fall back to no caching.
-     */
-    if (flags & BDRV_O_NOCACHE) {
-        rados_conf_set(s->cluster, "rbd_cache", "false");
-    } else {
-        rados_conf_set(s->cluster, "rbd_cache", "true");
-    }
-
     if (strstr(conf, "conf=") == NULL) {
         /* try default location, but ignore failure */
         rados_conf_read_file(s->cluster, NULL);
@@ -570,7 +557,7 @@ static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
     acb->cancelled = 1;
 }
 
-static const AIOCBInfo rbd_aiocb_info = {
+static AIOPool rbd_aio_pool = {
     .aiocb_size = sizeof(RBDAIOCB),
     .cancel = qemu_rbd_aio_cancel,
 };
@@ -633,7 +620,7 @@ static void rbd_aio_bh_cb(void *opaque)
     RBDAIOCB *acb = opaque;
 
     if (acb->cmd == RBD_AIO_READ) {
-        qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
+        qemu_iovec_from_buffer(acb->qiov, acb->bounce, acb->qiov->size);
     }
     qemu_vfree(acb->bounce);
     acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
@@ -672,7 +659,7 @@ 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) {
@@ -687,7 +674,7 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
     acb->bh = NULL;
 
     if (cmd == RBD_AIO_WRITE) {
-        qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
+        qemu_iovec_to_buffer(acb->qiov, acb->bounce);
     }
 
     buf = acb->bounce;

block/sheepdog.c

@@ -201,12 +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);
 }
@@ -231,7 +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;
 }
@@ -259,7 +259,8 @@ typedef struct AIOReq {
     uint8_t flags;
     uint32_t id;
 
-    QLIST_ENTRY(AIOReq) aio_siblings;
+    QLIST_ENTRY(AIOReq) outstanding_aio_siblings;
+    QLIST_ENTRY(AIOReq) aioreq_siblings;
 } AIOReq;
 
 enum AIOCBState {
@@ -281,8 +282,9 @@ struct SheepdogAIOCB {
     Coroutine *coroutine;
     void (*aio_done_func)(SheepdogAIOCB *);
 
-    bool canceled;
-    int nr_pending;
+    int canceled;
+
+    QLIST_HEAD(aioreq_head, AIOReq) aioreq_head;
 };
 
 typedef struct BDRVSheepdogState {
@@ -292,8 +294,8 @@ typedef struct BDRVSheepdogState {
     uint32_t max_dirty_data_idx;
 
     char name[SD_MAX_VDI_LEN];
-    bool is_snapshot;
-    bool cache_enabled;
+    int is_snapshot;
+    uint8_t cache_enabled;
 
     char *addr;
     char *port;
@@ -305,8 +307,7 @@ typedef struct BDRVSheepdogState {
     Coroutine *co_recv;
 
     uint32_t aioreq_seq_num;
-    QLIST_HEAD(inflight_aio_head, AIOReq) inflight_aio_head;
-    QLIST_HEAD(pending_aio_head, AIOReq) pending_aio_head;
+    QLIST_HEAD(outstanding_aio_head, AIOReq) outstanding_aio_head;
 } BDRVSheepdogState;
 
 static const char * sd_strerror(int err)
@@ -357,7 +358,7 @@ static const char * sd_strerror(int err)
  * Sheepdog I/O handling:
  *
  * 1. In sd_co_rw_vector, we send the I/O requests to the server and
- *    link the requests to the inflight_list in the
+ *    link the requests to the outstanding_list in the
  *    BDRVSheepdogState.  The function exits without waiting for
  *    receiving the response.
  *
@@ -385,18 +386,21 @@ static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb,
     aio_req->flags = flags;
     aio_req->id = s->aioreq_seq_num++;
 
-    acb->nr_pending++;
+    QLIST_INSERT_HEAD(&s->outstanding_aio_head, aio_req,
+                      outstanding_aio_siblings);
+    QLIST_INSERT_HEAD(&acb->aioreq_head, aio_req, aioreq_siblings);
+
     return aio_req;
 }
 
-static inline void free_aio_req(BDRVSheepdogState *s, AIOReq *aio_req)
+static inline int free_aio_req(BDRVSheepdogState *s, AIOReq *aio_req)
 {
     SheepdogAIOCB *acb = aio_req->aiocb;
-
-    QLIST_REMOVE(aio_req, aio_siblings);
+    QLIST_REMOVE(aio_req, outstanding_aio_siblings);
+    QLIST_REMOVE(aio_req, aioreq_siblings);
     g_free(aio_req);
 
-    acb->nr_pending--;
+    return !QLIST_EMPTY(&acb->aioreq_head);
 }
 
 static void coroutine_fn sd_finish_aiocb(SheepdogAIOCB *acb)
@@ -417,10 +421,10 @@ 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,
 };
@@ -431,7 +435,7 @@ static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
 {
     SheepdogAIOCB *acb;
 
-    acb = qemu_aio_get(&sd_aiocb_info, bs, cb, opaque);
+    acb = qemu_aio_get(&sd_aio_pool, bs, cb, opaque);
 
     acb->qiov = qiov;
 
@@ -439,10 +443,10 @@ 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;
+    QLIST_INIT(&acb->aioreq_head);
     return acb;
 }
 
@@ -499,8 +503,28 @@ success:
     return fd;
 }
 
-static coroutine_fn int send_co_req(int sockfd, SheepdogReq *hdr, void *data,
-                                    unsigned int *wlen)
+static int send_req(int sockfd, SheepdogReq *hdr, void *data,
+                    unsigned int *wlen)
+{
+    int ret;
+
+    ret = qemu_send_full(sockfd, hdr, sizeof(*hdr), 0);
+    if (ret < sizeof(*hdr)) {
+        error_report("failed to send a req, %s", strerror(errno));
+        return -errno;
+    }
+
+    ret = qemu_send_full(sockfd, data, *wlen, 0);
+    if (ret < *wlen) {
+        error_report("failed to send a req, %s", strerror(errno));
+        ret = -errno;
+    }
+
+    return ret;
+}
+
+static int send_co_req(int sockfd, SheepdogReq *hdr, void *data,
+                       unsigned int *wlen)
 {
     int ret;
 
@@ -517,37 +541,46 @@ static coroutine_fn int send_co_req(int sockfd, SheepdogReq *hdr, void *data,
 
     return ret;
 }
-
-static void restart_co_req(void *opaque)
+static int do_req(int sockfd, SheepdogReq *hdr, void *data,
+                  unsigned int *wlen, unsigned int *rlen)
 {
-    Coroutine *co = opaque;
+    int ret;
 
-    qemu_coroutine_enter(co, NULL);
+    socket_set_block(sockfd);
+    ret = send_req(sockfd, hdr, data, wlen);
+    if (ret < 0) {
+        goto out;
+    }
+
+    ret = qemu_recv_full(sockfd, hdr, sizeof(*hdr), 0);
+    if (ret < sizeof(*hdr)) {
+        error_report("failed to get a rsp, %s", strerror(errno));
+        ret = -errno;
+        goto out;
+    }
+
+    if (*rlen > hdr->data_length) {
+        *rlen = hdr->data_length;
+    }
+
+    if (*rlen) {
+        ret = qemu_recv_full(sockfd, data, *rlen, 0);
+        if (ret < *rlen) {
+            error_report("failed to get the data, %s", strerror(errno));
+            ret = -errno;
+            goto out;
+        }
+    }
+    ret = 0;
+out:
+    socket_set_nonblock(sockfd);
+    return ret;
 }
 
-typedef struct SheepdogReqCo {
-    int sockfd;
-    SheepdogReq *hdr;
-    void *data;
-    unsigned int *wlen;
-    unsigned int *rlen;
-    int ret;
-    bool finished;
-} SheepdogReqCo;
-
-static coroutine_fn void do_co_req(void *opaque)
+static int do_co_req(int sockfd, SheepdogReq *hdr, void *data,
+                     unsigned int *wlen, unsigned int *rlen)
 {
     int ret;
-    Coroutine *co;
-    SheepdogReqCo *srco = opaque;
-    int sockfd = srco->sockfd;
-    SheepdogReq *hdr = srco->hdr;
-    void *data = srco->data;
-    unsigned int *wlen = srco->wlen;
-    unsigned int *rlen = srco->rlen;
-
-    co = qemu_coroutine_self();
-    qemu_aio_set_fd_handler(sockfd, NULL, restart_co_req, NULL, co);
 
     socket_set_block(sockfd);
     ret = send_co_req(sockfd, hdr, data, wlen);
@@ -555,8 +588,6 @@ static coroutine_fn void do_co_req(void *opaque)
         goto out;
     }
 
-    qemu_aio_set_fd_handler(sockfd, restart_co_req, NULL, NULL, co);
-
     ret = qemu_co_recv(sockfd, hdr, sizeof(*hdr));
     if (ret < sizeof(*hdr)) {
         error_report("failed to get a rsp, %s", strerror(errno));
@@ -578,79 +609,40 @@ static coroutine_fn void do_co_req(void *opaque)
     }
     ret = 0;
 out:
-    qemu_aio_set_fd_handler(sockfd, NULL, NULL, NULL, NULL);
     socket_set_nonblock(sockfd);
-
-    srco->ret = ret;
-    srco->finished = true;
-}
-
-static int do_req(int sockfd, SheepdogReq *hdr, void *data,
-                  unsigned int *wlen, unsigned int *rlen)
-{
-    Coroutine *co;
-    SheepdogReqCo srco = {
-        .sockfd = sockfd,
-        .hdr = hdr,
-        .data = data,
-        .wlen = wlen,
-        .rlen = rlen,
-        .ret = 0,
-        .finished = false,
-    };
-
-    if (qemu_in_coroutine()) {
-        do_co_req(&srco);
-    } else {
-        co = qemu_coroutine_create(do_co_req);
-        qemu_coroutine_enter(co, &srco);
-        while (!srco.finished) {
-            qemu_aio_wait();
-        }
-    }
-
-    return srco.ret;
+    return ret;
 }
 
 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);
 
-
-static AIOReq *find_pending_req(BDRVSheepdogState *s, uint64_t oid)
-{
-    AIOReq *aio_req;
-
-    QLIST_FOREACH(aio_req, &s->pending_aio_head, aio_siblings) {
-        if (aio_req->oid == oid) {
-            return aio_req;
-        }
-    }
-
-    return NULL;
-}
-
 /*
  * This function searchs pending requests to the object `oid', and
  * sends them.
  */
-static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid)
+static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid, uint32_t id)
 {
-    AIOReq *aio_req;
+    AIOReq *aio_req, *next;
     SheepdogAIOCB *acb;
     int ret;
 
-    while ((aio_req = find_pending_req(s, oid)) != NULL) {
+    QLIST_FOREACH_SAFE(aio_req, &s->outstanding_aio_head,
+                       outstanding_aio_siblings, next) {
+        if (id == aio_req->id) {
+            continue;
+        }
+        if (aio_req->oid != oid) {
+            continue;
+        }
+
         acb = aio_req->aiocb;
-        /* move aio_req from pending list to inflight one */
-        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);
-            if (!acb->nr_pending) {
+            if (QLIST_EMPTY(&acb->aioreq_head)) {
                 sd_finish_aiocb(acb);
             }
         }
@@ -671,9 +663,10 @@ static void coroutine_fn aio_read_response(void *opaque)
     int ret;
     AIOReq *aio_req = NULL;
     SheepdogAIOCB *acb;
+    int rest;
     unsigned long idx;
 
-    if (QLIST_EMPTY(&s->inflight_aio_head)) {
+    if (QLIST_EMPTY(&s->outstanding_aio_head)) {
         goto out;
     }
 
@@ -684,8 +677,8 @@ static void coroutine_fn aio_read_response(void *opaque)
         goto out;
     }
 
-    /* find the right aio_req from the inflight aio list */
-    QLIST_FOREACH(aio_req, &s->inflight_aio_head, aio_siblings) {
+    /* find the right aio_req from the outstanding_aio list */
+    QLIST_FOREACH(aio_req, &s->outstanding_aio_head, outstanding_aio_siblings) {
         if (aio_req->id == rsp.id) {
             break;
         }
@@ -723,12 +716,12 @@ static void coroutine_fn aio_read_response(void *opaque)
              * create requests are not allowed, so we search the
              * pending requests here.
              */
-            send_pending_req(s, vid_to_data_oid(s->inode.vdi_id, idx));
+            send_pending_req(s, vid_to_data_oid(s->inode.vdi_id, idx), rsp.id);
         }
         break;
     case AIOCB_READ_UDATA:
-        ret = qemu_co_recvv(fd, acb->qiov->iov, acb->qiov->niov,
-                            aio_req->iov_offset, rsp.data_length);
+        ret = qemu_co_recvv(fd, acb->qiov->iov, rsp.data_length,
+                            aio_req->iov_offset);
         if (ret < 0) {
             error_report("failed to get the data, %s", strerror(errno));
             goto out;
@@ -741,8 +734,8 @@ static void coroutine_fn aio_read_response(void *opaque)
         error_report("%s", sd_strerror(rsp.result));
     }
 
-    free_aio_req(s, aio_req);
-    if (!acb->nr_pending) {
+    rest = free_aio_req(s, aio_req);
+    if (!rest) {
         /*
          * We've finished all requests which belong to the AIOCB, so
          * we can switch back to sd_co_readv/writev now.
@@ -775,8 +768,7 @@ static int aio_flush_request(void *opaque)
 {
     BDRVSheepdogState *s = opaque;
 
-    return !QLIST_EMPTY(&s->inflight_aio_head) ||
-        !QLIST_EMPTY(&s->pending_aio_head);
+    return !QLIST_EMPTY(&s->outstanding_aio_head);
 }
 
 static int set_nodelay(int fd)
@@ -866,14 +858,14 @@ 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 */
@@ -900,10 +892,7 @@ 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);
 
@@ -943,7 +932,7 @@ 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;
@@ -1004,7 +993,7 @@ static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
     }
 
     if (wlen) {
-        ret = qemu_co_sendv(s->fd, iov, niov, aio_req->iov_offset, wlen);
+        ret = qemu_co_sendv(s->fd, iov, wlen, aio_req->iov_offset);
         if (ret < 0) {
             qemu_co_mutex_unlock(&s->lock);
             error_report("failed to send a data, %s", strerror(errno));
@@ -1022,7 +1011,7 @@ 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, bool cache)
+                             int write, int create, uint8_t cache)
 {
     SheepdogObjReq hdr;
     SheepdogObjRsp *rsp = (SheepdogObjRsp *)&hdr;
@@ -1071,18 +1060,18 @@ 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, bool cache)
+                       unsigned int datalen, uint64_t offset, uint8_t cache)
 {
-    return read_write_object(fd, buf, oid, copies, datalen, offset, false,
-                             false, cache);
+    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,
-                        bool cache)
+                        unsigned int datalen, uint64_t offset, int create,
+                        uint8_t cache)
 {
-    return read_write_object(fd, buf, oid, copies, datalen, offset, true,
-                             create, cache);
+    return read_write_object(fd, buf, oid, copies, datalen, offset, 1, create,
+                             cache);
 }
 
 static int sd_open(BlockDriverState *bs, const char *filename, int flags)
@@ -1096,8 +1085,7 @@ static int sd_open(BlockDriverState *bs, const char *filename, int flags)
 
     strstart(filename, "sheepdog:", (const char **)&filename);
 
-    QLIST_INIT(&s->inflight_aio_head);
-    QLIST_INIT(&s->pending_aio_head);
+    QLIST_INIT(&s->outstanding_aio_head);
     s->fd = -1;
 
     memset(vdi, 0, sizeof(vdi));
@@ -1117,17 +1105,19 @@ static int sd_open(BlockDriverState *bs, const char *filename, int flags)
         goto out;
     }
 
-    s->cache_enabled = true;
-    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 (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 +1142,7 @@ 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;
@@ -1180,11 +1170,8 @@ 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;
@@ -1270,7 +1257,7 @@ 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));
@@ -1292,9 +1279,9 @@ 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);
@@ -1422,7 +1409,7 @@ 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_enabled);
+                       s->inode.nr_copies, datalen, 0, 0, s->cache_enabled);
     close(fd);
 
     if (ret < 0) {
@@ -1460,8 +1447,7 @@ static void coroutine_fn sd_write_done(SheepdogAIOCB *acb)
         iov.iov_len = sizeof(s->inode);
         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;
@@ -1515,7 +1501,7 @@ 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);
 
@@ -1529,7 +1515,7 @@ out:
  * Send I/O requests to the server.
  *
  * This function sends requests to the server, links the requests to
- * the inflight_list in BDRVSheepdogState, and exits without
+ * the outstanding_list in BDRVSheepdogState, and exits without
  * waiting the response.  The responses are received in the
  * `aio_read_response' function which is called from the main loop as
  * a fd handler.
@@ -1561,55 +1547,46 @@ static int coroutine_fn sd_co_rw_vector(void *p)
         }
     }
 
-    /*
-     * Make sure we don't free the aiocb before we are done with all requests.
-     * This additional reference is dropped at the end of this function.
-     */
-    acb->nr_pending++;
-
     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);
 
         len = MIN(total - done, SD_DATA_OBJ_SIZE - offset);
 
-        switch (acb->aiocb_type) {
-        case AIOCB_READ_UDATA:
-            if (!inode->data_vdi_id[idx]) {
-                qemu_iovec_memset(acb->qiov, done, 0, len);
+        if (!inode->data_vdi_id[idx]) {
+            if (acb->aiocb_type == AIOCB_READ_UDATA) {
                 goto done;
             }
-            break;
-        case AIOCB_WRITE_UDATA:
-            if (!inode->data_vdi_id[idx]) {
-                create = true;
-            } else if (!is_data_obj_writable(inode, idx)) {
-                /* Copy-On-Write */
-                create = true;
-                old_oid = oid;
-                flags = SD_FLAG_CMD_COW;
-            }
-            break;
-        default:
-            break;
+
+            create = 1;
+        } else if (acb->aiocb_type == AIOCB_WRITE_UDATA
+                   && !is_data_obj_writable(inode, idx)) {
+            /* Copy-On-Write */
+            create = 1;
+            old_oid = oid;
+            flags = SD_FLAG_CMD_COW;
         }
 
         if (create) {
-            dprintf("update ino (%" PRIu32 ") %" PRIu64 " %" PRIu64 " %ld\n",
-                    inode->vdi_id, oid,
+            dprintf("update ino (%" PRIu32") %" PRIu64 " %" PRIu64
+                    " %" PRIu64 "\n", inode->vdi_id, oid,
                     vid_to_data_oid(inode->data_vdi_id[idx], idx), idx);
             oid = vid_to_data_oid(inode->vdi_id, idx);
-            dprintf("new oid %" PRIx64 "\n", oid);
+            dprintf("new oid %lx\n", oid);
         }
 
         aio_req = alloc_aio_req(s, acb, oid, len, offset, flags, old_oid, done);
 
         if (create) {
             AIOReq *areq;
-            QLIST_FOREACH(areq, &s->inflight_aio_head, aio_siblings) {
+            QLIST_FOREACH(areq, &s->outstanding_aio_head,
+                          outstanding_aio_siblings) {
+                if (areq == aio_req) {
+                    continue;
+                }
                 if (areq->oid == oid) {
                     /*
                      * Sheepdog cannot handle simultaneous create
@@ -1619,14 +1596,11 @@ static int coroutine_fn sd_co_rw_vector(void *p)
                      */
                     aio_req->flags = 0;
                     aio_req->base_oid = 0;
-                    QLIST_INSERT_HEAD(&s->pending_aio_head, aio_req,
-                                      aio_siblings);
                     goto done;
                 }
             }
         }
 
-        QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
         ret = add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
                               create, acb->aiocb_type);
         if (ret < 0) {
@@ -1641,7 +1615,7 @@ static int coroutine_fn sd_co_rw_vector(void *p)
         done += len;
     }
 out:
-    if (!--acb->nr_pending) {
+    if (QLIST_EMPTY(&acb->aioreq_head)) {
         return acb->ret;
     }
     return 1;
@@ -1654,6 +1628,7 @@ static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
     int ret;
 
     if (bs->growable && sector_num + nb_sectors > bs->total_sectors) {
+        /* TODO: shouldn't block here */
         ret = sd_truncate(bs, (sector_num + nb_sectors) * SECTOR_SIZE);
         if (ret < 0) {
             return ret;
@@ -1680,12 +1655,20 @@ static coroutine_fn int sd_co_readv(BlockDriverState *bs, int64_t sector_num,
                        int nb_sectors, QEMUIOVector *qiov)
 {
     SheepdogAIOCB *acb;
-    int ret;
+    int i, ret;
 
     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;
 
+    /*
+     * TODO: we can do better; we don't need to initialize
+     * blindly.
+     */
+    for (i = 0; i < qiov->niov; i++) {
+        memset(qiov->iov[i].iov_base, 0, qiov->iov[i].iov_len);
+    }
+
     ret = sd_co_rw_vector(acb);
     if (ret <= 0) {
         qemu_aio_release(acb);
@@ -1713,7 +1696,7 @@ static int coroutine_fn sd_co_flush_to_disk(BlockDriverState *bs)
     hdr.opcode = SD_OP_FLUSH_VDI;
     hdr.oid = vid_to_vdi_oid(inode->vdi_id);
 
-    ret = do_req(s->flush_fd, (SheepdogReq *)&hdr, NULL, &wlen, &rlen);
+    ret = do_co_req(s->flush_fd, (SheepdogReq *)&hdr, NULL, &wlen, &rlen);
     if (ret) {
         error_report("failed to send a request to the sheep");
         return ret;
@@ -1722,7 +1705,7 @@ static int coroutine_fn sd_co_flush_to_disk(BlockDriverState *bs)
     if (rsp->result == SD_RES_INVALID_PARMS) {
         dprintf("disable write cache since the server doesn't support it\n");
 
-        s->cache_enabled = false;
+        s->cache_enabled = 0;
         closesocket(s->flush_fd);
         return 0;
     }
@@ -1743,7 +1726,7 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     SheepdogInode *inode;
     unsigned int datalen;
 
-    dprintf("sn_info: name %s id_str %s s: name %s vm_state_size %" PRId64 " "
+    dprintf("sn_info: name %s id_str %s s: name %s vm_state_size %d "
             "is_snapshot %d\n", sn_info->name, sn_info->id_str,
             s->name, sn_info->vm_state_size, s->is_snapshot);
 
@@ -1758,9 +1741,6 @@ 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);
@@ -1773,7 +1753,7 @@ 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_enabled);
+                       s->inode.nr_copies, datalen, 0, 0, s->cache_enabled);
     if (ret < 0) {
         error_report("failed to write snapshot's inode.");
         goto cleanup;
@@ -1820,13 +1800,13 @@ 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);
@@ -1860,7 +1840,7 @@ 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);
@@ -1955,9 +1935,8 @@ 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++;
         }
     }
@@ -1978,8 +1957,8 @@ 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;
@@ -1994,7 +1973,7 @@ static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data,
         vdi_index = pos / SD_DATA_OBJ_SIZE;
         offset = pos % SD_DATA_OBJ_SIZE;
 
-        data_len = MIN(remaining, SD_DATA_OBJ_SIZE - offset);
+        data_len = MIN(remaining, SD_DATA_OBJ_SIZE);
 
         vmstate_oid = vid_to_vmstate_oid(s->inode.vdi_id, vdi_index);
 
@@ -2015,7 +1994,6 @@ static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data,
         }
 
         pos += data_len;
-        data += data_len;
         remaining -= data_len;
     }
     ret = size;

block/stream.c

@@ -13,8 +13,6 @@
 
 #include "trace.h"
 #include "block_int.h"
-#include "blockjob.h"
-#include "qemu/ratelimit.h"
 
 enum {
     /*
@@ -27,11 +25,38 @@ enum {
 
 #define SLICE_TIME 100000000ULL /* ns */
 
+typedef struct {
+    int64_t next_slice_time;
+    uint64_t slice_quota;
+    uint64_t dispatched;
+} RateLimit;
+
+static int64_t ratelimit_calculate_delay(RateLimit *limit, uint64_t n)
+{
+    int64_t now = qemu_get_clock_ns(rt_clock);
+
+    if (limit->next_slice_time < now) {
+        limit->next_slice_time = now + SLICE_TIME;
+        limit->dispatched = 0;
+    }
+    if (limit->dispatched == 0 || limit->dispatched + n <= limit->slice_quota) {
+        limit->dispatched += n;
+        return 0;
+    } else {
+        limit->dispatched = n;
+        return limit->next_slice_time - now;
+    }
+}
+
+static void ratelimit_set_speed(RateLimit *limit, uint64_t speed)
+{
+    limit->slice_quota = speed / (1000000000ULL / SLICE_TIME);
+}
+
 typedef struct StreamBlockJob {
     BlockJob common;
     RateLimit limit;
     BlockDriverState *base;
-    BlockdevOnError on_error;
     char backing_file_id[1024];
 } StreamBlockJob;
 
@@ -73,20 +98,80 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
     top->backing_hd = base;
 }
 
+/*
+ * Given an image chain: [BASE] -> [INTER1] -> [INTER2] -> [TOP]
+ *
+ * Return true if the given sector is allocated in top.
+ * Return false if the given sector is allocated in intermediate images.
+ * Return true otherwise.
+ *
+ * 'pnum' is set to the number of sectors (including and immediately following
+ *  the specified sector) that are known to be in the same
+ *  allocated/unallocated state.
+ *
+ */
+static int coroutine_fn is_allocated_base(BlockDriverState *top,
+                                          BlockDriverState *base,
+                                          int64_t sector_num,
+                                          int nb_sectors, int *pnum)
+{
+    BlockDriverState *intermediate;
+    int ret, n;
+
+    ret = bdrv_co_is_allocated(top, sector_num, nb_sectors, &n);
+    if (ret) {
+        *pnum = n;
+        return ret;
+    }
+
+    /*
+     * Is the unallocated chunk [sector_num, n] also
+     * unallocated between base and top?
+     */
+    intermediate = top->backing_hd;
+
+    while (intermediate != base) {
+        int pnum_inter;
+
+        ret = bdrv_co_is_allocated(intermediate, sector_num, nb_sectors,
+                                   &pnum_inter);
+        if (ret < 0) {
+            return ret;
+        } else if (ret) {
+            *pnum = pnum_inter;
+            return 0;
+        }
+
+        /*
+         * [sector_num, nb_sectors] is unallocated on top but intermediate
+         * might have
+         *
+         * [sector_num+x, nr_sectors] allocated.
+         */
+        if (n > pnum_inter) {
+            n = pnum_inter;
+        }
+
+        intermediate = intermediate->backing_hd;
+    }
+
+    *pnum = n;
+    return 1;
+}
+
 static void coroutine_fn stream_run(void *opaque)
 {
     StreamBlockJob *s = opaque;
     BlockDriverState *bs = s->common.bs;
     BlockDriverState *base = s->base;
     int64_t sector_num, end;
-    int error = 0;
     int ret = 0;
     int n = 0;
     void *buf;
 
     s->common.len = bdrv_getlength(bs);
     if (s->common.len < 0) {
-        block_job_completed(&s->common, s->common.len);
+        block_job_complete(&s->common, s->common.len);
         return;
     }
 
@@ -104,7 +189,6 @@ static void coroutine_fn stream_run(void *opaque)
 
     for (sector_num = 0; sector_num < end; sector_num += n) {
         uint64_t delay_ns = 0;
-        bool copy;
 
 wait:
         /* Note that even when no rate limit is applied we need to yield
@@ -115,26 +199,10 @@ wait:
             break;
         }
 
-        ret = bdrv_co_is_allocated(bs, sector_num,
-                                   STREAM_BUFFER_SIZE / BDRV_SECTOR_SIZE, &n);
-        if (ret == 1) {
-            /* Allocated in the top, no need to copy.  */
-            copy = false;
-        } else {
-            /* Copy if allocated in the intermediate images.  Limit to the
-             * known-unallocated area [sector_num, sector_num+n).  */
-            ret = bdrv_co_is_allocated_above(bs->backing_hd, base,
-                                             sector_num, n, &n);
-
-            /* Finish early if end of backing file has been reached */
-            if (ret == 0 && n == 0) {
-                n = end - sector_num;
-            }
-
-            copy = (ret == 1);
-        }
+        ret = is_allocated_base(bs, base, sector_num,
+                                STREAM_BUFFER_SIZE / BDRV_SECTOR_SIZE, &n);
         trace_stream_one_iteration(s, sector_num, n, ret);
-        if (ret >= 0 && copy) {
+        if (ret == 0) {
             if (s->common.speed) {
                 delay_ns = ratelimit_calculate_delay(&s->limit, n);
                 if (delay_ns > 0) {
@@ -144,19 +212,7 @@ wait:
             ret = stream_populate(bs, sector_num, n, buf);
         }
         if (ret < 0) {
-            BlockErrorAction action =
-                block_job_error_action(&s->common, s->common.bs, s->on_error,
-                                       true, -ret);
-            if (action == BDRV_ACTION_STOP) {
-                n = 0;
-                continue;
-            }
-            if (error == 0) {
-                error = ret;
-            }
-            if (action == BDRV_ACTION_REPORT) {
-                break;
-            }
+            break;
         }
         ret = 0;
 
@@ -168,9 +224,6 @@ wait:
         bdrv_disable_copy_on_read(bs);
     }
 
-    /* Do not remove the backing file if an error was there but ignored.  */
-    ret = error;
-
     if (!block_job_is_cancelled(&s->common) && sector_num == end && ret == 0) {
         const char *base_id = NULL, *base_fmt = NULL;
         if (base) {
@@ -184,7 +237,7 @@ wait:
     }
 
     qemu_vfree(buf);
-    block_job_completed(&s->common, ret);
+    block_job_complete(&s->common, ret);
 }
 
 static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -195,7 +248,7 @@ static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
         error_set(errp, QERR_INVALID_PARAMETER, "speed");
         return;
     }
-    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
+    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE);
 }
 
 static BlockJobType stream_job_type = {
@@ -206,19 +259,11 @@ 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 +274,6 @@ void stream_start(BlockDriverState *bs, BlockDriverState *base,
         pstrcpy(s->backing_file_id, sizeof(s->backing_file_id), base_id);
     }
 
-    s->on_error = on_error;
     s->common.co = qemu_coroutine_create(stream_run);
     trace_stream_start(bs, base, s, s->common.co, opaque);
     qemu_coroutine_enter(s->common.co, s);

block/vdi.c

@@ -60,6 +60,9 @@
 /* TODO: move uuid emulation to some central place in QEMU. */
 #include "sysemu.h"     /* UUID_FMT */
 typedef unsigned char uuid_t[16];
+void uuid_generate(uuid_t out);
+int uuid_is_null(const uuid_t uu);
+void uuid_unparse(const uuid_t uu, char *out);
 #endif
 
 /* Code configuration options. */
@@ -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],
@@ -274,8 +277,7 @@ static void vdi_header_print(VdiHeader *header)
 }
 #endif
 
-static int vdi_check(BlockDriverState *bs, BdrvCheckResult *res,
-                     BdrvCheckMode fix)
+static int vdi_check(BlockDriverState *bs, BdrvCheckResult *res)
 {
     /* TODO: additional checks possible. */
     BDRVVdiState *s = (BDRVVdiState *)bs->opaque;
@@ -284,10 +286,6 @@ static int vdi_check(BlockDriverState *bs, BdrvCheckResult *res,
     uint32_t *bmap;
     logout("\n");
 
-    if (fix) {
-        return -ENOTSUP;
-    }
-
     bmap = g_malloc(s->header.blocks_in_image * sizeof(uint32_t));
     memset(bmap, 0xff, s->header.blocks_in_image * sizeof(uint32_t));
 
@@ -451,12 +449,6 @@ static int vdi_open(BlockDriverState *bs, int flags)
     return -1;
 }
 
-static int vdi_reopen_prepare(BDRVReopenState *state,
-                              BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 static int coroutine_fn vdi_co_is_allocated(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *pnum)
 {
@@ -631,6 +623,7 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
     VdiHeader header;
     size_t i;
     size_t bmap_size;
+    uint32_t *bmap;
 
     logout("\n");
 
@@ -655,9 +648,8 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
         options++;
     }
 
-    fd = qemu_open(filename,
-                   O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
-                   0644);
+    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
+              0644);
     if (fd < 0) {
         return -errno;
     }
@@ -695,21 +687,21 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
         result = -errno;
     }
 
+    bmap = NULL;
     if (bmap_size > 0) {
-        uint32_t *bmap = g_malloc0(bmap_size);
-        for (i = 0; i < blocks; i++) {
-            if (image_type == VDI_TYPE_STATIC) {
-                bmap[i] = i;
-            } else {
-                bmap[i] = VDI_UNALLOCATED;
-            }
-        }
-        if (write(fd, bmap, bmap_size) < 0) {
-            result = -errno;
-        }
-        g_free(bmap);
+        bmap = (uint32_t *)g_malloc0(bmap_size);
     }
-
+    for (i = 0; i < blocks; i++) {
+        if (image_type == VDI_TYPE_STATIC) {
+            bmap[i] = i;
+        } else {
+            bmap[i] = VDI_UNALLOCATED;
+        }
+    }
+    if (write(fd, bmap, bmap_size) < 0) {
+        result = -errno;
+    }
+    g_free(bmap);
     if (image_type == VDI_TYPE_STATIC) {
         if (ftruncate(fd, sizeof(header) + bmap_size + blocks * block_size)) {
             result = -errno;
@@ -764,7 +756,6 @@ 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

@@ -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;
@@ -1092,7 +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;
 
@@ -1104,9 +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;
@@ -1157,7 +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;
 
@@ -1200,9 +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;
@@ -1257,9 +1217,10 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
     VMDK4Header header;
     uint32_t tmp, magic, grains, gd_size, gt_size, gt_count;
 
-    fd = qemu_open(filename,
-                   O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
-                   0644);
+    fd = open(
+        filename,
+        O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
+        0644);
     if (fd < 0) {
         return -errno;
     }
@@ -1354,7 +1315,7 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
 
     ret = 0;
  exit:
-    qemu_close(fd);
+    close(fd);
     return ret;
 }
 
@@ -1414,7 +1375,8 @@ 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]) {
@@ -1578,13 +1540,15 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
             (flags & BLOCK_FLAG_COMPAT6 ? 6 : 4),
             total_size / (int64_t)(63 * 16 * 512));
     if (split || flat) {
-        fd = qemu_open(filename,
-                       O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
-                       0644);
+        fd = open(
+                filename,
+                O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
+                0644);
     } else {
-        fd = qemu_open(filename,
-                       O_WRONLY | O_BINARY | O_LARGEFILE,
-                       0644);
+        fd = open(
+                filename,
+                O_WRONLY | O_BINARY | O_LARGEFILE,
+                0644);
     }
     if (fd < 0) {
         return -errno;
@@ -1601,7 +1565,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
     }
     ret = 0;
 exit:
-    qemu_close(fd);
+    close(fd);
     return ret;
 }
 
@@ -1685,7 +1649,6 @@ 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

@@ -265,12 +265,6 @@ static int vpc_open(BlockDriverState *bs, int flags)
     return err;
 }
 
-static int vpc_reopen_prepare(BDRVReopenState *state,
-                              BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 /*
  * Returns the absolute byte offset of the given sector in the image file.
  * If the sector is not allocated, -1 is returned instead.
@@ -684,7 +678,7 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options)
     }
 
     /* Create the file */
-    fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
+    fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
     if (fd < 0) {
         return -EIO;
     }
@@ -750,7 +744,7 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options)
     }
 
  fail:
-    qemu_close(fd);
+    close(fd);
     return ret;
 }
 
@@ -789,7 +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

@@ -359,12 +359,11 @@ typedef struct BDRVVVFATState {
  * if the position is outside the specified geometry, fill maximum value for CHS
  * and return 1 to signal overflow.
  */
-static int sector2CHS(mbr_chs_t *chs, int spos, int cyls, int heads, int secs)
-{
+static int sector2CHS(BlockDriverState* bs, mbr_chs_t * chs, int spos){
     int head,sector;
-    sector   = spos % secs;  spos /= secs;
-    head     = spos % heads; spos /= heads;
-    if (spos >= cyls) {
+    sector   = spos % (bs->secs);  spos/= bs->secs;
+    head     = spos % (bs->heads); spos/= bs->heads;
+    if(spos >= bs->cyls){
         /* Overflow,
         it happens if 32bit sector positions are used, while CHS is only 24bit.
         Windows/Dos is said to take 1023/255/63 as nonrepresentable CHS */
@@ -379,7 +378,7 @@ static int sector2CHS(mbr_chs_t *chs, int spos, int cyls, int heads, int secs)
     return 0;
 }
 
-static void init_mbr(BDRVVVFATState *s, int cyls, int heads, int secs)
+static void init_mbr(BDRVVVFATState* s)
 {
     /* TODO: if the files mbr.img and bootsect.img exist, use them */
     mbr_t* real_mbr=(mbr_t*)s->first_sectors;
@@ -394,15 +393,12 @@ static void init_mbr(BDRVVVFATState *s, int cyls, int heads, int secs)
     partition->attributes=0x80; /* bootable */
 
     /* LBA is used when partition is outside the CHS geometry */
-    lba  = sector2CHS(&partition->start_CHS, s->first_sectors_number - 1,
-                     cyls, heads, secs);
-    lba |= sector2CHS(&partition->end_CHS,   s->bs->total_sectors - 1,
-                     cyls, heads, secs);
+    lba = sector2CHS(s->bs, &partition->start_CHS, s->first_sectors_number-1);
+    lba|= sector2CHS(s->bs, &partition->end_CHS,   s->sector_count);
 
     /*LBA partitions are identified only by start/length_sector_long not by CHS*/
-    partition->start_sector_long  = cpu_to_le32(s->first_sectors_number - 1);
-    partition->length_sector_long = cpu_to_le32(s->bs->total_sectors
-                                                - s->first_sectors_number + 1);
+    partition->start_sector_long =cpu_to_le32(s->first_sectors_number-1);
+    partition->length_sector_long=cpu_to_le32(s->sector_count - s->first_sectors_number+1);
 
     /* FAT12/FAT16/FAT32 */
     /* DOS uses different types when partition is LBA,
@@ -834,7 +830,7 @@ static inline off_t cluster2sector(BDRVVVFATState* s, uint32_t cluster_num)
 }
 
 static int init_directories(BDRVVVFATState* s,
-                            const char *dirname, int heads, int secs)
+	const char* dirname)
 {
     bootsector_t* bootsector;
     mapping_t* mapping;
@@ -961,8 +957,8 @@ static int init_directories(BDRVVVFATState* s,
     bootsector->media_type=(s->first_sectors_number>1?0xf8:0xf0); /* media descriptor (f8=hd, f0=3.5 fd)*/
     s->fat.pointer[0] = bootsector->media_type;
     bootsector->sectors_per_fat=cpu_to_le16(s->sectors_per_fat);
-    bootsector->sectors_per_track = cpu_to_le16(secs);
-    bootsector->number_of_heads = cpu_to_le16(heads);
+    bootsector->sectors_per_track=cpu_to_le16(s->bs->secs);
+    bootsector->number_of_heads=cpu_to_le16(s->bs->heads);
     bootsector->hidden_sectors=cpu_to_le32(s->first_sectors_number==1?0:0x3f);
     bootsector->total_sectors=cpu_to_le32(s->sector_count>0xffff?s->sector_count:0);
 
@@ -995,7 +991,7 @@ static void vvfat_rebind(BlockDriverState *bs)
 static int vvfat_open(BlockDriverState *bs, const char* dirname, int flags)
 {
     BDRVVVFATState *s = bs->opaque;
-    int i, cyls, heads, secs;
+    int i;
 
 #ifdef DEBUG
     vvv = s;
@@ -1037,28 +1033,24 @@ DLOG(if (stderr == NULL) {
 	/* 1.44MB or 2.88MB floppy.  2.88MB can be FAT12 (default) or FAT16. */
 	if (!s->fat_type) {
 	    s->fat_type = 12;
-            secs = 36;
+	    bs->secs = 36;
 	    s->sectors_per_cluster=2;
 	} else {
-            secs = s->fat_type == 12 ? 18 : 36;
+	    bs->secs=(s->fat_type == 12 ? 18 : 36);
 	    s->sectors_per_cluster=1;
 	}
 	s->first_sectors_number = 1;
-        cyls = 80;
-        heads = 2;
+	bs->cyls=80; bs->heads=2;
     } else {
 	/* 32MB or 504MB disk*/
 	if (!s->fat_type) {
 	    s->fat_type = 16;
 	}
-        cyls = s->fat_type == 12 ? 64 : 1024;
-        heads = 16;
-        secs = 63;
+	bs->cyls=(s->fat_type == 12 ? 64 : 1024);
+	bs->heads=16; bs->secs=63;
     }
-    fprintf(stderr, "vvfat %s chs %d,%d,%d\n",
-            dirname, cyls, heads, secs);
 
-    s->sector_count = cyls * heads * secs - (s->first_sectors_number - 1);
+    s->sector_count=bs->cyls*bs->heads*bs->secs-(s->first_sectors_number-1);
 
     if (strstr(dirname, ":rw:")) {
 	if (enable_write_target(s))
@@ -1074,16 +1066,18 @@ DLOG(if (stderr == NULL) {
     else
 	dirname += i+1;
 
-    bs->total_sectors = cyls * heads * secs;
+    bs->total_sectors=bs->cyls*bs->heads*bs->secs;
 
-    if (init_directories(s, dirname, heads, secs)) {
+    if(init_directories(s, dirname))
 	return -1;
-    }
 
     s->sector_count = s->faked_sectors + s->sectors_per_cluster*s->cluster_count;
 
-    if (s->first_sectors_number == 0x40) {
-        init_mbr(s, cyls, heads, secs);
+    if(s->first_sectors_number==0x40)
+	init_mbr(s);
+    else {
+        /* MS-DOS does not like to know about CHS (?). */
+	bs->heads = bs->cyls = bs->secs = 0;
     }
 
     //    assert(is_consistent(s));
@@ -1105,7 +1099,7 @@ static inline void vvfat_close_current_file(BDRVVVFATState *s)
     if(s->current_mapping) {
 	s->current_mapping = NULL;
 	if (s->current_fd) {
-		qemu_close(s->current_fd);
+		close(s->current_fd);
 		s->current_fd = 0;
 	}
     }
@@ -1162,7 +1156,7 @@ static int open_file(BDRVVVFATState* s,mapping_t* mapping)
     if(!s->current_mapping ||
 	    strcmp(s->current_mapping->path,mapping->path)) {
 	/* open file */
-	int fd = qemu_open(mapping->path, O_RDONLY | O_BINARY | O_LARGEFILE);
+	int fd = open(mapping->path, O_RDONLY | O_BINARY | O_LARGEFILE);
 	if(fd<0)
 	    return -1;
 	vvfat_close_current_file(s);
@@ -2221,7 +2215,7 @@ static int commit_one_file(BDRVVVFATState* s,
     for (i = s->cluster_size; i < offset; i += s->cluster_size)
 	c = modified_fat_get(s, c);
 
-    fd = qemu_open(mapping->path, O_RDWR | O_CREAT | O_BINARY, 0666);
+    fd = open(mapping->path, O_RDWR | O_CREAT | O_BINARY, 0666);
     if (fd < 0) {
 	fprintf(stderr, "Could not open %s... (%s, %d)\n", mapping->path,
 		strerror(errno), errno);
@@ -2230,7 +2224,7 @@ static int commit_one_file(BDRVVVFATState* s,
     }
     if (offset > 0) {
         if (lseek(fd, offset, SEEK_SET) != offset) {
-            qemu_close(fd);
+            close(fd);
             g_free(cluster);
             return -3;
         }
@@ -2251,13 +2245,13 @@ static int commit_one_file(BDRVVVFATState* s,
 	    (uint8_t*)cluster, (rest_size + 0x1ff) / 0x200);
 
         if (ret < 0) {
-            qemu_close(fd);
+            close(fd);
             g_free(cluster);
             return ret;
         }
 
         if (write(fd, cluster, rest_size) < 0) {
-            qemu_close(fd);
+            close(fd);
             g_free(cluster);
             return -2;
         }
@@ -2268,11 +2262,11 @@ static int commit_one_file(BDRVVVFATState* s,
 
     if (ftruncate(fd, size)) {
         perror("ftruncate()");
-        qemu_close(fd);
+        close(fd);
         g_free(cluster);
         return -4;
     }
-    qemu_close(fd);
+    close(fd);
     g_free(cluster);
 
     return commit_mappings(s, first_cluster, dir_index);

block/win32-aio.c

@@ -1,226 +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_int.h"
-#include "module.h"
-#include "qemu-common.h"
-#include "qemu-aio.h"
-#include "raw-aio.h"
-#include "event_notifier.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;
-            char *p = waiocb->buf;
-            int i;
-
-            for (i = 0; i < qiov->niov; ++i) {
-                memcpy(qiov->iov[i].iov_base, p, qiov->iov[i].iov_len);
-                p += qiov->iov[i].iov_len;
-            }
-        }
-        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) {
-            char *p = waiocb->buf;
-            int i;
-
-            for (i = 0; i < qiov->niov; ++i) {
-                memcpy(p, qiov->iov[i].iov_base, qiov->iov[i].iov_len);
-                p += qiov->iov[i].iov_len;
-            }
-        }
-        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

@@ -30,12 +30,9 @@
 #include "qemu-coroutine.h"
 #include "qemu-timer.h"
 #include "qapi-types.h"
-#include "qerror.h"
-#include "monitor.h"
 
-#define BLOCK_FLAG_ENCRYPT          1
-#define BLOCK_FLAG_COMPAT6          4
-#define BLOCK_FLAG_LAZY_REFCOUNTS   8
+#define BLOCK_FLAG_ENCRYPT	1
+#define BLOCK_FLAG_COMPAT6	4
 
 #define BLOCK_IO_LIMIT_READ     0
 #define BLOCK_IO_LIMIT_WRITE    1
@@ -44,17 +41,16 @@
 #define BLOCK_IO_SLICE_TIME     100000000
 #define NANOSECONDS_PER_SECOND  1000000000.0
 
-#define BLOCK_OPT_SIZE              "size"
-#define BLOCK_OPT_ENCRYPT           "encryption"
-#define BLOCK_OPT_COMPAT6           "compat6"
-#define BLOCK_OPT_BACKING_FILE      "backing_file"
-#define BLOCK_OPT_BACKING_FMT       "backing_fmt"
-#define BLOCK_OPT_CLUSTER_SIZE      "cluster_size"
-#define BLOCK_OPT_TABLE_SIZE        "table_size"
-#define BLOCK_OPT_PREALLOC          "preallocation"
-#define BLOCK_OPT_SUBFMT            "subformat"
-#define BLOCK_OPT_COMPAT_LEVEL      "compat"
-#define BLOCK_OPT_LAZY_REFCOUNTS    "lazy_refcounts"
+#define BLOCK_OPT_SIZE          "size"
+#define BLOCK_OPT_ENCRYPT       "encryption"
+#define BLOCK_OPT_COMPAT6       "compat6"
+#define BLOCK_OPT_BACKING_FILE  "backing_file"
+#define BLOCK_OPT_BACKING_FMT   "backing_fmt"
+#define BLOCK_OPT_CLUSTER_SIZE  "cluster_size"
+#define BLOCK_OPT_TABLE_SIZE    "table_size"
+#define BLOCK_OPT_PREALLOC      "preallocation"
+#define BLOCK_OPT_SUBFMT        "subformat"
+#define BLOCK_OPT_COMPAT_LEVEL  "compat"
 
 typedef struct BdrvTrackedRequest BdrvTrackedRequest;
 
@@ -68,18 +64,78 @@ 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,
@@ -185,8 +241,7 @@ struct BlockDriver {
      * Returns 0 for completed check, -errno for internal errors.
      * The check results are stored in result.
      */
-    int (*bdrv_check)(BlockDriverState* bs, BdrvCheckResult *result,
-        BdrvCheckMode fix);
+    int (*bdrv_check)(BlockDriverState* bs, BdrvCheckResult *result);
 
     void (*bdrv_debug_event)(BlockDriverState *bs, BlkDebugEvent event);
 
@@ -209,6 +264,7 @@ 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 */
@@ -233,8 +289,6 @@ 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;
 
@@ -265,7 +319,8 @@ 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;
+    int cyls, heads, secs, translation;
+    BlockErrorAction on_read_error, on_write_error;
     bool iostatus_enabled;
     BlockDeviceIoStatus iostatus;
     char device_name[32];
@@ -278,7 +333,6 @@ struct BlockDriverState {
 
     /* long-running background operation */
     BlockJob *job;
-
 };
 
 int get_tmp_filename(char *filename, int size);
@@ -289,9 +343,92 @@ 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:
@@ -301,7 +438,6 @@ 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.
@@ -313,47 +449,7 @@ 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.
- * @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, 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 "blockdev.h"
-#include "hw/block-common.h"
-#include "monitor.h"
-#include "qerror.h"
-#include "sysemu.h"
-#include "qmp-commands.h"
-#include "trace.h"
-#include "nbd.h"
-#include "qemu_socket.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

@@ -7,9 +7,8 @@
  * later.  See the COPYING file in the top-level directory.
  */
 
+#include "block.h"
 #include "blockdev.h"
-#include "hw/block-common.h"
-#include "blockjob.h"
 #include "monitor.h"
 #include "qerror.h"
 #include "qemu-option.h"
@@ -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");
@@ -279,6 +278,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 {
     const char *buf;
     const char *file = NULL;
+    char devname[128];
     const char *serial;
     const char *mediastr = "";
     BlockInterfaceType type;
@@ -318,6 +318,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
     serial = qemu_opt_get(opts, "serial");
 
     if ((buf = qemu_opt_get(opts, "if")) != NULL) {
+        pstrcpy(devname, sizeof(devname), buf);
         for (type = 0; type < IF_COUNT && strcmp(buf, if_name[type]); type++)
             ;
         if (type == IF_COUNT) {
@@ -326,20 +327,21 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 	}
     } else {
         type = default_to_scsi ? IF_SCSI : IF_IDE;
+        pstrcpy(devname, sizeof(devname), if_name[type]);
     }
 
     max_devs = if_max_devs[type];
 
     if (cyls || heads || secs) {
-        if (cyls < 1) {
+        if (cyls < 1 || (type == IF_IDE && cyls > 16383)) {
             error_report("invalid physical cyls number");
 	    return NULL;
 	}
-        if (heads < 1) {
+        if (heads < 1 || (type == IF_IDE && heads > 16)) {
             error_report("invalid physical heads number");
 	    return NULL;
 	}
-        if (secs < 1) {
+        if (secs < 1 || (type == IF_IDE && secs > 63)) {
             error_report("invalid physical secs number");
 	    return NULL;
 	}
@@ -378,7 +380,6 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 	}
     }
 
-    bdrv_flags |= BDRV_O_CACHE_WB;
     if ((buf = qemu_opt_get(opts, "cache")) != NULL) {
         if (bdrv_parse_cache_flags(buf, &bdrv_flags) != 0) {
             error_report("invalid cache option");
@@ -400,11 +401,11 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 #endif
 
     if ((buf = qemu_opt_get(opts, "format")) != NULL) {
-        if (is_help_option(buf)) {
-            error_printf("Supported formats:");
-            bdrv_iterate_format(bdrv_format_print, NULL);
-            error_printf("\n");
-            return NULL;
+       if (strcmp(buf, "?") == 0) {
+           error_printf("Supported formats:");
+           bdrv_iterate_format(bdrv_format_print, NULL);
+           error_printf("\n");
+           return NULL;
         }
         drv = bdrv_find_whitelisted_format(buf);
         if (!drv) {
@@ -433,13 +434,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
         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 +447,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
         }
     }
 
-    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");
@@ -528,25 +523,21 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
             mediastr = (media == MEDIA_CDROM) ? "-cd" : "-hd";
         if (max_devs)
             snprintf(dinfo->id, 32, "%s%i%s%i",
-                     if_name[type], bus_id, mediastr, unit_id);
+                     devname, bus_id, mediastr, unit_id);
         else
             snprintf(dinfo->id, 32, "%s%s%i",
-                     if_name[type], mediastr, unit_id);
+                     devname, mediastr, unit_id);
     }
     dinfo->bdrv = bdrv_new(dinfo->id);
-    dinfo->bdrv->open_flags = snapshot ? BDRV_O_SNAPSHOT : 0;
-    dinfo->bdrv->read_only = ro;
     dinfo->devaddr = devaddr;
     dinfo->type = type;
     dinfo->bus = bus_id;
     dinfo->unit = unit_id;
-    dinfo->cyls = cyls;
-    dinfo->heads = heads;
-    dinfo->secs = secs;
-    dinfo->trans = translation;
     dinfo->opts = opts;
     dinfo->refcount = 1;
-    dinfo->serial = serial;
+    if (serial) {
+        pstrcpy(dinfo->serial, sizeof(dinfo->serial), serial);
+    }
     QTAILQ_INSERT_TAIL(&drives, dinfo, next);
 
     bdrv_set_on_error(dinfo->bdrv, on_read_error, on_write_error);
@@ -559,7 +550,17 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
     case IF_SCSI:
     case IF_XEN:
     case IF_NONE:
-        dinfo->media_cd = media == MEDIA_CDROM;
+        switch(media) {
+	case MEDIA_DISK:
+            if (cyls != 0) {
+                bdrv_set_geometry_hint(dinfo->bdrv, cyls, heads, secs);
+                bdrv_set_translation_hint(dinfo->bdrv, translation);
+            }
+	    break;
+	case MEDIA_CDROM:
+            dinfo->media_cd = 1;
+	    break;
+	}
         break;
     case IF_SD:
     case IF_FLOPPY:
@@ -568,7 +569,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
         break;
     case IF_VIRTIO:
         /* add virtio block device */
-        opts = qemu_opts_create(qemu_find_opts("device"), NULL, 0, NULL);
+        opts = qemu_opts_create(qemu_find_opts("device"), NULL, 0);
         if (arch_type == QEMU_ARCH_S390X) {
             qemu_opt_set(opts, "driver", "virtio-blk-s390");
         } else {
@@ -611,10 +612,6 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
 
     bdrv_flags |= ro ? 0 : BDRV_O_RDWR;
 
-    if (ro && copy_on_read) {
-        error_report("warning: disabling copy_on_read on readonly drive");
-    }
-
     ret = bdrv_open(dinfo->bdrv, file, bdrv_flags, drv);
     if (ret < 0) {
         error_report("could not open disk image %s: %s",
@@ -812,11 +809,6 @@ 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 */
@@ -836,6 +828,7 @@ exit:
     QSIMPLEQ_FOREACH_SAFE(states, &snap_bdrv_states, entry, next) {
         g_free(states);
     }
+    return;
 }
 
 
@@ -1062,12 +1055,26 @@ 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);
@@ -1087,18 +1094,13 @@ 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);
@@ -1114,7 +1116,7 @@ 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;
@@ -1128,199 +1130,6 @@ 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));
-}
-
-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_on_source_error, BlockdevOnError on_source_error,
-                      bool has_on_target_error, BlockdevOnError on_target_error,
-                      Error **errp)
-{
-    BlockDriverInfo bdi;
-    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;
-    }
-
-    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;
-    }
-
-    if (sync == MIRROR_SYNC_MODE_FULL && mode != NEW_IMAGE_MODE_EXISTING) {
-        /* create new image w/o backing file */
-        assert(format && drv);
-        bdrv_get_geometry(bs, &size);
-        size *= 512;
-        ret = bdrv_img_create(target, format,
-                              NULL, NULL, NULL, size, flags);
-    } else {
-        switch (mode) {
-        case NEW_IMAGE_MODE_EXISTING:
-            ret = 0;
-            break;
-        case NEW_IMAGE_MODE_ABSOLUTE_PATHS:
-            /* create new image with backing file */
-            ret = bdrv_img_create(target, format,
-                                  source->filename,
-                                  source->drv->format_name,
-                                  NULL, -1, flags);
-            break;
-        default:
-            abort();
-        }
-    }
-
-    if (ret) {
-        error_set(errp, QERR_OPEN_FILE_FAILED, target);
-        return;
-    }
-
-    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;
-    }
-
-    /* We need a backing file if we will copy parts of a cluster.  */
-    if (bdrv_get_info(target_bs, &bdi) >= 0 && bdi.cluster_size != 0 &&
-        bdi.cluster_size >= BDRV_SECTORS_PER_DIRTY_CHUNK * 512) {
-        ret = bdrv_open_backing_file(target_bs);
-        if (ret < 0) {
-            bdrv_delete(target_bs);
-            error_set(errp, QERR_OPEN_FILE_FAILED, target);
-            return;
-        }
-    }
-
-    mirror_start(bs, target_bs, speed, 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;
@@ -1337,28 +1146,19 @@ 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;
     }
 
@@ -1366,53 +1166,25 @@ 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;
     }

blockdev.h

@@ -17,6 +17,8 @@
 void blockdev_mark_auto_del(BlockDriverState *bs);
 void blockdev_auto_del(BlockDriverState *bs);
 
+#define BLOCK_SERIAL_STRLEN 20
+
 typedef enum {
     IF_DEFAULT = -1,            /* for use with drive_add() only */
     IF_NONE,
@@ -33,9 +35,8 @@ struct DriveInfo {
     int unit;
     int auto_del;               /* see blockdev_mark_auto_del() */
     int media_cd;
-    int cyls, heads, secs, trans;
     QemuOpts *opts;
-    const char *serial;
+    char serial[BLOCK_SERIAL_STRLEN + 1];
     QTAILQ_ENTRY(DriveInfo) next;
     int refcount;
 };

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.h"
-#include "block.h"
-#include "blockjob.h"
-#include "block_int.h"
-#include "qjson.h"
-#include "qemu-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;
-}

blockjob.h

@@ -1,278 +0,0 @@
-/*
- * Declarations for long-running block device operations
- *
- * 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.
- */
-#ifndef BLOCKJOB_H
-#define BLOCKJOB_H 1
-
-#include "block.h"
-
-/**
- * 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);
-
-    /** Optional callback for job types that need to forward I/O status reset */
-    void (*iostatus_reset)(BlockJob *job);
-
-    /**
-     * Optional callback for job types whose completion must be triggered
-     * manually.
-     */
-    void (*complete)(BlockJob *job, 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 true if the job is either paused, or will pause itself
-     * as soon as possible (if busy == true).
-     */
-    bool paused;
-
-    /**
-     * 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;
-
-    /** Status that is published by the query-block-jobs QMP API */
-    BlockDeviceIoStatus iostatus;
-
-    /** 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;
-};
-
-/**
- * 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_completed:
- * @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_completed(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_complete:
- * @job: The job to be completed.
- * @errp: Error object.
- *
- * Asynchronously complete the specified job.
- */
-void block_job_complete(BlockJob *job, Error **errp);
-
-/**
- * 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_query:
- * @job: The job to get information about.
- *
- * Return information about a job.
- */
-BlockJobInfo *block_job_query(BlockJob *job);
-
-/**
- * block_job_pause:
- * @job: The job to be paused.
- *
- * Asynchronously pause the specified job.
- */
-void block_job_pause(BlockJob *job);
-
-/**
- * block_job_resume:
- * @job: The job to be resumed.
- *
- * Resume the specified job.
- */
-void block_job_resume(BlockJob *job);
-
-/**
- * qobject_from_block_job:
- * @job: The job whose information is requested.
- *
- * Return a QDict corresponding to @job's query-block-jobs entry.
- */
-QObject *qobject_from_block_job(BlockJob *job);
-
-/**
- * block_job_ready:
- * @job: The job which is now ready to complete.
- *
- * Send a BLOCK_JOB_READY event for the specified job.
- */
-void block_job_ready(BlockJob *job);
-
-/**
- * block_job_is_paused:
- * @job: The job being queried.
- *
- * Returns whether the job is currently paused, or will pause
- * as soon as it reaches a sleeping point.
- */
-bool block_job_is_paused(BlockJob *job);
-
-/**
- * block_job_cancel_sync:
- * @job: The job to be canceled.
- *
- * Synchronously cancel the job.  The completion callback is called
- * before the function returns.  The job may actually complete
- * instead of canceling itself; the circumstances under which this
- * happens depend on the kind of job that is active.
- *
- * 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);
-
-/**
- * block_job_iostatus_reset:
- * @job: The job whose I/O status should be reset.
- *
- * Reset I/O status on @job and on BlockDriverState objects it uses,
- * other than job->bs.
- */
-void block_job_iostatus_reset(BlockJob *job);
-
-/**
- * block_job_error_action:
- * @job: The job to signal an error for.
- * @bs: The block device on which to set an I/O error.
- * @on_err: The error action setting.
- * @is_read: Whether the operation was a read.
- * @error: The error that was reported.
- *
- * Report an I/O error for a block job and possibly stop the VM.  Return the
- * action that was selected based on @on_err and @error.
- */
-BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
-                                        BlockdevOnError on_err,
-                                        int is_read, int error);
-#endif

bsd-user/Makefile.objs

@@ -1,2 +0,0 @@
-obj-y = main.o bsdload.o elfload.o mmap.o signal.o strace.o syscall.o \
-	        uaccess.o

bsd-user/main.c

@@ -681,7 +681,7 @@ static void usage(void)
            "-g port           wait gdb connection to port\n"
            "-L path           set the elf interpreter prefix (default=%s)\n"
            "-s size           set the stack size in bytes (default=%ld)\n"
-           "-cpu model        select CPU (-cpu help for list)\n"
+           "-cpu model        select CPU (-cpu ? for list)\n"
            "-drop-ld-preload  drop LD_PRELOAD for target process\n"
            "-E var=value      sets/modifies targets environment variable(s)\n"
            "-U var            unsets targets environment variable(s)\n"
@@ -825,7 +825,7 @@ int main(int argc, char **argv)
             qemu_uname_release = argv[optind++];
         } else if (!strcmp(r, "cpu")) {
             cpu_model = argv[optind++];
-            if (is_help_option(cpu_model)) {
+            if (strcmp(cpu_model, "?") == 0) {
 /* XXX: implement xxx_cpu_list for targets that still miss it */
 #if defined(cpu_list)
                     cpu_list(stdout, &fprintf);
@@ -918,7 +918,7 @@ int main(int argc, char **argv)
         exit(1);
     }
 #if defined(TARGET_I386) || defined(TARGET_SPARC) || defined(TARGET_PPC)
-    cpu_reset(ENV_GET_CPU(env));
+    cpu_state_reset(env);
 #endif
     thread_env = env;
 

buffered_file.c

@@ -23,7 +23,11 @@
 
 typedef struct QEMUFileBuffered
 {
-    MigrationState *migration_state;
+    BufferedPutFunc *put_buffer;
+    BufferedPutReadyFunc *put_ready;
+    BufferedWaitForUnfreezeFunc *wait_for_unfreeze;
+    BufferedCloseFunc *close;
+    void *opaque;
     QEMUFile *file;
     int freeze_output;
     size_t bytes_xfer;
@@ -46,60 +50,70 @@ static void buffered_append(QEMUFileBuffered *s,
                             const uint8_t *buf, size_t size)
 {
     if (size > (s->buffer_capacity - s->buffer_size)) {
+        void *tmp;
+
         DPRINTF("increasing buffer capacity from %zu by %zu\n",
                 s->buffer_capacity, size + 1024);
 
         s->buffer_capacity += size + 1024;
 
-        s->buffer = g_realloc(s->buffer, s->buffer_capacity);
+        tmp = g_realloc(s->buffer, s->buffer_capacity);
+        if (tmp == NULL) {
+            fprintf(stderr, "qemu file buffer expansion failed\n");
+            exit(1);
+        }
+
+        s->buffer = tmp;
     }
 
     memcpy(s->buffer + s->buffer_size, buf, size);
     s->buffer_size += size;
 }
 
-static ssize_t buffered_flush(QEMUFileBuffered *s)
+static void buffered_flush(QEMUFileBuffered *s)
 {
     size_t offset = 0;
-    ssize_t ret = 0;
+    int error;
+
+    error = qemu_file_get_error(s->file);
+    if (error != 0) {
+        DPRINTF("flush when error, bailing: %s\n", strerror(-error));
+        return;
+    }
 
     DPRINTF("flushing %zu byte(s) of data\n", s->buffer_size);
 
-    while (s->bytes_xfer < s->xfer_limit && offset < s->buffer_size) {
-        size_t to_send = MIN(s->buffer_size - offset, s->xfer_limit - s->bytes_xfer);
-        ret = migrate_fd_put_buffer(s->migration_state, s->buffer + offset,
-                                    to_send);
+    while (offset < s->buffer_size) {
+        ssize_t ret;
+
+        ret = s->put_buffer(s->opaque, s->buffer + offset,
+                            s->buffer_size - offset);
         if (ret == -EAGAIN) {
             DPRINTF("backend not ready, freezing\n");
-            ret = 0;
             s->freeze_output = 1;
             break;
         }
 
         if (ret <= 0) {
             DPRINTF("error flushing data, %zd\n", ret);
+            qemu_file_set_error(s->file, ret);
             break;
         } else {
             DPRINTF("flushed %zd byte(s)\n", ret);
             offset += ret;
-            s->bytes_xfer += ret;
         }
     }
 
     DPRINTF("flushed %zu of %zu byte(s)\n", offset, s->buffer_size);
     memmove(s->buffer, s->buffer + offset, s->buffer_size - offset);
     s->buffer_size -= offset;
-
-    if (ret < 0) {
-        return ret;
-    }
-    return offset;
 }
 
 static int buffered_put_buffer(void *opaque, const uint8_t *buf, int64_t pos, int size)
 {
     QEMUFileBuffered *s = opaque;
-    ssize_t error;
+    int offset = 0, error;
+    ssize_t ret;
 
     DPRINTF("putting %d bytes at %" PRId64 "\n", size, pos);
 
@@ -112,54 +126,65 @@ static int buffered_put_buffer(void *opaque, const uint8_t *buf, int64_t pos, in
     DPRINTF("unfreezing output\n");
     s->freeze_output = 0;
 
-    if (size > 0) {
-        DPRINTF("buffering %d bytes\n", size - offset);
-        buffered_append(s, buf, size);
+    buffered_flush(s);
+
+    while (!s->freeze_output && offset < size) {
+        if (s->bytes_xfer > s->xfer_limit) {
+            DPRINTF("transfer limit exceeded when putting\n");
+            break;
+        }
+
+        ret = s->put_buffer(s->opaque, buf + offset, size - offset);
+        if (ret == -EAGAIN) {
+            DPRINTF("backend not ready, freezing\n");
+            s->freeze_output = 1;
+            break;
+        }
+
+        if (ret <= 0) {
+            DPRINTF("error putting\n");
+            qemu_file_set_error(s->file, ret);
+            offset = -EINVAL;
+            break;
+        }
+
+        DPRINTF("put %zd byte(s)\n", ret);
+        offset += ret;
+        s->bytes_xfer += ret;
     }
 
-    error = buffered_flush(s);
-    if (error < 0) {
-        DPRINTF("buffered flush error. bailing: %s\n", strerror(-error));
-        return error;
+    if (offset >= 0) {
+        DPRINTF("buffering %d bytes\n", size - offset);
+        buffered_append(s, buf + offset, size - offset);
+        offset = size;
     }
 
     if (pos == 0 && size == 0) {
         DPRINTF("file is ready\n");
-        if (!s->freeze_output && s->bytes_xfer < s->xfer_limit) {
+        if (s->bytes_xfer <= s->xfer_limit) {
             DPRINTF("notifying client\n");
-            migrate_fd_put_ready(s->migration_state);
+            s->put_ready(s->opaque);
         }
     }
 
-    return size;
+    return offset;
 }
 
 static int buffered_close(void *opaque)
 {
     QEMUFileBuffered *s = opaque;
-    ssize_t ret = 0;
-    int ret2;
+    int ret;
 
     DPRINTF("closing\n");
 
-    s->xfer_limit = INT_MAX;
     while (!qemu_file_get_error(s->file) && s->buffer_size) {
-        ret = buffered_flush(s);
-        if (ret < 0) {
-            break;
-        }
-        if (s->freeze_output) {
-            ret = migrate_fd_wait_for_unfreeze(s->migration_state);
-            if (ret < 0) {
-                break;
-            }
-        }
+        buffered_flush(s);
+        if (s->freeze_output)
+            s->wait_for_unfreeze(s->opaque);
     }
 
-    ret2 = migrate_fd_close(s->migration_state);
-    if (ret >= 0) {
-        ret = ret2;
-    }
+    ret = s->close(s->opaque);
+
     qemu_del_timer(s->timer);
     qemu_free_timer(s->timer);
     g_free(s->buffer);
@@ -174,13 +199,6 @@ static int buffered_close(void *opaque)
  *   1: Time to stop
  *   negative: There has been an error
  */
-static int buffered_get_fd(void *opaque)
-{
-    QEMUFileBuffered *s = opaque;
-
-    return qemu_get_fd(s->file);
-}
-
 static int buffered_rate_limit(void *opaque)
 {
     QEMUFileBuffered *s = opaque;
@@ -238,28 +256,34 @@ static void buffered_rate_tick(void *opaque)
 
     s->bytes_xfer = 0;
 
-    buffered_put_buffer(s, NULL, 0, 0);
+    buffered_flush(s);
+
+    /* Add some checks around this */
+    s->put_ready(s->opaque);
 }
 
-static const QEMUFileOps buffered_file_ops = {
-    .get_fd =         buffered_get_fd,
-    .put_buffer =     buffered_put_buffer,
-    .close =          buffered_close,
-    .rate_limit =     buffered_rate_limit,
-    .get_rate_limit = buffered_get_rate_limit,
-    .set_rate_limit = buffered_set_rate_limit,
-};
-
-QEMUFile *qemu_fopen_ops_buffered(MigrationState *migration_state)
+QEMUFile *qemu_fopen_ops_buffered(void *opaque,
+                                  size_t bytes_per_sec,
+                                  BufferedPutFunc *put_buffer,
+                                  BufferedPutReadyFunc *put_ready,
+                                  BufferedWaitForUnfreezeFunc *wait_for_unfreeze,
+                                  BufferedCloseFunc *close)
 {
     QEMUFileBuffered *s;
 
     s = g_malloc0(sizeof(*s));
 
-    s->migration_state = migration_state;
-    s->xfer_limit = migration_state->bandwidth_limit / 10;
+    s->opaque = opaque;
+    s->xfer_limit = bytes_per_sec / 10;
+    s->put_buffer = put_buffer;
+    s->put_ready = put_ready;
+    s->wait_for_unfreeze = wait_for_unfreeze;
+    s->close = close;
 
-    s->file = qemu_fopen_ops(s, &buffered_file_ops);
+    s->file = qemu_fopen_ops(s, buffered_put_buffer, NULL,
+                             buffered_close, buffered_rate_limit,
+                             buffered_set_rate_limit,
+			     buffered_get_rate_limit);
 
     s->timer = qemu_new_timer_ms(rt_clock, buffered_rate_tick, s);
 

buffered_file.h

@@ -15,8 +15,16 @@
 #define QEMU_BUFFERED_FILE_H
 
 #include "hw/hw.h"
-#include "migration.h"
 
-QEMUFile *qemu_fopen_ops_buffered(MigrationState *migration_state);
+typedef ssize_t (BufferedPutFunc)(void *opaque, const void *data, size_t size);
+typedef void (BufferedPutReadyFunc)(void *opaque);
+typedef void (BufferedWaitForUnfreezeFunc)(void *opaque);
+typedef int (BufferedCloseFunc)(void *opaque);
+
+QEMUFile *qemu_fopen_ops_buffered(void *opaque, size_t xfer_limit,
+                                  BufferedPutFunc *put_buffer,
+                                  BufferedPutReadyFunc *put_ready,
+                                  BufferedWaitForUnfreezeFunc *wait_for_unfreeze,
+                                  BufferedCloseFunc *close);
 
 #endif

compiler.h

@@ -44,11 +44,6 @@
    /* Use gnu_printf when supported (qemu uses standard format strings). */
 #  define GCC_ATTR __attribute__((__unused__, format(gnu_printf, 1, 2)))
 #  define GCC_FMT_ATTR(n, m) __attribute__((format(gnu_printf, n, m)))
-#  if defined(_WIN32)
-    /* Map __printf__ to __gnu_printf__ because we want standard format strings
-     * even when MinGW or GLib include files use __printf__. */
-#   define __printf__ __gnu_printf__
-#  endif
 # endif
 #else
 #define GCC_ATTR /**/

console.c

@@ -24,12 +24,10 @@
 #include "qemu-common.h"
 #include "console.h"
 #include "qemu-timer.h"
-#include "qmp-commands.h"
 
 //#define DEBUG_CONSOLE
 #define DEFAULT_BACKSCROLL 512
 #define MAX_CONSOLES 12
-#define CONSOLE_CURSOR_PERIOD 500
 
 #define QEMU_RGBA(r, g, b, a) (((a) << 24) | ((r) << 16) | ((g) << 8) | (b))
 #define QEMU_RGB(r, g, b) QEMU_RGBA(r, g, b, 0xff)
@@ -114,20 +112,20 @@ typedef enum {
     TEXT_CONSOLE_FIXED_SIZE
 } console_type_t;
 
-struct QemuConsole {
+/* ??? This is mis-named.
+   It is used for both text and graphical consoles.  */
+struct TextConsole {
     int index;
     console_type_t console_type;
     DisplayState *ds;
-
     /* Graphic console state.  */
     vga_hw_update_ptr hw_update;
     vga_hw_invalidate_ptr hw_invalidate;
     vga_hw_screen_dump_ptr hw_screen_dump;
     vga_hw_text_update_ptr hw_text_update;
     void *hw;
-    int g_width, g_height;
 
-    /* Text console state */
+    int g_width, g_height;
     int width;
     int height;
     int total_height;
@@ -141,8 +139,6 @@ struct QemuConsole {
     TextCell *cells;
     int text_x[2], text_y[2], cursor_invalidate;
     int echo;
-    bool cursor_visible_phase;
-    QEMUTimer *cursor_timer;
 
     int update_x0;
     int update_y0;
@@ -161,8 +157,8 @@ struct QemuConsole {
 };
 
 static DisplayState *display_state;
-static QemuConsole *active_console;
-static QemuConsole *consoles[MAX_CONSOLES];
+static TextConsole *active_console;
+static TextConsole *consoles[MAX_CONSOLES];
 static int nb_consoles = 0;
 
 void vga_hw_update(void)
@@ -177,9 +173,9 @@ void vga_hw_invalidate(void)
         active_console->hw_invalidate(active_console->hw);
 }
 
-void qmp_screendump(const char *filename, Error **errp)
+void vga_hw_screen_dump(const char *filename)
 {
-    QemuConsole *previous_active_console;
+    TextConsole *previous_active_console;
     bool cswitch;
 
     previous_active_console = active_console;
@@ -191,9 +187,9 @@ void qmp_screendump(const char *filename, Error **errp)
         console_select(0);
     }
     if (consoles[0] && consoles[0]->hw_screen_dump) {
-        consoles[0]->hw_screen_dump(consoles[0]->hw, filename, cswitch, errp);
+        consoles[0]->hw_screen_dump(consoles[0]->hw, filename, cswitch);
     } else {
-        error_setg(errp, "device doesn't support screendump\n");
+        error_report("screen dump not implemented");
     }
 
     if (cswitch) {
@@ -521,7 +517,7 @@ static void vga_putcharxy(DisplayState *ds, int x, int y, int ch,
     }
 }
 
-static void text_console_resize(QemuConsole *s)
+static void text_console_resize(TextConsole *s)
 {
     TextCell *cells, *c, *c1;
     int w1, x, y, last_width;
@@ -553,7 +549,7 @@ static void text_console_resize(QemuConsole *s)
     s->cells = cells;
 }
 
-static inline void text_update_xy(QemuConsole *s, int x, int y)
+static inline void text_update_xy(TextConsole *s, int x, int y)
 {
     s->text_x[0] = MIN(s->text_x[0], x);
     s->text_x[1] = MAX(s->text_x[1], x);
@@ -561,7 +557,7 @@ static inline void text_update_xy(QemuConsole *s, int x, int y)
     s->text_y[1] = MAX(s->text_y[1], y);
 }
 
-static void invalidate_xy(QemuConsole *s, int x, int y)
+static void invalidate_xy(TextConsole *s, int x, int y)
 {
     if (s->update_x0 > x * FONT_WIDTH)
         s->update_x0 = x * FONT_WIDTH;
@@ -573,7 +569,7 @@ static void invalidate_xy(QemuConsole *s, int x, int y)
         s->update_y1 = (y + 1) * FONT_HEIGHT;
 }
 
-static void update_xy(QemuConsole *s, int x, int y)
+static void update_xy(TextConsole *s, int x, int y)
 {
     TextCell *c;
     int y1, y2;
@@ -597,7 +593,7 @@ static void update_xy(QemuConsole *s, int x, int y)
     }
 }
 
-static void console_show_cursor(QemuConsole *s, int show)
+static void console_show_cursor(TextConsole *s, int show)
 {
     TextCell *c;
     int y, y1;
@@ -619,7 +615,7 @@ static void console_show_cursor(QemuConsole *s, int show)
             y += s->total_height;
         if (y < s->height) {
             c = &s->cells[y1 * s->width + x];
-            if (show && s->cursor_visible_phase) {
+            if (show) {
                 TextAttributes t_attrib = s->t_attrib_default;
                 t_attrib.invers = !(t_attrib.invers); /* invert fg and bg */
                 vga_putcharxy(s->ds, x, y, c->ch, &t_attrib);
@@ -631,45 +627,42 @@ static void console_show_cursor(QemuConsole *s, int show)
     }
 }
 
-static void console_refresh(QemuConsole *s)
+static void console_refresh(TextConsole *s)
 {
     TextCell *c;
     int x, y, y1;
 
     if (s != active_console)
         return;
-
-    if (s->ds->have_text) {
+    if (!ds_get_bits_per_pixel(s->ds)) {
         s->text_x[0] = 0;
         s->text_y[0] = 0;
         s->text_x[1] = s->width - 1;
         s->text_y[1] = s->height - 1;
         s->cursor_invalidate = 1;
+        return;
     }
 
-    if (s->ds->have_gfx) {
-        vga_fill_rect(s->ds, 0, 0, ds_get_width(s->ds), ds_get_height(s->ds),
-                      color_table[0][COLOR_BLACK]);
-        y1 = s->y_displayed;
-        for (y = 0; y < s->height; y++) {
-            c = s->cells + y1 * s->width;
-            for (x = 0; x < s->width; x++) {
-                vga_putcharxy(s->ds, x, y, c->ch,
-                              &(c->t_attrib));
-                c++;
-            }
-            if (++y1 == s->total_height) {
-                y1 = 0;
-            }
+    vga_fill_rect(s->ds, 0, 0, ds_get_width(s->ds), ds_get_height(s->ds),
+                  color_table[0][COLOR_BLACK]);
+    y1 = s->y_displayed;
+    for(y = 0; y < s->height; y++) {
+        c = s->cells + y1 * s->width;
+        for(x = 0; x < s->width; x++) {
+            vga_putcharxy(s->ds, x, y, c->ch,
+                          &(c->t_attrib));
+            c++;
         }
-        console_show_cursor(s, 1);
-        dpy_gfx_update(s->ds, 0, 0, ds_get_width(s->ds), ds_get_height(s->ds));
+        if (++y1 == s->total_height)
+            y1 = 0;
     }
+    console_show_cursor(s, 1);
+    dpy_update(s->ds, 0, 0, ds_get_width(s->ds), ds_get_height(s->ds));
 }
 
 static void console_scroll(int ydelta)
 {
-    QemuConsole *s;
+    TextConsole *s;
     int i, y1;
 
     s = active_console;
@@ -701,7 +694,7 @@ static void console_scroll(int ydelta)
     console_refresh(s);
 }
 
-static void console_put_lf(QemuConsole *s)
+static void console_put_lf(TextConsole *s)
 {
     TextCell *c;
     int x, y1;
@@ -752,7 +745,7 @@ static void console_put_lf(QemuConsole *s)
  * NOTE: I know this code is not very efficient (checking every color for it
  * self) but it is more readable and better maintainable.
  */
-static void console_handle_escape(QemuConsole *s)
+static void console_handle_escape(TextConsole *s)
 {
     int i;
 
@@ -845,7 +838,7 @@ static void console_handle_escape(QemuConsole *s)
     }
 }
 
-static void console_clear_xy(QemuConsole *s, int x, int y)
+static void console_clear_xy(TextConsole *s, int x, int y)
 {
     int y1 = (s->y_base + y) % s->total_height;
     TextCell *c = &s->cells[y1 * s->width + x];
@@ -855,7 +848,7 @@ static void console_clear_xy(QemuConsole *s, int x, int y)
 }
 
 /* set cursor, checking bounds */
-static void set_cursor(QemuConsole *s, int x, int y)
+static void set_cursor(TextConsole *s, int x, int y)
 {
     if (x < 0) {
         x = 0;
@@ -874,7 +867,7 @@ static void set_cursor(QemuConsole *s, int x, int y)
     s->y = y;
 }
 
-static void console_putchar(QemuConsole *s, int ch)
+static void console_putchar(TextConsole *s, int ch)
 {
     TextCell *c;
     int y1, i;
@@ -941,11 +934,8 @@ static void console_putchar(QemuConsole *s, int ch)
     case TTY_STATE_CSI: /* handle escape sequence parameters */
         if (ch >= '0' && ch <= '9') {
             if (s->nb_esc_params < MAX_ESC_PARAMS) {
-                int *param = &s->esc_params[s->nb_esc_params];
-                int digit = (ch - '0');
-
-                *param = (*param <= (INT_MAX - digit) / 10) ?
-                         *param * 10 + digit : INT_MAX;
+                s->esc_params[s->nb_esc_params] =
+                    s->esc_params[s->nb_esc_params] * 10 + ch - '0';
             }
         } else {
             if (s->nb_esc_params < MAX_ESC_PARAMS)
@@ -1081,7 +1071,7 @@ static void console_putchar(QemuConsole *s, int ch)
 
 void console_select(unsigned int index)
 {
-    QemuConsole *s;
+    TextConsole *s;
 
     if (index >= MAX_CONSOLES)
         return;
@@ -1092,29 +1082,21 @@ void console_select(unsigned int index)
     s = consoles[index];
     if (s) {
         DisplayState *ds = s->ds;
-
-        if (active_console && active_console->cursor_timer) {
-            qemu_del_timer(active_console->cursor_timer);
-        }
         active_console = s;
-        if (ds->have_gfx) {
+        if (ds_get_bits_per_pixel(s->ds)) {
             ds->surface = qemu_resize_displaysurface(ds, s->g_width, s->g_height);
-            dpy_gfx_resize(ds);
-        }
-        if (ds->have_text) {
-            dpy_text_resize(ds, s->width, s->height);
-        }
-        if (s->cursor_timer) {
-            qemu_mod_timer(s->cursor_timer,
-                   qemu_get_clock_ms(rt_clock) + CONSOLE_CURSOR_PERIOD / 2);
+        } else {
+            s->ds->surface->width = s->width;
+            s->ds->surface->height = s->height;
         }
+        dpy_resize(s->ds);
         vga_hw_invalidate();
     }
 }
 
 static int console_puts(CharDriverState *chr, const uint8_t *buf, int len)
 {
-    QemuConsole *s = chr->opaque;
+    TextConsole *s = chr->opaque;
     int i;
 
     s->update_x0 = s->width * FONT_WIDTH;
@@ -1126,17 +1108,17 @@ static int console_puts(CharDriverState *chr, const uint8_t *buf, int len)
         console_putchar(s, buf[i]);
     }
     console_show_cursor(s, 1);
-    if (s->ds->have_gfx && s->update_x0 < s->update_x1) {
-        dpy_gfx_update(s->ds, s->update_x0, s->update_y0,
-                       s->update_x1 - s->update_x0,
-                       s->update_y1 - s->update_y0);
+    if (ds_get_bits_per_pixel(s->ds) && s->update_x0 < s->update_x1) {
+        dpy_update(s->ds, s->update_x0, s->update_y0,
+                   s->update_x1 - s->update_x0,
+                   s->update_y1 - s->update_y0);
     }
     return len;
 }
 
 static void kbd_send_chars(void *opaque)
 {
-    QemuConsole *s = opaque;
+    TextConsole *s = opaque;
     int len;
     uint8_t buf[16];
 
@@ -1159,7 +1141,7 @@ static void kbd_send_chars(void *opaque)
 /* called when an ascii key is pressed */
 void kbd_put_keysym(int keysym)
 {
-    QemuConsole *s;
+    TextConsole *s;
     uint8_t buf[16], *q;
     int c;
 
@@ -1214,7 +1196,7 @@ void kbd_put_keysym(int keysym)
 
 static void text_console_invalidate(void *opaque)
 {
-    QemuConsole *s = (QemuConsole *) opaque;
+    TextConsole *s = (TextConsole *) opaque;
     if (!ds_get_bits_per_pixel(s->ds) && s->console_type == TEXT_CONSOLE) {
         s->g_width = ds_get_width(s->ds);
         s->g_height = ds_get_height(s->ds);
@@ -1225,7 +1207,7 @@ static void text_console_invalidate(void *opaque)
 
 static void text_console_update(void *opaque, console_ch_t *chardata)
 {
-    QemuConsole *s = (QemuConsole *) opaque;
+    TextConsole *s = (TextConsole *) opaque;
     int i, j, src;
 
     if (s->text_x[0] <= s->text_x[1]) {
@@ -1237,23 +1219,23 @@ static void text_console_update(void *opaque, console_ch_t *chardata)
                                 (s->cells[src].t_attrib.fgcol << 12) |
                                 (s->cells[src].t_attrib.bgcol << 8) |
                                 (s->cells[src].t_attrib.bold << 21));
-        dpy_text_update(s->ds, s->text_x[0], s->text_y[0],
-                        s->text_x[1] - s->text_x[0], i - s->text_y[0]);
+        dpy_update(s->ds, s->text_x[0], s->text_y[0],
+                   s->text_x[1] - s->text_x[0], i - s->text_y[0]);
         s->text_x[0] = s->width;
         s->text_y[0] = s->height;
         s->text_x[1] = 0;
         s->text_y[1] = 0;
     }
     if (s->cursor_invalidate) {
-        dpy_text_cursor(s->ds, s->x, s->y);
+        dpy_cursor(s->ds, s->x, s->y);
         s->cursor_invalidate = 0;
     }
 }
 
-static QemuConsole *get_graphic_console(DisplayState *ds)
+static TextConsole *get_graphic_console(DisplayState *ds)
 {
     int i;
-    QemuConsole *s;
+    TextConsole *s;
     for (i = 0; i < nb_consoles; i++) {
         s = consoles[i];
         if (s->console_type == GRAPHIC_CONSOLE && s->ds == ds)
@@ -1262,14 +1244,14 @@ static QemuConsole *get_graphic_console(DisplayState *ds)
     return NULL;
 }
 
-static QemuConsole *new_console(DisplayState *ds, console_type_t console_type)
+static TextConsole *new_console(DisplayState *ds, console_type_t console_type)
 {
-    QemuConsole *s;
+    TextConsole *s;
     int i;
 
     if (nb_consoles >= MAX_CONSOLES)
         return NULL;
-    s = g_malloc0(sizeof(QemuConsole));
+    s = g_malloc0(sizeof(TextConsole));
     if (!active_console || ((active_console->console_type != GRAPHIC_CONSOLE) &&
         (console_type == GRAPHIC_CONSOLE))) {
         active_console = s;
@@ -1294,31 +1276,9 @@ static QemuConsole *new_console(DisplayState *ds, console_type_t console_type)
     return s;
 }
 
-static void qemu_alloc_display(DisplaySurface *surface, int width, int height,
-                               int linesize, PixelFormat pf, int newflags)
+static DisplaySurface* defaultallocator_create_displaysurface(int width, int height)
 {
-    surface->pf = pf;
-
-    qemu_pixman_image_unref(surface->image);
-    surface->image = NULL;
-
-    surface->format = qemu_pixman_get_format(&pf);
-    assert(surface->format != 0);
-    surface->image = pixman_image_create_bits(surface->format,
-                                              width, height,
-                                              NULL, linesize);
-    assert(surface->image != NULL);
-
-    surface->flags = newflags | QEMU_ALLOCATED_FLAG;
-#ifdef HOST_WORDS_BIGENDIAN
-    surface->flags |= QEMU_BIG_ENDIAN_FLAG;
-#endif
-}
-
-DisplaySurface *qemu_create_displaysurface(DisplayState *ds,
-                                           int width, int height)
-{
-    DisplaySurface *surface = g_new0(DisplaySurface, 1);
+    DisplaySurface *surface = (DisplaySurface*) g_malloc0(sizeof(DisplaySurface));
 
     int linesize = width * 4;
     qemu_alloc_display(surface, width, height, linesize,
@@ -1326,54 +1286,75 @@ DisplaySurface *qemu_create_displaysurface(DisplayState *ds,
     return surface;
 }
 
-DisplaySurface *qemu_resize_displaysurface(DisplayState *ds,
-                                           int width, int height)
+static DisplaySurface* defaultallocator_resize_displaysurface(DisplaySurface *surface,
+                                          int width, int height)
 {
     int linesize = width * 4;
-
-    trace_displaysurface_resize(ds, ds->surface, width, height);
-    qemu_alloc_display(ds->surface, width, height, linesize,
+    qemu_alloc_display(surface, width, height, linesize,
                        qemu_default_pixelformat(32), 0);
-    return ds->surface;
+    return surface;
 }
 
-DisplaySurface *qemu_create_displaysurface_from(int width, int height, int bpp,
-                                                int linesize, uint8_t *data)
+void qemu_alloc_display(DisplaySurface *surface, int width, int height,
+                        int linesize, PixelFormat pf, int newflags)
 {
-    DisplaySurface *surface = g_new0(DisplaySurface, 1);
+    void *data;
+    surface->width = width;
+    surface->height = height;
+    surface->linesize = linesize;
+    surface->pf = pf;
+    if (surface->flags & QEMU_ALLOCATED_FLAG) {
+        data = g_realloc(surface->data,
+                            surface->linesize * surface->height);
+    } else {
+        data = g_malloc(surface->linesize * surface->height);
+    }
+    surface->data = (uint8_t *)data;
+    surface->flags = newflags | QEMU_ALLOCATED_FLAG;
+#ifdef HOST_WORDS_BIGENDIAN
+    surface->flags |= QEMU_BIG_ENDIAN_FLAG;
+#endif
+}
 
+DisplaySurface* qemu_create_displaysurface_from(int width, int height, int bpp,
+                                              int linesize, uint8_t *data)
+{
+    DisplaySurface *surface = (DisplaySurface*) g_malloc0(sizeof(DisplaySurface));
+
+    surface->width = width;
+    surface->height = height;
+    surface->linesize = linesize;
     surface->pf = qemu_default_pixelformat(bpp);
-
-    surface->format = qemu_pixman_get_format(&surface->pf);
-    assert(surface->format != 0);
-    surface->image = pixman_image_create_bits(surface->format,
-                                              width, height,
-                                              (void *)data, linesize);
-    assert(surface->image != NULL);
-
 #ifdef HOST_WORDS_BIGENDIAN
     surface->flags = QEMU_BIG_ENDIAN_FLAG;
 #endif
+    surface->data = data;
 
     return surface;
 }
 
-void qemu_free_displaysurface(DisplayState *ds)
+static void defaultallocator_free_displaysurface(DisplaySurface *surface)
 {
-    trace_displaysurface_free(ds, ds->surface);
-    if (ds->surface == NULL) {
+    if (surface == NULL)
         return;
-    }
-    qemu_pixman_image_unref(ds->surface->image);
-    g_free(ds->surface);
+    if (surface->flags & QEMU_ALLOCATED_FLAG)
+        g_free(surface->data);
+    g_free(surface);
 }
 
+static struct DisplayAllocator default_allocator = {
+    defaultallocator_create_displaysurface,
+    defaultallocator_resize_displaysurface,
+    defaultallocator_free_displaysurface
+};
+
 static void dumb_display_init(void)
 {
     DisplayState *ds = g_malloc0(sizeof(DisplayState));
     int width = 640;
     int height = 480;
 
+    ds->allocator = &default_allocator;
     if (is_fixedsize_console()) {
         width = active_console->g_width;
         height = active_console->g_height;
@@ -1403,16 +1384,29 @@ DisplayState *get_displaystate(void)
     return display_state;
 }
 
+DisplayAllocator *register_displayallocator(DisplayState *ds, DisplayAllocator *da)
+{
+    if(ds->allocator ==  &default_allocator) {
+        DisplaySurface *surf;
+        surf = da->create_displaysurface(ds_get_width(ds), ds_get_height(ds));
+        defaultallocator_free_displaysurface(ds->surface);
+        ds->surface = surf;
+        ds->allocator = da;
+    }
+    return ds->allocator;
+}
+
 DisplayState *graphic_console_init(vga_hw_update_ptr update,
                                    vga_hw_invalidate_ptr invalidate,
                                    vga_hw_screen_dump_ptr screen_dump,
                                    vga_hw_text_update_ptr text_update,
                                    void *opaque)
 {
-    QemuConsole *s;
+    TextConsole *s;
     DisplayState *ds;
 
     ds = (DisplayState *) g_malloc0(sizeof(DisplayState));
+    ds->allocator = &default_allocator; 
     ds->surface = qemu_create_displaysurface(ds, 640, 480);
 
     s = new_console(ds, GRAPHIC_CONSOLE);
@@ -1454,24 +1448,14 @@ void console_color_init(DisplayState *ds)
 
 static void text_console_set_echo(CharDriverState *chr, bool echo)
 {
-    QemuConsole *s = chr->opaque;
+    TextConsole *s = chr->opaque;
 
     s->echo = echo;
 }
 
-static void text_console_update_cursor(void *opaque)
-{
-    QemuConsole *s = opaque;
-
-    s->cursor_visible_phase = !s->cursor_visible_phase;
-    vga_hw_invalidate();
-    qemu_mod_timer(s->cursor_timer,
-                   qemu_get_clock_ms(rt_clock) + CONSOLE_CURSOR_PERIOD / 2);
-}
-
 static void text_console_do_init(CharDriverState *chr, DisplayState *ds)
 {
-    QemuConsole *s;
+    TextConsole *s;
     static int color_inited;
 
     s = chr->opaque;
@@ -1497,9 +1481,6 @@ static void text_console_do_init(CharDriverState *chr, DisplayState *ds)
         s->g_height = ds_get_height(s->ds);
     }
 
-    s->cursor_timer =
-        qemu_new_timer_ms(rt_clock, text_console_update_cursor, s);
-
     s->hw_invalidate = text_console_invalidate;
     s->hw_text_update = text_console_update;
     s->hw = s;
@@ -1534,7 +1515,7 @@ static void text_console_do_init(CharDriverState *chr, DisplayState *ds)
 CharDriverState *text_console_init(QemuOpts *opts)
 {
     CharDriverState *chr;
-    QemuConsole *s;
+    TextConsole *s;
     unsigned width;
     unsigned height;
 
@@ -1580,14 +1561,14 @@ void text_consoles_set_display(DisplayState *ds)
 
 void qemu_console_resize(DisplayState *ds, int width, int height)
 {
-    QemuConsole *s = get_graphic_console(ds);
+    TextConsole *s = get_graphic_console(ds);
     if (!s) return;
 
     s->g_width = width;
     s->g_height = height;
     if (is_graphic_console()) {
         ds->surface = qemu_resize_displaysurface(ds, width, height);
-        dpy_gfx_resize(ds);
+        dpy_resize(ds);
     }
 }
 
@@ -1595,7 +1576,7 @@ void qemu_console_copy(DisplayState *ds, int src_x, int src_y,
                        int dst_x, int dst_y, int w, int h)
 {
     if (is_graphic_console()) {
-        dpy_gfx_copy(ds, src_x, src_y, dst_x, dst_y, w, h);
+        dpy_copy(ds, src_x, src_y, dst_x, dst_y, w, h);
     }
 }
 
@@ -1606,7 +1587,7 @@ PixelFormat qemu_different_endianness_pixelformat(int bpp)
     memset(&pf, 0x00, sizeof(PixelFormat));
 
     pf.bits_per_pixel = bpp;
-    pf.bytes_per_pixel = DIV_ROUND_UP(bpp, 8);
+    pf.bytes_per_pixel = bpp / 8;
     pf.depth = bpp == 32 ? 24 : bpp;
 
     switch (bpp) {
@@ -1655,12 +1636,13 @@ PixelFormat qemu_default_pixelformat(int bpp)
     memset(&pf, 0x00, sizeof(PixelFormat));
 
     pf.bits_per_pixel = bpp;
-    pf.bytes_per_pixel = DIV_ROUND_UP(bpp, 8);
+    pf.bytes_per_pixel = bpp / 8;
     pf.depth = bpp == 32 ? 24 : bpp;
 
     switch (bpp) {
         case 15:
             pf.bits_per_pixel = 16;
+            pf.bytes_per_pixel = 2;
             pf.rmask = 0x00007c00;
             pf.gmask = 0x000003E0;
             pf.bmask = 0x0000001F;
@@ -1706,15 +1688,18 @@ PixelFormat qemu_default_pixelformat(int bpp)
             pf.rmask = 0x00FF0000;
             pf.gmask = 0x0000FF00;
             pf.bmask = 0x000000FF;
+            pf.amax = 255;
             pf.rmax = 255;
             pf.gmax = 255;
             pf.bmax = 255;
+            pf.ashift = 24;
             pf.rshift = 16;
             pf.gshift = 8;
             pf.bshift = 0;
             pf.rbits = 8;
             pf.gbits = 8;
             pf.bbits = 8;
+            pf.abits = 8;
             break;
         default:
             break;

console.h

@@ -2,13 +2,10 @@
 #define CONSOLE_H
 
 #include "qemu-char.h"
-#include "qemu-pixman.h"
 #include "qdict.h"
 #include "notify.h"
 #include "monitor.h"
 #include "trace.h"
-#include "qapi-types.h"
-#include "error.h"
 
 /* keyboard/mouse support */
 
@@ -108,6 +105,7 @@ void kbd_put_keysym(int keysym);
 
 #define QEMU_BIG_ENDIAN_FLAG    0x01
 #define QEMU_ALLOCATED_FLAG     0x02
+#define QEMU_REALPIXELS_FLAG    0x04
 
 struct PixelFormat {
     uint8_t bits_per_pixel;
@@ -120,9 +118,11 @@ struct PixelFormat {
 };
 
 struct DisplaySurface {
-    pixman_format_code_t format;
-    pixman_image_t *image;
     uint8_t flags;
+    int width;
+    int height;
+    int linesize;        /* bytes per line */
+    uint8_t *data;
 
     struct PixelFormat pf;
 };
@@ -152,32 +152,35 @@ struct DisplayChangeListener {
     int idle;
     uint64_t gui_timer_interval;
 
+    void (*dpy_update)(struct DisplayState *s, int x, int y, int w, int h);
+    void (*dpy_resize)(struct DisplayState *s);
+    void (*dpy_setdata)(struct DisplayState *s);
     void (*dpy_refresh)(struct DisplayState *s);
-
-    void (*dpy_gfx_update)(struct DisplayState *s, int x, int y, int w, int h);
-    void (*dpy_gfx_resize)(struct DisplayState *s);
-    void (*dpy_gfx_setdata)(struct DisplayState *s);
-    void (*dpy_gfx_copy)(struct DisplayState *s, int src_x, int src_y,
-                         int dst_x, int dst_y, int w, int h);
-
+    void (*dpy_copy)(struct DisplayState *s, int src_x, int src_y,
+                     int dst_x, int dst_y, int w, int h);
+    void (*dpy_fill)(struct DisplayState *s, int x, int y,
+                     int w, int h, uint32_t c);
     void (*dpy_text_cursor)(struct DisplayState *s, int x, int y);
-    void (*dpy_text_resize)(struct DisplayState *s, int w, int h);
-    void (*dpy_text_update)(struct DisplayState *s, int x, int y, int w, int h);
 
-    void (*dpy_mouse_set)(struct DisplayState *s, int x, int y, int on);
-    void (*dpy_cursor_define)(struct DisplayState *s, QEMUCursor *cursor);
+    struct DisplayChangeListener *next;
+};
 
-    QLIST_ENTRY(DisplayChangeListener) next;
+struct DisplayAllocator {
+    DisplaySurface* (*create_displaysurface)(int width, int height);
+    DisplaySurface* (*resize_displaysurface)(DisplaySurface *surface, int width, int height);
+    void (*free_displaysurface)(DisplaySurface *surface);
 };
 
 struct DisplayState {
     struct DisplaySurface *surface;
     void *opaque;
     struct QEMUTimer *gui_timer;
-    bool have_gfx;
-    bool have_text;
 
-    QLIST_HEAD(, DisplayChangeListener) listeners;
+    struct DisplayAllocator* allocator;
+    struct DisplayChangeListener* listeners;
+
+    void (*mouse_set)(int x, int y, int on);
+    void (*cursor_define)(QEMUCursor *cursor);
 
     struct DisplayState *next;
 };
@@ -186,14 +189,29 @@ void register_displaystate(DisplayState *ds);
 DisplayState *get_displaystate(void);
 DisplaySurface* qemu_create_displaysurface_from(int width, int height, int bpp,
                                                 int linesize, uint8_t *data);
+void qemu_alloc_display(DisplaySurface *surface, int width, int height,
+                        int linesize, PixelFormat pf, int newflags);
 PixelFormat qemu_different_endianness_pixelformat(int bpp);
 PixelFormat qemu_default_pixelformat(int bpp);
 
-DisplaySurface *qemu_create_displaysurface(DisplayState *ds,
-                                           int width, int height);
-DisplaySurface *qemu_resize_displaysurface(DisplayState *ds,
-                                           int width, int height);
-void qemu_free_displaysurface(DisplayState *ds);
+DisplayAllocator *register_displayallocator(DisplayState *ds, DisplayAllocator *da);
+
+static inline DisplaySurface* qemu_create_displaysurface(DisplayState *ds, int width, int height)
+{
+    return ds->allocator->create_displaysurface(width, height);    
+}
+
+static inline DisplaySurface* qemu_resize_displaysurface(DisplayState *ds, int width, int height)
+{
+    trace_displaysurface_resize(ds, ds->surface, width, height);
+    return ds->allocator->resize_displaysurface(ds->surface, width, height);
+}
+
+static inline void qemu_free_displaysurface(DisplayState *ds)
+{
+    trace_displaysurface_free(ds, ds->surface);
+    ds->allocator->free_displaysurface(ds->surface);
+}
 
 static inline int is_surface_bgr(DisplaySurface *surface)
 {
@@ -205,201 +223,109 @@ static inline int is_surface_bgr(DisplaySurface *surface)
 
 static inline int is_buffer_shared(DisplaySurface *surface)
 {
-    return !(surface->flags & QEMU_ALLOCATED_FLAG);
+    return (!(surface->flags & QEMU_ALLOCATED_FLAG) &&
+            !(surface->flags & QEMU_REALPIXELS_FLAG));
 }
 
-void gui_setup_refresh(DisplayState *ds);
-
 static inline void register_displaychangelistener(DisplayState *ds, DisplayChangeListener *dcl)
 {
-    QLIST_INSERT_HEAD(&ds->listeners, dcl, next);
-    gui_setup_refresh(ds);
-    if (dcl->dpy_gfx_resize) {
-        dcl->dpy_gfx_resize(ds);
+    dcl->next = ds->listeners;
+    ds->listeners = dcl;
+}
+
+static inline void dpy_update(DisplayState *s, int x, int y, int w, int h)
+{
+    struct DisplayChangeListener *dcl = s->listeners;
+    while (dcl != NULL) {
+        dcl->dpy_update(s, x, y, w, h);
+        dcl = dcl->next;
     }
 }
 
-static inline void unregister_displaychangelistener(DisplayState *ds,
-                                                    DisplayChangeListener *dcl)
+static inline void dpy_resize(DisplayState *s)
 {
-    QLIST_REMOVE(dcl, next);
-    gui_setup_refresh(ds);
-}
-
-static inline void dpy_gfx_update(DisplayState *s, int x, int y, int w, int h)
-{
-    struct DisplayChangeListener *dcl;
-    QLIST_FOREACH(dcl, &s->listeners, next) {
-        if (dcl->dpy_gfx_update) {
-            dcl->dpy_gfx_update(s, x, y, w, h);
-        }
+    struct DisplayChangeListener *dcl = s->listeners;
+    while (dcl != NULL) {
+        dcl->dpy_resize(s);
+        dcl = dcl->next;
     }
 }
 
-static inline void dpy_gfx_resize(DisplayState *s)
+static inline void dpy_setdata(DisplayState *s)
 {
-    struct DisplayChangeListener *dcl;
-    QLIST_FOREACH(dcl, &s->listeners, next) {
-        if (dcl->dpy_gfx_resize) {
-            dcl->dpy_gfx_resize(s);
-        }
-    }
-}
-
-static inline void dpy_gfx_setdata(DisplayState *s)
-{
-    struct DisplayChangeListener *dcl;
-    QLIST_FOREACH(dcl, &s->listeners, next) {
-        if (dcl->dpy_gfx_setdata) {
-            dcl->dpy_gfx_setdata(s);
-        }
+    struct DisplayChangeListener *dcl = s->listeners;
+    while (dcl != NULL) {
+        if (dcl->dpy_setdata) dcl->dpy_setdata(s);
+        dcl = dcl->next;
     }
 }
 
 static inline void dpy_refresh(DisplayState *s)
 {
-    struct DisplayChangeListener *dcl;
-    QLIST_FOREACH(dcl, &s->listeners, next) {
-        if (dcl->dpy_refresh) {
-            dcl->dpy_refresh(s);
-        }
+    struct DisplayChangeListener *dcl = s->listeners;
+    while (dcl != NULL) {
+        if (dcl->dpy_refresh) dcl->dpy_refresh(s);
+        dcl = dcl->next;
     }
 }
 
-static inline void dpy_gfx_copy(struct DisplayState *s, int src_x, int src_y,
-                             int dst_x, int dst_y, int w, int h)
-{
-    struct DisplayChangeListener *dcl;
-    QLIST_FOREACH(dcl, &s->listeners, next) {
-        if (dcl->dpy_gfx_copy) {
-            dcl->dpy_gfx_copy(s, src_x, src_y, dst_x, dst_y, w, h);
-        } else { /* TODO */
-            dcl->dpy_gfx_update(s, dst_x, dst_y, w, h);
-        }
+static inline void dpy_copy(struct DisplayState *s, int src_x, int src_y,
+                             int dst_x, int dst_y, int w, int h) {
+    struct DisplayChangeListener *dcl = s->listeners;
+    while (dcl != NULL) {
+        if (dcl->dpy_copy)
+            dcl->dpy_copy(s, src_x, src_y, dst_x, dst_y, w, h);
+        else /* TODO */
+            dcl->dpy_update(s, dst_x, dst_y, w, h);
+        dcl = dcl->next;
     }
 }
 
-static inline void dpy_text_cursor(struct DisplayState *s, int x, int y)
-{
-    struct DisplayChangeListener *dcl;
-    QLIST_FOREACH(dcl, &s->listeners, next) {
-        if (dcl->dpy_text_cursor) {
-            dcl->dpy_text_cursor(s, x, y);
-        }
+static inline void dpy_fill(struct DisplayState *s, int x, int y,
+                             int w, int h, uint32_t c) {
+    struct DisplayChangeListener *dcl = s->listeners;
+    while (dcl != NULL) {
+        if (dcl->dpy_fill) dcl->dpy_fill(s, x, y, w, h, c);
+        dcl = dcl->next;
     }
 }
 
-static inline void dpy_text_update(DisplayState *s, int x, int y, int w, int h)
-{
-    struct DisplayChangeListener *dcl;
-    QLIST_FOREACH(dcl, &s->listeners, next) {
-        if (dcl->dpy_text_update) {
-            dcl->dpy_text_update(s, x, y, w, h);
-        }
+static inline void dpy_cursor(struct DisplayState *s, int x, int y) {
+    struct DisplayChangeListener *dcl = s->listeners;
+    while (dcl != NULL) {
+        if (dcl->dpy_text_cursor) dcl->dpy_text_cursor(s, x, y);
+        dcl = dcl->next;
     }
 }
 
-static inline void dpy_text_resize(DisplayState *s, int w, int h)
-{
-    struct DisplayChangeListener *dcl;
-    QLIST_FOREACH(dcl, &s->listeners, next) {
-        if (dcl->dpy_text_resize) {
-            dcl->dpy_text_resize(s, w, h);
-        }
-    }
-}
-
-static inline void dpy_mouse_set(struct DisplayState *s, int x, int y, int on)
-{
-    struct DisplayChangeListener *dcl;
-    QLIST_FOREACH(dcl, &s->listeners, next) {
-        if (dcl->dpy_mouse_set) {
-            dcl->dpy_mouse_set(s, x, y, on);
-        }
-    }
-}
-
-static inline void dpy_cursor_define(struct DisplayState *s, QEMUCursor *cursor)
-{
-    struct DisplayChangeListener *dcl;
-    QLIST_FOREACH(dcl, &s->listeners, next) {
-        if (dcl->dpy_cursor_define) {
-            dcl->dpy_cursor_define(s, cursor);
-        }
-    }
-}
-
-static inline bool dpy_cursor_define_supported(struct DisplayState *s)
-{
-    struct DisplayChangeListener *dcl;
-    QLIST_FOREACH(dcl, &s->listeners, next) {
-        if (dcl->dpy_cursor_define) {
-            return true;
-        }
-    }
-    return false;
-}
-
 static inline int ds_get_linesize(DisplayState *ds)
 {
-    return pixman_image_get_stride(ds->surface->image);
+    return ds->surface->linesize;
 }
 
 static inline uint8_t* ds_get_data(DisplayState *ds)
 {
-    return (void *)pixman_image_get_data(ds->surface->image);
+    return ds->surface->data;
 }
 
 static inline int ds_get_width(DisplayState *ds)
 {
-    return pixman_image_get_width(ds->surface->image);
+    return ds->surface->width;
 }
 
 static inline int ds_get_height(DisplayState *ds)
 {
-    return pixman_image_get_height(ds->surface->image);
+    return ds->surface->height;
 }
 
 static inline int ds_get_bits_per_pixel(DisplayState *ds)
 {
-    int bits = PIXMAN_FORMAT_BPP(ds->surface->format);
-    return bits;
+    return ds->surface->pf.bits_per_pixel;
 }
 
 static inline int ds_get_bytes_per_pixel(DisplayState *ds)
 {
-    int bits = PIXMAN_FORMAT_BPP(ds->surface->format);
-    return (bits + 7) / 8;
-}
-
-static inline pixman_format_code_t ds_get_format(DisplayState *ds)
-{
-    return ds->surface->format;
-}
-
-static inline pixman_image_t *ds_get_image(DisplayState *ds)
-{
-    return ds->surface->image;
-}
-
-static inline int ds_get_depth(DisplayState *ds)
-{
-    return ds->surface->pf.depth;
-}
-
-static inline int ds_get_rmask(DisplayState *ds)
-{
-    return ds->surface->pf.rmask;
-}
-
-static inline int ds_get_gmask(DisplayState *ds)
-{
-    return ds->surface->pf.gmask;
-}
-
-static inline int ds_get_bmask(DisplayState *ds)
-{
-    return ds->surface->pf.bmask;
+    return ds->surface->pf.bytes_per_pixel;
 }
 
 #ifdef CONFIG_CURSES
@@ -417,8 +343,7 @@ static inline void console_write_ch(console_ch_t *dest, uint32_t ch)
 
 typedef void (*vga_hw_update_ptr)(void *);
 typedef void (*vga_hw_invalidate_ptr)(void *);
-typedef void (*vga_hw_screen_dump_ptr)(void *, const char *, bool cswitch,
-                                       Error **errp);
+typedef void (*vga_hw_screen_dump_ptr)(void *, const char *, bool cswitch);
 typedef void (*vga_hw_text_update_ptr)(void *, console_ch_t *);
 
 DisplayState *graphic_console_init(vga_hw_update_ptr update,
@@ -429,6 +354,7 @@ DisplayState *graphic_console_init(vga_hw_update_ptr update,
 
 void vga_hw_update(void);
 void vga_hw_invalidate(void);
+void vga_hw_screen_dump(const char *filename);
 void vga_hw_text_update(console_ch_t *chardata);
 
 int is_graphic_console(void);
@@ -449,8 +375,10 @@ void cocoa_display_init(DisplayState *ds, int full_screen);
 
 /* vnc.c */
 void vnc_display_init(DisplayState *ds);
-void vnc_display_open(DisplayState *ds, const char *display, Error **errp);
+void vnc_display_close(DisplayState *ds);
+int vnc_display_open(DisplayState *ds, const char *display);
 void vnc_display_add_client(DisplayState *ds, int csock, int skipauth);
+int vnc_display_disable_login(DisplayState *ds);
 char *vnc_display_local_addr(DisplayState *ds);
 #ifdef CONFIG_VNC
 int vnc_display_password(DisplayState *ds, const char *password);
@@ -469,8 +397,4 @@ static inline int vnc_display_pw_expire(DisplayState *ds, time_t expires)
 /* curses.c */
 void curses_display_init(DisplayState *ds, int full_screen);
 
-/* input.c */
-int index_from_key(const char *key);
-int index_from_keycode(int code);
-
 #endif

coroutine-sigaltstack.c

@@ -171,8 +171,8 @@ static Coroutine *coroutine_new(void)
     CoroutineThreadState *coTS;
     struct sigaction sa;
     struct sigaction osa;
-    stack_t ss;
-    stack_t oss;
+    struct sigaltstack ss;
+    struct sigaltstack oss;
     sigset_t sigs;
     sigset_t osigs;
     jmp_buf old_env;

coroutine-ucontext.c

@@ -30,10 +30,6 @@
 #include "qemu-common.h"
 #include "qemu-coroutine-int.h"
 
-#ifdef CONFIG_VALGRIND_H
-#include <valgrind/valgrind.h>
-#endif
-
 enum {
     /* Maximum free pool size prevents holding too many freed coroutines */
     POOL_MAX_SIZE = 64,
@@ -47,11 +43,6 @@ typedef struct {
     Coroutine base;
     void *stack;
     jmp_buf env;
-
-#ifdef CONFIG_VALGRIND_H
-    unsigned int valgrind_stack_id;
-#endif
-
 } CoroutineUContext;
 
 /**
@@ -168,11 +159,6 @@ static Coroutine *coroutine_new(void)
     uc.uc_stack.ss_size = stack_size;
     uc.uc_stack.ss_flags = 0;
 
-#ifdef CONFIG_VALGRIND_H
-    co->valgrind_stack_id =
-        VALGRIND_STACK_REGISTER(co->stack, co->stack + stack_size);
-#endif
-
     arg.p = co;
 
     makecontext(&uc, (void (*)(void))coroutine_trampoline,
@@ -199,20 +185,6 @@ Coroutine *qemu_coroutine_new(void)
     return co;
 }
 
-#ifdef CONFIG_VALGRIND_H
-#ifdef CONFIG_PRAGMA_DISABLE_UNUSED_BUT_SET
-/* Work around an unused variable in the valgrind.h macro... */
-#pragma GCC diagnostic ignored "-Wunused-but-set-variable"
-#endif
-static inline void valgrind_stack_deregister(CoroutineUContext *co)
-{
-    VALGRIND_STACK_DEREGISTER(co->valgrind_stack_id);
-}
-#ifdef CONFIG_PRAGMA_DISABLE_UNUSED_BUT_SET
-#pragma GCC diagnostic error "-Wunused-but-set-variable"
-#endif
-#endif
-
 void qemu_coroutine_delete(Coroutine *co_)
 {
     CoroutineUContext *co = DO_UPCAST(CoroutineUContext, base, co_);
@@ -224,10 +196,6 @@ void qemu_coroutine_delete(Coroutine *co_)
         return;
     }
 
-#ifdef CONFIG_VALGRIND_H
-    valgrind_stack_deregister(co);
-#endif
-
     g_free(co->stack);
     g_free(co);
 }

cpu-all.h

@@ -260,34 +260,21 @@ extern unsigned long reserved_va;
 #define stfl(p, v) stfl_raw(p, v)
 #define stfq(p, v) stfq_raw(p, v)
 
+#ifndef CONFIG_TCG_PASS_AREG0
+#define ldub_code(p) ldub_raw(p)
+#define ldsb_code(p) ldsb_raw(p)
+#define lduw_code(p) lduw_raw(p)
+#define ldsw_code(p) ldsw_raw(p)
+#define ldl_code(p) ldl_raw(p)
+#define ldq_code(p) ldq_raw(p)
+#else
 #define cpu_ldub_code(env1, p) ldub_raw(p)
 #define cpu_ldsb_code(env1, p) ldsb_raw(p)
 #define cpu_lduw_code(env1, p) lduw_raw(p)
 #define cpu_ldsw_code(env1, p) ldsw_raw(p)
 #define cpu_ldl_code(env1, p) ldl_raw(p)
 #define cpu_ldq_code(env1, p) ldq_raw(p)
-
-#define cpu_ldub_data(env, addr) ldub_raw(addr)
-#define cpu_lduw_data(env, addr) lduw_raw(addr)
-#define cpu_ldsw_data(env, addr) ldsw_raw(addr)
-#define cpu_ldl_data(env, addr) ldl_raw(addr)
-#define cpu_ldq_data(env, addr) ldq_raw(addr)
-
-#define cpu_stb_data(env, addr, data) stb_raw(addr, data)
-#define cpu_stw_data(env, addr, data) stw_raw(addr, data)
-#define cpu_stl_data(env, addr, data) stl_raw(addr, data)
-#define cpu_stq_data(env, addr, data) stq_raw(addr, data)
-
-#define cpu_ldub_kernel(env, addr) ldub_raw(addr)
-#define cpu_lduw_kernel(env, addr) lduw_raw(addr)
-#define cpu_ldsw_kernel(env, addr) ldsw_raw(addr)
-#define cpu_ldl_kernel(env, addr) ldl_raw(addr)
-#define cpu_ldq_kernel(env, addr) ldq_raw(addr)
-
-#define cpu_stb_kernel(env, addr, data) stb_raw(addr, data)
-#define cpu_stw_kernel(env, addr, data) stw_raw(addr, data)
-#define cpu_stl_kernel(env, addr, data) stl_raw(addr, data)
-#define cpu_stq_kernel(env, addr, data) stq_raw(addr, data)
+#endif
 
 #define ldub_kernel(p) ldub_raw(p)
 #define ldsb_kernel(p) ldsb_raw(p)
@@ -304,13 +291,6 @@ extern unsigned long reserved_va;
 #define stfl_kernel(p, v) stfl_raw(p, v)
 #define stfq_kernel(p, vt) stfq_raw(p, v)
 
-#define cpu_ldub_data(env, addr) ldub_raw(addr)
-#define cpu_lduw_data(env, addr) lduw_raw(addr)
-#define cpu_ldl_data(env, addr) ldl_raw(addr)
-
-#define cpu_stb_data(env, addr, data) stb_raw(addr, data)
-#define cpu_stw_data(env, addr, data) stw_raw(addr, data)
-#define cpu_stl_data(env, addr, data) stl_raw(addr, data)
 #endif /* defined(CONFIG_USER_ONLY) */
 
 /* page related stuff */
@@ -356,9 +336,6 @@ CPUArchState *cpu_copy(CPUArchState *env);
 CPUArchState *qemu_get_cpu(int cpu);
 
 #define CPU_DUMP_CODE 0x00010000
-#define CPU_DUMP_FPU 0x00020000 /* dump FPU register state, not just integer */
-/* dump info about TCG QEMU's condition code optimization state */
-#define CPU_DUMP_CCOP 0x00040000
 
 void cpu_dump_state(CPUArchState *env, FILE *f, fprintf_function cpu_fprintf,
                     int flags);
@@ -438,6 +415,8 @@ void cpu_reset_interrupt(CPUArchState *env, int mask);
 
 void cpu_exit(CPUArchState *s);
 
+bool qemu_cpu_has_work(CPUArchState *env);
+
 /* Breakpoint/watchpoint flags */
 #define BP_MEM_READ           0x01
 #define BP_MEM_WRITE          0x02
@@ -464,13 +443,40 @@ void cpu_watchpoint_remove_all(CPUArchState *env, int mask);
 #define SSTEP_NOTIMER 0x4  /* Do not Timers while single stepping */
 
 void cpu_single_step(CPUArchState *env, int enabled);
+void cpu_state_reset(CPUArchState *s);
+int cpu_is_stopped(CPUArchState *env);
+void run_on_cpu(CPUArchState *env, void (*func)(void *data), void *data);
+
+#define CPU_LOG_TB_OUT_ASM (1 << 0)
+#define CPU_LOG_TB_IN_ASM  (1 << 1)
+#define CPU_LOG_TB_OP      (1 << 2)
+#define CPU_LOG_TB_OP_OPT  (1 << 3)
+#define CPU_LOG_INT        (1 << 4)
+#define CPU_LOG_EXEC       (1 << 5)
+#define CPU_LOG_PCALL      (1 << 6)
+#define CPU_LOG_IOPORT     (1 << 7)
+#define CPU_LOG_TB_CPU     (1 << 8)
+#define CPU_LOG_RESET      (1 << 9)
+
+/* define log items */
+typedef struct CPULogItem {
+    int mask;
+    const char *name;
+    const char *help;
+} CPULogItem;
+
+extern const CPULogItem cpu_log_items[];
+
+void cpu_set_log(int log_flags);
+void cpu_set_log_filename(const char *filename);
+int cpu_str_to_log_mask(const char *str);
 
 #if !defined(CONFIG_USER_ONLY)
 
 /* Return the physical page corresponding to a virtual one. Use it
    only for debugging because no protection checks are done. Return -1
    if no page found. */
-hwaddr cpu_get_phys_page_debug(CPUArchState *env, target_ulong addr);
+target_phys_addr_t cpu_get_phys_page_debug(CPUArchState *env, target_ulong addr);
 
 /* memory API */
 
@@ -513,7 +519,6 @@ extern int mem_prealloc;
 #define TLB_MMIO        (1 << 5)
 
 void dump_exec_info(FILE *f, fprintf_function cpu_fprintf);
-ram_addr_t last_ram_offset(void);
 #endif /* !CONFIG_USER_ONLY */
 
 int cpu_memory_rw_debug(CPUArchState *env, target_ulong addr,

cpu-common.h

@@ -3,7 +3,9 @@
 
 /* CPU interfaces that are target independent.  */
 
-#include "hwaddr.h"
+#ifdef TARGET_PHYS_ADDR_BITS
+#include "targphys.h"
+#endif
 
 #ifndef NEED_CPU_H
 #include "poison.h"
@@ -21,7 +23,7 @@ enum device_endian {
 };
 
 /* address in the RAM (different from a physical address) */
-#if defined(CONFIG_XEN_BACKEND)
+#if defined(CONFIG_XEN_BACKEND) && TARGET_PHYS_ADDR_BITS == 64
 typedef uint64_t ram_addr_t;
 #  define RAM_ADDR_MAX UINT64_MAX
 #  define RAM_ADDR_FMT "%" PRIx64
@@ -33,38 +35,41 @@ typedef uintptr_t ram_addr_t;
 
 /* memory API */
 
-typedef void CPUWriteMemoryFunc(void *opaque, hwaddr addr, uint32_t value);
-typedef uint32_t CPUReadMemoryFunc(void *opaque, hwaddr addr);
+typedef void CPUWriteMemoryFunc(void *opaque, target_phys_addr_t addr, uint32_t value);
+typedef uint32_t CPUReadMemoryFunc(void *opaque, target_phys_addr_t addr);
 
 void qemu_ram_remap(ram_addr_t addr, ram_addr_t length);
 /* This should only be used for ram local to a device.  */
 void *qemu_get_ram_ptr(ram_addr_t addr);
+void *qemu_ram_ptr_length(ram_addr_t addr, ram_addr_t *size);
+/* Same but slower, to use for migration, where the order of
+ * RAMBlocks must not change. */
+void *qemu_safe_ram_ptr(ram_addr_t addr);
 void qemu_put_ram_ptr(void *addr);
 /* This should not be used by devices.  */
 int qemu_ram_addr_from_host(void *ptr, ram_addr_t *ram_addr);
 ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr);
 void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev);
 
-void cpu_physical_memory_rw(hwaddr addr, uint8_t *buf,
+void cpu_physical_memory_rw(target_phys_addr_t addr, uint8_t *buf,
                             int len, int is_write);
-static inline void cpu_physical_memory_read(hwaddr addr,
+static inline void cpu_physical_memory_read(target_phys_addr_t addr,
                                             void *buf, int len)
 {
     cpu_physical_memory_rw(addr, buf, len, 0);
 }
-static inline void cpu_physical_memory_write(hwaddr addr,
+static inline void cpu_physical_memory_write(target_phys_addr_t addr,
                                              const void *buf, int len)
 {
     cpu_physical_memory_rw(addr, (void *)buf, len, 1);
 }
-void *cpu_physical_memory_map(hwaddr addr,
-                              hwaddr *plen,
+void *cpu_physical_memory_map(target_phys_addr_t addr,
+                              target_phys_addr_t *plen,
                               int is_write);
-void cpu_physical_memory_unmap(void *buffer, hwaddr len,
-                               int is_write, hwaddr access_len);
+void cpu_physical_memory_unmap(void *buffer, target_phys_addr_t len,
+                               int is_write, target_phys_addr_t access_len);
 void *cpu_register_map_client(void *opaque, void (*callback)(void *opaque));
-
-bool cpu_physical_memory_is_io(hwaddr phys_addr);
+void cpu_unregister_map_client(void *cookie);
 
 /* Coalesced MMIO regions are areas where write operations can be reordered.
  * This usually implies that write operations are side-effect free.  This allows
@@ -73,33 +78,33 @@ bool cpu_physical_memory_is_io(hwaddr phys_addr);
  */
 void qemu_flush_coalesced_mmio_buffer(void);
 
-uint32_t ldub_phys(hwaddr addr);
-uint32_t lduw_le_phys(hwaddr addr);
-uint32_t lduw_be_phys(hwaddr addr);
-uint32_t ldl_le_phys(hwaddr addr);
-uint32_t ldl_be_phys(hwaddr addr);
-uint64_t ldq_le_phys(hwaddr addr);
-uint64_t ldq_be_phys(hwaddr addr);
-void stb_phys(hwaddr addr, uint32_t val);
-void stw_le_phys(hwaddr addr, uint32_t val);
-void stw_be_phys(hwaddr addr, uint32_t val);
-void stl_le_phys(hwaddr addr, uint32_t val);
-void stl_be_phys(hwaddr addr, uint32_t val);
-void stq_le_phys(hwaddr addr, uint64_t val);
-void stq_be_phys(hwaddr addr, uint64_t val);
+uint32_t ldub_phys(target_phys_addr_t addr);
+uint32_t lduw_le_phys(target_phys_addr_t addr);
+uint32_t lduw_be_phys(target_phys_addr_t addr);
+uint32_t ldl_le_phys(target_phys_addr_t addr);
+uint32_t ldl_be_phys(target_phys_addr_t addr);
+uint64_t ldq_le_phys(target_phys_addr_t addr);
+uint64_t ldq_be_phys(target_phys_addr_t addr);
+void stb_phys(target_phys_addr_t addr, uint32_t val);
+void stw_le_phys(target_phys_addr_t addr, uint32_t val);
+void stw_be_phys(target_phys_addr_t addr, uint32_t val);
+void stl_le_phys(target_phys_addr_t addr, uint32_t val);
+void stl_be_phys(target_phys_addr_t addr, uint32_t val);
+void stq_le_phys(target_phys_addr_t addr, uint64_t val);
+void stq_be_phys(target_phys_addr_t addr, uint64_t val);
 
 #ifdef NEED_CPU_H
-uint32_t lduw_phys(hwaddr addr);
-uint32_t ldl_phys(hwaddr addr);
-uint64_t ldq_phys(hwaddr addr);
-void stl_phys_notdirty(hwaddr addr, uint32_t val);
-void stq_phys_notdirty(hwaddr addr, uint64_t val);
-void stw_phys(hwaddr addr, uint32_t val);
-void stl_phys(hwaddr addr, uint32_t val);
-void stq_phys(hwaddr addr, uint64_t val);
+uint32_t lduw_phys(target_phys_addr_t addr);
+uint32_t ldl_phys(target_phys_addr_t addr);
+uint64_t ldq_phys(target_phys_addr_t addr);
+void stl_phys_notdirty(target_phys_addr_t addr, uint32_t val);
+void stq_phys_notdirty(target_phys_addr_t addr, uint64_t val);
+void stw_phys(target_phys_addr_t addr, uint32_t val);
+void stl_phys(target_phys_addr_t addr, uint32_t val);
+void stq_phys(target_phys_addr_t addr, uint64_t val);
 #endif
 
-void cpu_physical_memory_write_rom(hwaddr addr,
+void cpu_physical_memory_write_rom(target_phys_addr_t addr,
                                    const uint8_t *buf, int len);
 
 extern struct MemoryRegion io_mem_ram;

cpu-defs.h

@@ -29,7 +29,7 @@
 #include <signal.h>
 #include "osdep.h"
 #include "qemu-queue.h"
-#include "hwaddr.h"
+#include "targphys.h"
 
 #ifndef TARGET_LONG_BITS
 #error TARGET_LONG_BITS must be defined before including this header
@@ -111,7 +111,7 @@ extern int CPUTLBEntry_wrong_size[sizeof(CPUTLBEntry) == (1 << CPU_TLB_ENTRY_BIT
 #define CPU_COMMON_TLB \
     /* The meaning of the MMU modes is defined in the target code. */   \
     CPUTLBEntry tlb_table[NB_MMU_MODES][CPU_TLB_SIZE];                  \
-    hwaddr iotlb[NB_MMU_MODES][CPU_TLB_SIZE];               \
+    target_phys_addr_t iotlb[NB_MMU_MODES][CPU_TLB_SIZE];               \
     target_ulong tlb_flush_addr;                                        \
     target_ulong tlb_flush_mask;
 
@@ -151,6 +151,14 @@ typedef struct CPUWatchpoint {
     QTAILQ_ENTRY(CPUWatchpoint) entry;
 } CPUWatchpoint;
 
+#ifdef _WIN32
+#define CPU_COMMON_THREAD \
+    void *hThread;
+
+#else
+#define CPU_COMMON_THREAD
+#endif
+
 #define CPU_TEMP_BUF_NLONGS 128
 #define CPU_COMMON                                                      \
     struct TranslationBlock *current_tb; /* currently executing TB  */  \
@@ -201,9 +209,18 @@ typedef struct CPUWatchpoint {
     int nr_cores;  /* number of cores within this CPU package */        \
     int nr_threads;/* number of threads within this CPU */              \
     int running; /* Nonzero if cpu is currently running(usermode).  */  \
+    int thread_id;                                                      \
     /* user data */                                                     \
     void *opaque;                                                       \
                                                                         \
+    uint32_t created;                                                   \
+    uint32_t stop;   /* Stop request */                                 \
+    uint32_t stopped; /* Artificially stopped */                        \
+    struct QemuThread *thread;                                          \
+    CPU_COMMON_THREAD                                                   \
+    struct QemuCond *halt_cond;                                         \
+    int thread_kicked;                                                  \
+    struct qemu_work_item *queued_work_first, *queued_work_last;        \
     const char *cpu_model_str;                                          \
     struct KVMState *kvm_state;                                         \
     struct kvm_run *kvm_run;                                            \

cpu-exec.c

@@ -27,9 +27,9 @@ int tb_invalidated_flag;
 
 //#define CONFIG_DEBUG_EXEC
 
-bool qemu_cpu_has_work(CPUState *cpu)
+bool qemu_cpu_has_work(CPUArchState *env)
 {
-    return cpu_has_work(cpu);
+    return cpu_has_work(env);
 }
 
 void cpu_loop_exit(CPUArchState *env)
@@ -156,9 +156,12 @@ static inline TranslationBlock *tb_find_fast(CPUArchState *env)
 
 static CPUDebugExcpHandler *debug_excp_handler;
 
-void cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler)
+CPUDebugExcpHandler *cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler)
 {
+    CPUDebugExcpHandler *old_handler = debug_excp_handler;
+
     debug_excp_handler = handler;
+    return old_handler;
 }
 
 static void cpu_handle_debug_exception(CPUArchState *env)
@@ -181,14 +184,13 @@ volatile sig_atomic_t exit_request;
 
 int cpu_exec(CPUArchState *env)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
     int ret, interrupt_request;
     TranslationBlock *tb;
     uint8_t *tc_ptr;
     tcg_target_ulong next_tb;
 
     if (env->halted) {
-        if (!cpu_has_work(cpu)) {
+        if (!cpu_has_work(env)) {
             return EXCP_HALTED;
         }
 
@@ -220,7 +222,6 @@ int cpu_exec(CPUArchState *env)
 #elif defined(TARGET_LM32)
 #elif defined(TARGET_MICROBLAZE)
 #elif defined(TARGET_MIPS)
-#elif defined(TARGET_OPENRISC)
 #elif defined(TARGET_SH4)
 #elif defined(TARGET_CRIS)
 #elif defined(TARGET_S390X)
@@ -291,18 +292,16 @@ int cpu_exec(CPUArchState *env)
                     }
 #endif
                     if (interrupt_request & CPU_INTERRUPT_INIT) {
-                            cpu_svm_check_intercept_param(env, SVM_EXIT_INIT,
-                                                          0);
-                            do_cpu_init(x86_env_get_cpu(env));
+                            svm_check_intercept(env, SVM_EXIT_INIT);
+                            do_cpu_init(env);
                             env->exception_index = EXCP_HALTED;
                             cpu_loop_exit(env);
                     } else if (interrupt_request & CPU_INTERRUPT_SIPI) {
-                            do_cpu_sipi(x86_env_get_cpu(env));
+                            do_cpu_sipi(env);
                     } else if (env->hflags2 & HF2_GIF_MASK) {
                         if ((interrupt_request & CPU_INTERRUPT_SMI) &&
                             !(env->hflags & HF_SMM_MASK)) {
-                            cpu_svm_check_intercept_param(env, SVM_EXIT_SMI,
-                                                          0);
+                            svm_check_intercept(env, SVM_EXIT_SMI);
                             env->interrupt_request &= ~CPU_INTERRUPT_SMI;
                             do_smm_enter(env);
                             next_tb = 0;
@@ -323,8 +322,7 @@ int cpu_exec(CPUArchState *env)
                                      (env->eflags & IF_MASK && 
                                       !(env->hflags & HF_INHIBIT_IRQ_MASK))))) {
                             int intno;
-                            cpu_svm_check_intercept_param(env, SVM_EXIT_INTR,
-                                                          0);
+                            svm_check_intercept(env, SVM_EXIT_INTR);
                             env->interrupt_request &= ~(CPU_INTERRUPT_HARD | CPU_INTERRUPT_VIRQ);
                             intno = cpu_get_pic_interrupt(env);
                             qemu_log_mask(CPU_LOG_TB_IN_ASM, "Servicing hardware INT=0x%02x\n", intno);
@@ -338,8 +336,7 @@ int cpu_exec(CPUArchState *env)
                                    !(env->hflags & HF_INHIBIT_IRQ_MASK)) {
                             int intno;
                             /* FIXME: this should respect TPR */
-                            cpu_svm_check_intercept_param(env, SVM_EXIT_VINTR,
-                                                          0);
+                            svm_check_intercept(env, SVM_EXIT_VINTR);
                             intno = ldl_phys(env->vm_vmcb + offsetof(struct vmcb, control.int_vector));
                             qemu_log_mask(CPU_LOG_TB_IN_ASM, "Servicing virtual hardware INT=0x%02x\n", intno);
                             do_interrupt_x86_hardirq(env, intno, 1);
@@ -350,7 +347,7 @@ int cpu_exec(CPUArchState *env)
                     }
 #elif defined(TARGET_PPC)
                     if ((interrupt_request & CPU_INTERRUPT_RESET)) {
-                        cpu_reset(cpu);
+                        cpu_state_reset(env);
                     }
                     if (interrupt_request & CPU_INTERRUPT_HARD) {
                         ppc_hw_interrupt(env);
@@ -383,23 +380,6 @@ int cpu_exec(CPUArchState *env)
                         do_interrupt(env);
                         next_tb = 0;
                     }
-#elif defined(TARGET_OPENRISC)
-                    {
-                        int idx = -1;
-                        if ((interrupt_request & CPU_INTERRUPT_HARD)
-                            && (env->sr & SR_IEE)) {
-                            idx = EXCP_INT;
-                        }
-                        if ((interrupt_request & CPU_INTERRUPT_TIMER)
-                            && (env->sr & SR_TEE)) {
-                            idx = EXCP_TICK;
-                        }
-                        if (idx >= 0) {
-                            env->exception_index = idx;
-                            do_interrupt(env);
-                            next_tb = 0;
-                        }
-                    }
 #elif defined(TARGET_SPARC)
                     if (interrupt_request & CPU_INTERRUPT_HARD) {
                         if (cpu_interrupts_enabled(env) &&
@@ -442,7 +422,6 @@ int cpu_exec(CPUArchState *env)
 #elif defined(TARGET_UNICORE32)
                     if (interrupt_request & CPU_INTERRUPT_HARD
                         && !(env->uncached_asr & ASR_I)) {
-                        env->exception_index = UC32_EXCP_INTR;
                         do_interrupt(env);
                         next_tb = 0;
                     }
@@ -491,18 +470,11 @@ int cpu_exec(CPUArchState *env)
                         do_interrupt(env);
                         next_tb = 0;
                     }
-                    if (interrupt_request & CPU_INTERRUPT_NMI) {
-                        unsigned int m_flag_archval;
-                        if (env->pregs[PR_VR] < 32) {
-                            m_flag_archval = M_FLAG_V10;
-                        } else {
-                            m_flag_archval = M_FLAG_V32;
-                        }
-                        if ((env->pregs[PR_CCS] & m_flag_archval)) {
-                            env->exception_index = EXCP_NMI;
-                            do_interrupt(env);
-                            next_tb = 0;
-                        }
+                    if (interrupt_request & CPU_INTERRUPT_NMI
+                        && (env->pregs[PR_CCS] & M_FLAG)) {
+                        env->exception_index = EXCP_NMI;
+                        do_interrupt(env);
+                        next_tb = 0;
                     }
 #elif defined(TARGET_M68K)
                     if (interrupt_request & CPU_INTERRUPT_HARD
@@ -550,7 +522,7 @@ int cpu_exec(CPUArchState *env)
 #if defined(TARGET_I386)
                     env->eflags = env->eflags | cpu_cc_compute_all(env, CC_OP)
                         | (DF & DF_MASK);
-                    log_cpu_state(env, CPU_DUMP_CCOP);
+                    log_cpu_state(env, X86_DUMP_CCOP);
                     env->eflags &= ~(DF_MASK | CC_O | CC_S | CC_Z | CC_A | CC_P | CC_C);
 #elif defined(TARGET_M68K)
                     cpu_m68k_flush_flags(env, env->cc_op);
@@ -654,7 +626,6 @@ int cpu_exec(CPUArchState *env)
               | env->cc_dest | (env->cc_x << 4);
 #elif defined(TARGET_MICROBLAZE)
 #elif defined(TARGET_MIPS)
-#elif defined(TARGET_OPENRISC)
 #elif defined(TARGET_SH4)
 #elif defined(TARGET_ALPHA)
 #elif defined(TARGET_CRIS)

cpus.c

@@ -36,7 +36,6 @@
 #include "cpus.h"
 #include "qtest.h"
 #include "main-loop.h"
-#include "bitmap.h"
 
 #ifndef _WIN32
 #include "compatfd.h"
@@ -62,35 +61,6 @@
 
 static CPUArchState *next_cpu;
 
-static bool cpu_thread_is_idle(CPUArchState *env)
-{
-    CPUState *cpu = ENV_GET_CPU(env);
-
-    if (cpu->stop || cpu->queued_work_first) {
-        return false;
-    }
-    if (cpu->stopped || !runstate_is_running()) {
-        return true;
-    }
-    if (!env->halted || qemu_cpu_has_work(cpu) ||
-        kvm_async_interrupts_enabled()) {
-        return false;
-    }
-    return true;
-}
-
-static bool all_cpu_threads_idle(void)
-{
-    CPUArchState *env;
-
-    for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        if (!cpu_thread_is_idle(env)) {
-            return false;
-        }
-    }
-    return true;
-}
-
 /***********************************************************/
 /* guest cycle counter */
 
@@ -397,7 +367,11 @@ void hw_error(const char *fmt, ...)
     fprintf(stderr, "\n");
     for(env = first_cpu; env != NULL; env = env->next_cpu) {
         fprintf(stderr, "CPU #%d:\n", env->cpu_index);
-        cpu_dump_state(env, stderr, fprintf, CPU_DUMP_FPU);
+#ifdef TARGET_I386
+        cpu_dump_state(env, stderr, fprintf, X86_DUMP_FPU);
+#else
+        cpu_dump_state(env, stderr, fprintf, 0);
+#endif
     }
     va_end(ap);
     abort();
@@ -430,9 +404,9 @@ void cpu_synchronize_all_post_init(void)
     }
 }
 
-bool cpu_is_stopped(CPUState *cpu)
+int cpu_is_stopped(CPUArchState *env)
 {
-    return !runstate_is_running() || cpu->stopped;
+    return !runstate_is_running() || env->stopped;
 }
 
 static void do_vm_stop(RunState state)
@@ -448,24 +422,48 @@ static void do_vm_stop(RunState state)
     }
 }
 
-static bool cpu_can_run(CPUState *cpu)
+static int cpu_can_run(CPUArchState *env)
 {
-    if (cpu->stop) {
+    if (env->stop) {
+        return 0;
+    }
+    if (env->stopped || !runstate_is_running()) {
+        return 0;
+    }
+    return 1;
+}
+
+static bool cpu_thread_is_idle(CPUArchState *env)
+{
+    if (env->stop || env->queued_work_first) {
         return false;
     }
-    if (cpu->stopped || !runstate_is_running()) {
+    if (env->stopped || !runstate_is_running()) {
+        return true;
+    }
+    if (!env->halted || qemu_cpu_has_work(env) || kvm_irqchip_in_kernel()) {
         return false;
     }
     return true;
 }
 
+bool all_cpu_threads_idle(void)
+{
+    CPUArchState *env;
+
+    for (env = first_cpu; env != NULL; env = env->next_cpu) {
+        if (!cpu_thread_is_idle(env)) {
+            return false;
+        }
+    }
+    return true;
+}
+
 static void cpu_handle_guest_debug(CPUArchState *env)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
-
     gdb_set_stop_cpu(env);
     qemu_system_debug_request();
-    cpu->stopped = true;
+    env->stopped = 1;
 }
 
 static void cpu_signal(int sig)
@@ -613,7 +611,7 @@ static void qemu_tcg_init_cpu_signals(void)
 }
 #endif /* _WIN32 */
 
-static QemuMutex qemu_global_mutex;
+QemuMutex qemu_global_mutex;
 static QemuCond qemu_io_proceeded_cond;
 static bool iothread_requesting_mutex;
 
@@ -640,27 +638,27 @@ void qemu_init_cpu_loop(void)
     qemu_thread_get_self(&io_thread);
 }
 
-void run_on_cpu(CPUState *cpu, void (*func)(void *data), void *data)
+void run_on_cpu(CPUArchState *env, void (*func)(void *data), void *data)
 {
     struct qemu_work_item wi;
 
-    if (qemu_cpu_is_self(cpu)) {
+    if (qemu_cpu_is_self(env)) {
         func(data);
         return;
     }
 
     wi.func = func;
     wi.data = data;
-    if (cpu->queued_work_first == NULL) {
-        cpu->queued_work_first = &wi;
+    if (!env->queued_work_first) {
+        env->queued_work_first = &wi;
     } else {
-        cpu->queued_work_last->next = &wi;
+        env->queued_work_last->next = &wi;
     }
-    cpu->queued_work_last = &wi;
+    env->queued_work_last = &wi;
     wi.next = NULL;
     wi.done = false;
 
-    qemu_cpu_kick(cpu);
+    qemu_cpu_kick(env);
     while (!wi.done) {
         CPUArchState *self_env = cpu_single_env;
 
@@ -669,32 +667,32 @@ void run_on_cpu(CPUState *cpu, void (*func)(void *data), void *data)
     }
 }
 
-static void flush_queued_work(CPUState *cpu)
+static void flush_queued_work(CPUArchState *env)
 {
     struct qemu_work_item *wi;
 
-    if (cpu->queued_work_first == NULL) {
+    if (!env->queued_work_first) {
         return;
     }
 
-    while ((wi = cpu->queued_work_first)) {
-        cpu->queued_work_first = wi->next;
+    while ((wi = env->queued_work_first)) {
+        env->queued_work_first = wi->next;
         wi->func(wi->data);
         wi->done = true;
     }
-    cpu->queued_work_last = NULL;
+    env->queued_work_last = NULL;
     qemu_cond_broadcast(&qemu_work_cond);
 }
 
-static void qemu_wait_io_event_common(CPUState *cpu)
+static void qemu_wait_io_event_common(CPUArchState *env)
 {
-    if (cpu->stop) {
-        cpu->stop = false;
-        cpu->stopped = true;
+    if (env->stop) {
+        env->stop = 0;
+        env->stopped = 1;
         qemu_cond_signal(&qemu_pause_cond);
     }
-    flush_queued_work(cpu);
-    cpu->thread_kicked = false;
+    flush_queued_work(env);
+    env->thread_kicked = false;
 }
 
 static void qemu_tcg_wait_io_event(void)
@@ -713,31 +711,28 @@ static void qemu_tcg_wait_io_event(void)
     }
 
     for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        qemu_wait_io_event_common(ENV_GET_CPU(env));
+        qemu_wait_io_event_common(env);
     }
 }
 
 static void qemu_kvm_wait_io_event(CPUArchState *env)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
-
     while (cpu_thread_is_idle(env)) {
-        qemu_cond_wait(cpu->halt_cond, &qemu_global_mutex);
+        qemu_cond_wait(env->halt_cond, &qemu_global_mutex);
     }
 
     qemu_kvm_eat_signals(env);
-    qemu_wait_io_event_common(cpu);
+    qemu_wait_io_event_common(env);
 }
 
 static void *qemu_kvm_cpu_thread_fn(void *arg)
 {
     CPUArchState *env = arg;
-    CPUState *cpu = ENV_GET_CPU(env);
     int r;
 
     qemu_mutex_lock(&qemu_global_mutex);
-    qemu_thread_get_self(cpu->thread);
-    cpu->thread_id = qemu_get_thread_id();
+    qemu_thread_get_self(env->thread);
+    env->thread_id = qemu_get_thread_id();
     cpu_single_env = env;
 
     r = kvm_init_vcpu(env);
@@ -749,11 +744,11 @@ static void *qemu_kvm_cpu_thread_fn(void *arg)
     qemu_kvm_init_cpu_signals(env);
 
     /* signal CPU creation */
-    cpu->created = true;
+    env->created = 1;
     qemu_cond_signal(&qemu_cpu_cond);
 
     while (1) {
-        if (cpu_can_run(cpu)) {
+        if (cpu_can_run(env)) {
             r = kvm_cpu_exec(env);
             if (r == EXCP_DEBUG) {
                 cpu_handle_guest_debug(env);
@@ -772,19 +767,18 @@ static void *qemu_dummy_cpu_thread_fn(void *arg)
     exit(1);
 #else
     CPUArchState *env = arg;
-    CPUState *cpu = ENV_GET_CPU(env);
     sigset_t waitset;
     int r;
 
     qemu_mutex_lock_iothread();
-    qemu_thread_get_self(cpu->thread);
-    cpu->thread_id = qemu_get_thread_id();
+    qemu_thread_get_self(env->thread);
+    env->thread_id = qemu_get_thread_id();
 
     sigemptyset(&waitset);
     sigaddset(&waitset, SIG_IPI);
 
     /* signal CPU creation */
-    cpu->created = true;
+    env->created = 1;
     qemu_cond_signal(&qemu_cpu_cond);
 
     cpu_single_env = env;
@@ -801,7 +795,7 @@ static void *qemu_dummy_cpu_thread_fn(void *arg)
         }
         qemu_mutex_lock_iothread();
         cpu_single_env = env;
-        qemu_wait_io_event_common(cpu);
+        qemu_wait_io_event_common(env);
     }
 
     return NULL;
@@ -812,28 +806,26 @@ static void tcg_exec_all(void);
 
 static void *qemu_tcg_cpu_thread_fn(void *arg)
 {
-    CPUState *cpu = arg;
-    CPUArchState *env;
+    CPUArchState *env = arg;
 
     qemu_tcg_init_cpu_signals();
-    qemu_thread_get_self(cpu->thread);
+    qemu_thread_get_self(env->thread);
 
     /* signal CPU creation */
     qemu_mutex_lock(&qemu_global_mutex);
     for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        cpu = ENV_GET_CPU(env);
-        cpu->thread_id = qemu_get_thread_id();
-        cpu->created = true;
+        env->thread_id = qemu_get_thread_id();
+        env->created = 1;
     }
     qemu_cond_signal(&qemu_cpu_cond);
 
     /* wait for initial kick-off after machine start */
-    while (ENV_GET_CPU(first_cpu)->stopped) {
+    while (first_cpu->stopped) {
         qemu_cond_wait(tcg_halt_cond, &qemu_global_mutex);
 
         /* process any pending work */
         for (env = first_cpu; env != NULL; env = env->next_cpu) {
-            qemu_wait_io_event_common(ENV_GET_CPU(env));
+            qemu_wait_io_event_common(env);
         }
     }
 
@@ -848,31 +840,33 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
     return NULL;
 }
 
-static void qemu_cpu_kick_thread(CPUState *cpu)
+static void qemu_cpu_kick_thread(CPUArchState *env)
 {
 #ifndef _WIN32
     int err;
 
-    err = pthread_kill(cpu->thread->thread, SIG_IPI);
+    err = pthread_kill(env->thread->thread, SIG_IPI);
     if (err) {
         fprintf(stderr, "qemu:%s: %s", __func__, strerror(err));
         exit(1);
     }
 #else /* _WIN32 */
-    if (!qemu_cpu_is_self(cpu)) {
-        SuspendThread(cpu->hThread);
+    if (!qemu_cpu_is_self(env)) {
+        SuspendThread(env->hThread);
         cpu_signal(0);
-        ResumeThread(cpu->hThread);
+        ResumeThread(env->hThread);
     }
 #endif
 }
 
-void qemu_cpu_kick(CPUState *cpu)
+void qemu_cpu_kick(void *_env)
 {
-    qemu_cond_broadcast(cpu->halt_cond);
-    if (!tcg_enabled() && !cpu->thread_kicked) {
-        qemu_cpu_kick_thread(cpu);
-        cpu->thread_kicked = true;
+    CPUArchState *env = _env;
+
+    qemu_cond_broadcast(env->halt_cond);
+    if (!tcg_enabled() && !env->thread_kicked) {
+        qemu_cpu_kick_thread(env);
+        env->thread_kicked = true;
     }
 }
 
@@ -880,25 +874,21 @@ void qemu_cpu_kick_self(void)
 {
 #ifndef _WIN32
     assert(cpu_single_env);
-    CPUState *cpu_single_cpu = ENV_GET_CPU(cpu_single_env);
 
-    if (!cpu_single_cpu->thread_kicked) {
-        qemu_cpu_kick_thread(cpu_single_cpu);
-        cpu_single_cpu->thread_kicked = true;
+    if (!cpu_single_env->thread_kicked) {
+        qemu_cpu_kick_thread(cpu_single_env);
+        cpu_single_env->thread_kicked = true;
     }
 #else
     abort();
 #endif
 }
 
-bool qemu_cpu_is_self(CPUState *cpu)
+int qemu_cpu_is_self(void *_env)
 {
-    return qemu_thread_is_self(cpu->thread);
-}
+    CPUArchState *env = _env;
 
-static bool qemu_in_vcpu_thread(void)
-{
-    return cpu_single_env && qemu_cpu_is_self(ENV_GET_CPU(cpu_single_env));
+    return qemu_thread_is_self(env->thread);
 }
 
 void qemu_mutex_lock_iothread(void)
@@ -908,7 +898,7 @@ void qemu_mutex_lock_iothread(void)
     } else {
         iothread_requesting_mutex = true;
         if (qemu_mutex_trylock(&qemu_global_mutex)) {
-            qemu_cpu_kick_thread(ENV_GET_CPU(first_cpu));
+            qemu_cpu_kick_thread(first_cpu);
             qemu_mutex_lock(&qemu_global_mutex);
         }
         iothread_requesting_mutex = false;
@@ -926,8 +916,7 @@ static int all_vcpus_paused(void)
     CPUArchState *penv = first_cpu;
 
     while (penv) {
-        CPUState *pcpu = ENV_GET_CPU(penv);
-        if (!pcpu->stopped) {
+        if (!penv->stopped) {
             return 0;
         }
         penv = penv->next_cpu;
@@ -942,19 +931,17 @@ void pause_all_vcpus(void)
 
     qemu_clock_enable(vm_clock, false);
     while (penv) {
-        CPUState *pcpu = ENV_GET_CPU(penv);
-        pcpu->stop = true;
-        qemu_cpu_kick(pcpu);
+        penv->stop = 1;
+        qemu_cpu_kick(penv);
         penv = penv->next_cpu;
     }
 
-    if (qemu_in_vcpu_thread()) {
+    if (!qemu_thread_is_self(&io_thread)) {
         cpu_stop_current();
         if (!kvm_enabled()) {
             while (penv) {
-                CPUState *pcpu = ENV_GET_CPU(penv);
-                pcpu->stop = 0;
-                pcpu->stopped = true;
+                penv->stop = 0;
+                penv->stopped = 1;
                 penv = penv->next_cpu;
             }
             return;
@@ -965,7 +952,7 @@ void pause_all_vcpus(void)
         qemu_cond_wait(&qemu_pause_cond, &qemu_global_mutex);
         penv = first_cpu;
         while (penv) {
-            qemu_cpu_kick(ENV_GET_CPU(penv));
+            qemu_cpu_kick(penv);
             penv = penv->next_cpu;
         }
     }
@@ -977,61 +964,58 @@ void resume_all_vcpus(void)
 
     qemu_clock_enable(vm_clock, true);
     while (penv) {
-        CPUState *pcpu = ENV_GET_CPU(penv);
-        pcpu->stop = false;
-        pcpu->stopped = false;
-        qemu_cpu_kick(pcpu);
+        penv->stop = 0;
+        penv->stopped = 0;
+        qemu_cpu_kick(penv);
         penv = penv->next_cpu;
     }
 }
 
-static void qemu_tcg_init_vcpu(CPUState *cpu)
+static void qemu_tcg_init_vcpu(void *_env)
 {
+    CPUArchState *env = _env;
+
     /* share a single thread for all cpus with TCG */
     if (!tcg_cpu_thread) {
-        cpu->thread = g_malloc0(sizeof(QemuThread));
-        cpu->halt_cond = g_malloc0(sizeof(QemuCond));
-        qemu_cond_init(cpu->halt_cond);
-        tcg_halt_cond = cpu->halt_cond;
-        qemu_thread_create(cpu->thread, qemu_tcg_cpu_thread_fn, cpu,
+        env->thread = g_malloc0(sizeof(QemuThread));
+        env->halt_cond = g_malloc0(sizeof(QemuCond));
+        qemu_cond_init(env->halt_cond);
+        tcg_halt_cond = env->halt_cond;
+        qemu_thread_create(env->thread, qemu_tcg_cpu_thread_fn, env,
                            QEMU_THREAD_JOINABLE);
 #ifdef _WIN32
-        cpu->hThread = qemu_thread_get_handle(cpu->thread);
+        env->hThread = qemu_thread_get_handle(env->thread);
 #endif
-        while (!cpu->created) {
+        while (env->created == 0) {
             qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
         }
-        tcg_cpu_thread = cpu->thread;
+        tcg_cpu_thread = env->thread;
     } else {
-        cpu->thread = tcg_cpu_thread;
-        cpu->halt_cond = tcg_halt_cond;
+        env->thread = tcg_cpu_thread;
+        env->halt_cond = tcg_halt_cond;
     }
 }
 
 static void qemu_kvm_start_vcpu(CPUArchState *env)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
-
-    cpu->thread = g_malloc0(sizeof(QemuThread));
-    cpu->halt_cond = g_malloc0(sizeof(QemuCond));
-    qemu_cond_init(cpu->halt_cond);
-    qemu_thread_create(cpu->thread, qemu_kvm_cpu_thread_fn, env,
+    env->thread = g_malloc0(sizeof(QemuThread));
+    env->halt_cond = g_malloc0(sizeof(QemuCond));
+    qemu_cond_init(env->halt_cond);
+    qemu_thread_create(env->thread, qemu_kvm_cpu_thread_fn, env,
                        QEMU_THREAD_JOINABLE);
-    while (!cpu->created) {
+    while (env->created == 0) {
         qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
     }
 }
 
 static void qemu_dummy_start_vcpu(CPUArchState *env)
 {
-    CPUState *cpu = ENV_GET_CPU(env);
-
-    cpu->thread = g_malloc0(sizeof(QemuThread));
-    cpu->halt_cond = g_malloc0(sizeof(QemuCond));
-    qemu_cond_init(cpu->halt_cond);
-    qemu_thread_create(cpu->thread, qemu_dummy_cpu_thread_fn, env,
+    env->thread = g_malloc0(sizeof(QemuThread));
+    env->halt_cond = g_malloc0(sizeof(QemuCond));
+    qemu_cond_init(env->halt_cond);
+    qemu_thread_create(env->thread, qemu_dummy_cpu_thread_fn, env,
                        QEMU_THREAD_JOINABLE);
-    while (!cpu->created) {
+    while (env->created == 0) {
         qemu_cond_wait(&qemu_cpu_cond, &qemu_global_mutex);
     }
 }
@@ -1039,15 +1023,14 @@ static void qemu_dummy_start_vcpu(CPUArchState *env)
 void qemu_init_vcpu(void *_env)
 {
     CPUArchState *env = _env;
-    CPUState *cpu = ENV_GET_CPU(env);
 
     env->nr_cores = smp_cores;
     env->nr_threads = smp_threads;
-    cpu->stopped = true;
+    env->stopped = 1;
     if (kvm_enabled()) {
         qemu_kvm_start_vcpu(env);
     } else if (tcg_enabled()) {
-        qemu_tcg_init_vcpu(cpu);
+        qemu_tcg_init_vcpu(env);
     } else {
         qemu_dummy_start_vcpu(env);
     }
@@ -1056,9 +1039,8 @@ void qemu_init_vcpu(void *_env)
 void cpu_stop_current(void)
 {
     if (cpu_single_env) {
-        CPUState *cpu_single_cpu = ENV_GET_CPU(cpu_single_env);
-        cpu_single_cpu->stop = false;
-        cpu_single_cpu->stopped = true;
+        cpu_single_env->stop = 0;
+        cpu_single_env->stopped = 1;
         cpu_exit(cpu_single_env);
         qemu_cond_signal(&qemu_pause_cond);
     }
@@ -1066,7 +1048,7 @@ void cpu_stop_current(void)
 
 void vm_stop(RunState state)
 {
-    if (qemu_in_vcpu_thread()) {
+    if (!qemu_thread_is_self(&io_thread)) {
         qemu_system_vmstop_request(state);
         /*
          * FIXME: should not return to device code in case
@@ -1139,18 +1121,17 @@ static void tcg_exec_all(void)
     }
     for (; next_cpu != NULL && !exit_request; next_cpu = next_cpu->next_cpu) {
         CPUArchState *env = next_cpu;
-        CPUState *cpu = ENV_GET_CPU(env);
 
         qemu_clock_enable(vm_clock,
                           (env->singlestep_enabled & SSTEP_NOTIMER) == 0);
 
-        if (cpu_can_run(cpu)) {
+        if (cpu_can_run(env)) {
             r = tcg_cpu_exec(env);
             if (r == EXCP_DEBUG) {
                 cpu_handle_guest_debug(env);
                 break;
             }
-        } else if (cpu->stop || cpu->stopped) {
+        } else if (env->stop || env->stopped) {
             break;
         }
     }
@@ -1164,7 +1145,7 @@ void set_numa_modes(void)
 
     for (env = first_cpu; env != NULL; env = env->next_cpu) {
         for (i = 0; i < nb_numa_nodes; i++) {
-            if (test_bit(env->cpu_index, node_cpumask[i])) {
+            if (node_cpumask[i] & (1 << env->cpu_index)) {
                 env->numa_node = i;
             }
         }
@@ -1195,8 +1176,10 @@ void set_cpu_log_filename(const char *optarg)
 void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg)
 {
     /* XXX: implement xxx_cpu_list for targets that still miss it */
-#if defined(cpu_list)
-    cpu_list(f, cpu_fprintf);
+#if defined(cpu_list_id)
+    cpu_list_id(f, cpu_fprintf, optarg);
+#elif defined(cpu_list)
+    cpu_list(f, cpu_fprintf); /* deprecated */
 #endif
 }
 
@@ -1205,8 +1188,7 @@ CpuInfoList *qmp_query_cpus(Error **errp)
     CpuInfoList *head = NULL, *cur_item = NULL;
     CPUArchState *env;
 
-    for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        CPUState *cpu = ENV_GET_CPU(env);
+    for(env = first_cpu; env != NULL; env = env->next_cpu) {
         CpuInfoList *info;
 
         cpu_synchronize_state(env);
@@ -1216,7 +1198,7 @@ CpuInfoList *qmp_query_cpus(Error **errp)
         info->value->CPU = env->cpu_index;
         info->value->current = (env == first_cpu);
         info->value->halted = env->halted;
-        info->value->thread_id = cpu->thread_id;
+        info->value->thread_id = env->thread_id;
 #if defined(TARGET_I386)
         info->value->has_pc = true;
         info->value->pc = env->eip + env->segs[R_CS].base;

cputlb.c

@@ -21,11 +21,11 @@
 #include "cpu.h"
 #include "exec-all.h"
 #include "memory.h"
-#include "exec-memory.h"
 
 #include "cputlb.h"
 
-#include "memory-internal.h"
+#define WANT_EXEC_OBSOLETE
+#include "exec-obsolete.h"
 
 //#define DEBUG_TLB
 //#define DEBUG_TLB_CHECK
@@ -237,7 +237,7 @@ static void tlb_add_large_page(CPUArchState *env, target_ulong vaddr,
    is permitted. Only a single TARGET_PAGE_SIZE region is mapped, the
    supplied size is only used by tlb_flush_page.  */
 void tlb_set_page(CPUArchState *env, target_ulong vaddr,
-                  hwaddr paddr, int prot,
+                  target_phys_addr_t paddr, int prot,
                   int mmu_idx, target_ulong size)
 {
     MemoryRegionSection *section;
@@ -246,13 +246,13 @@ void tlb_set_page(CPUArchState *env, target_ulong vaddr,
     target_ulong code_address;
     uintptr_t addend;
     CPUTLBEntry *te;
-    hwaddr iotlb;
+    target_phys_addr_t iotlb;
 
     assert(size >= TARGET_PAGE_SIZE);
     if (size != TARGET_PAGE_SIZE) {
         tlb_add_large_page(env, vaddr, size);
     }
-    section = phys_page_find(address_space_memory.dispatch, paddr >> TARGET_PAGE_BITS);
+    section = phys_page_find(paddr >> TARGET_PAGE_BITS);
 #if defined(DEBUG_TLB)
     printf("tlb_set_page: vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx
            " prot=%x idx=%d pd=0x%08lx\n",
@@ -312,9 +312,7 @@ void tlb_set_page(CPUArchState *env, target_ulong vaddr,
 
 /* NOTE: this function can trigger an exception */
 /* NOTE2: the returned address is not exactly the physical address: it
- * is actually a ram_addr_t (in system mode; the user mode emulation
- * version of this function returns a guest virtual address).
- */
+   is the offset relative to phys_ram_base */
 tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
 {
     int mmu_idx, page_index, pd;
@@ -325,7 +323,11 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
     mmu_idx = cpu_mmu_index(env1);
     if (unlikely(env1->tlb_table[mmu_idx][page_index].addr_code !=
                  (addr & TARGET_PAGE_MASK))) {
+#ifdef CONFIG_TCG_PASS_AREG0
         cpu_ldub_code(env1, addr);
+#else
+        ldub_code(addr);
+#endif
     }
     pd = env1->iotlb[mmu_idx][page_index] & ~TARGET_PAGE_MASK;
     mr = iotlb_to_region(pd);
@@ -344,6 +346,7 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
 #define MMUSUFFIX _cmmu
 #undef GETPC
 #define GETPC() ((uintptr_t)0)
+#define env cpu_single_env
 #define SOFTMMU_CODE_ACCESS
 
 #define SHIFT 0

cputlb.h

@@ -26,18 +26,17 @@ void tlb_unprotect_code_phys(CPUArchState *env, ram_addr_t ram_addr,
                              target_ulong vaddr);
 void tlb_reset_dirty_range(CPUTLBEntry *tlb_entry, uintptr_t start,
                            uintptr_t length);
-MemoryRegionSection *phys_page_find(struct AddressSpaceDispatch *d,
-                                    hwaddr index);
+MemoryRegionSection *phys_page_find(target_phys_addr_t index);
 void cpu_tlb_reset_dirty_all(ram_addr_t start1, ram_addr_t length);
 void tlb_set_dirty(CPUArchState *env, target_ulong vaddr);
 extern int tlb_flush_count;
 
 /* exec.c */
 void tb_flush_jmp_cache(CPUArchState *env, target_ulong addr);
-hwaddr memory_region_section_get_iotlb(CPUArchState *env,
+target_phys_addr_t memory_region_section_get_iotlb(CPUArchState *env,
                                                    MemoryRegionSection *section,
                                                    target_ulong vaddr,
-                                                   hwaddr paddr,
+                                                   target_phys_addr_t paddr,
                                                    int prot,
                                                    target_ulong *address);
 bool memory_region_is_unassigned(MemoryRegion *mr);

cutils.c

@@ -26,14 +26,6 @@
 #include <math.h>
 
 #include "qemu_socket.h"
-#include "iov.h"
-
-void strpadcpy(char *buf, int buf_size, const char *str, char pad)
-{
-    int len = qemu_strnlen(str, buf_size);
-    memcpy(buf, str, len);
-    memset(buf + len, pad, buf_size - len);
-}
 
 void pstrcpy(char *buf, int buf_size, const char *str)
 {
@@ -115,7 +107,7 @@ time_t mktimegm(struct tm *tm)
         m += 12;
         y--;
     }
-    t = 86400ULL * (d + (153 * m - 457) / 5 + 365 * y + y / 4 - y / 100 + 
+    t = 86400 * (d + (153 * m - 457) / 5 + 365 * y + y / 4 - y / 100 + 
                  y / 400 - 719469);
     t += 3600 * tm->tm_hour + 60 * tm->tm_min + tm->tm_sec;
     return t;
@@ -142,6 +134,175 @@ int qemu_fdatasync(int fd)
 #endif
 }
 
+/* io vectors */
+
+void qemu_iovec_init(QEMUIOVector *qiov, int alloc_hint)
+{
+    qiov->iov = g_malloc(alloc_hint * sizeof(struct iovec));
+    qiov->niov = 0;
+    qiov->nalloc = alloc_hint;
+    qiov->size = 0;
+}
+
+void qemu_iovec_init_external(QEMUIOVector *qiov, struct iovec *iov, int niov)
+{
+    int i;
+
+    qiov->iov = iov;
+    qiov->niov = niov;
+    qiov->nalloc = -1;
+    qiov->size = 0;
+    for (i = 0; i < niov; i++)
+        qiov->size += iov[i].iov_len;
+}
+
+void qemu_iovec_add(QEMUIOVector *qiov, void *base, size_t len)
+{
+    assert(qiov->nalloc != -1);
+
+    if (qiov->niov == qiov->nalloc) {
+        qiov->nalloc = 2 * qiov->nalloc + 1;
+        qiov->iov = g_realloc(qiov->iov, qiov->nalloc * sizeof(struct iovec));
+    }
+    qiov->iov[qiov->niov].iov_base = base;
+    qiov->iov[qiov->niov].iov_len = len;
+    qiov->size += len;
+    ++qiov->niov;
+}
+
+/*
+ * Copies iovecs from src to the end of dst. It starts copying after skipping
+ * the given number of bytes in src and copies until src is completely copied
+ * or the total size of the copied iovec reaches size.The size of the last
+ * copied iovec is changed in order to fit the specified total size if it isn't
+ * a perfect fit already.
+ */
+void qemu_iovec_copy(QEMUIOVector *dst, QEMUIOVector *src, uint64_t skip,
+    size_t size)
+{
+    int i;
+    size_t done;
+    void *iov_base;
+    uint64_t iov_len;
+
+    assert(dst->nalloc != -1);
+
+    done = 0;
+    for (i = 0; (i < src->niov) && (done != size); i++) {
+        if (skip >= src->iov[i].iov_len) {
+            /* Skip the whole iov */
+            skip -= src->iov[i].iov_len;
+            continue;
+        } else {
+            /* Skip only part (or nothing) of the iov */
+            iov_base = (uint8_t*) src->iov[i].iov_base + skip;
+            iov_len = src->iov[i].iov_len - skip;
+            skip = 0;
+        }
+
+        if (done + iov_len > size) {
+            qemu_iovec_add(dst, iov_base, size - done);
+            break;
+        } else {
+            qemu_iovec_add(dst, iov_base, iov_len);
+        }
+        done += iov_len;
+    }
+}
+
+void qemu_iovec_concat(QEMUIOVector *dst, QEMUIOVector *src, size_t size)
+{
+    qemu_iovec_copy(dst, src, 0, size);
+}
+
+void qemu_iovec_destroy(QEMUIOVector *qiov)
+{
+    assert(qiov->nalloc != -1);
+
+    qemu_iovec_reset(qiov);
+    g_free(qiov->iov);
+    qiov->nalloc = 0;
+    qiov->iov = NULL;
+}
+
+void qemu_iovec_reset(QEMUIOVector *qiov)
+{
+    assert(qiov->nalloc != -1);
+
+    qiov->niov = 0;
+    qiov->size = 0;
+}
+
+void qemu_iovec_to_buffer(QEMUIOVector *qiov, void *buf)
+{
+    uint8_t *p = (uint8_t *)buf;
+    int i;
+
+    for (i = 0; i < qiov->niov; ++i) {
+        memcpy(p, qiov->iov[i].iov_base, qiov->iov[i].iov_len);
+        p += qiov->iov[i].iov_len;
+    }
+}
+
+void qemu_iovec_from_buffer(QEMUIOVector *qiov, const void *buf, size_t count)
+{
+    const uint8_t *p = (const uint8_t *)buf;
+    size_t copy;
+    int i;
+
+    for (i = 0; i < qiov->niov && count; ++i) {
+        copy = count;
+        if (copy > qiov->iov[i].iov_len)
+            copy = qiov->iov[i].iov_len;
+        memcpy(qiov->iov[i].iov_base, p, copy);
+        p     += copy;
+        count -= copy;
+    }
+}
+
+void qemu_iovec_memset(QEMUIOVector *qiov, int c, size_t count)
+{
+    size_t n;
+    int i;
+
+    for (i = 0; i < qiov->niov && count; ++i) {
+        n = MIN(count, qiov->iov[i].iov_len);
+        memset(qiov->iov[i].iov_base, c, n);
+        count -= n;
+    }
+}
+
+void qemu_iovec_memset_skip(QEMUIOVector *qiov, int c, size_t count,
+                            size_t skip)
+{
+    int i;
+    size_t done;
+    void *iov_base;
+    uint64_t iov_len;
+
+    done = 0;
+    for (i = 0; (i < qiov->niov) && (done != count); i++) {
+        if (skip >= qiov->iov[i].iov_len) {
+            /* Skip the whole iov */
+            skip -= qiov->iov[i].iov_len;
+            continue;
+        } else {
+            /* Skip only part (or nothing) of the iov */
+            iov_base = (uint8_t*) qiov->iov[i].iov_base + skip;
+            iov_len = qiov->iov[i].iov_len - skip;
+            skip = 0;
+        }
+
+        if (done + iov_len > count) {
+            memset(iov_base, c, count - done);
+            break;
+        } else {
+            memset(iov_base, c, iov_len);
+        }
+        done += iov_len;
+    }
+}
+
 /*
  * Checks if a buffer is all zeroes
  *
@@ -280,44 +441,111 @@ int qemu_parse_fd(const char *param)
     return fd;
 }
 
-/* round down to the nearest power of 2*/
-int64_t pow2floor(int64_t value)
-{
-    if (!is_power_of_2(value)) {
-        value = 0x8000000000000000ULL >> clz64(value);
-    }
-    return value;
-}
-
 /*
- * Implementation of  ULEB128 (http://en.wikipedia.org/wiki/LEB128)
- * Input is limited to 14-bit numbers
+ * Send/recv data with iovec buffers
+ *
+ * This function send/recv data from/to the iovec buffer directly.
+ * The first `offset' bytes in the iovec buffer are skipped and next
+ * `len' bytes are used.
+ *
+ * For example,
+ *
+ *   do_sendv_recvv(sockfd, iov, len, offset, 1);
+ *
+ * is equal to
+ *
+ *   char *buf = malloc(size);
+ *   iov_to_buf(iov, iovcnt, buf, offset, size);
+ *   send(sockfd, buf, size, 0);
+ *   free(buf);
  */
-int uleb128_encode_small(uint8_t *out, uint32_t n)
+static int do_sendv_recvv(int sockfd, struct iovec *iov, int len, int offset,
+                          int do_sendv)
 {
-    g_assert(n <= 0x3fff);
-    if (n < 0x80) {
-        *out++ = n;
-        return 1;
-    } else {
-        *out++ = (n & 0x7f) | 0x80;
-        *out++ = n >> 7;
-        return 2;
+    int ret, diff, iovlen;
+    struct iovec *last_iov;
+
+    /* last_iov is inclusive, so count from one.  */
+    iovlen = 1;
+    last_iov = iov;
+    len += offset;
+
+    while (last_iov->iov_len < len) {
+        len -= last_iov->iov_len;
+
+        last_iov++;
+        iovlen++;
     }
+
+    diff = last_iov->iov_len - len;
+    last_iov->iov_len -= diff;
+
+    while (iov->iov_len <= offset) {
+        offset -= iov->iov_len;
+
+        iov++;
+        iovlen--;
+    }
+
+    iov->iov_base = (char *) iov->iov_base + offset;
+    iov->iov_len -= offset;
+
+    {
+#if defined CONFIG_IOVEC && defined CONFIG_POSIX
+        struct msghdr msg;
+        memset(&msg, 0, sizeof(msg));
+        msg.msg_iov = iov;
+        msg.msg_iovlen = iovlen;
+
+        do {
+            if (do_sendv) {
+                ret = sendmsg(sockfd, &msg, 0);
+            } else {
+                ret = recvmsg(sockfd, &msg, 0);
+            }
+        } while (ret == -1 && errno == EINTR);
+#else
+        struct iovec *p = iov;
+        ret = 0;
+        while (iovlen > 0) {
+            int rc;
+            if (do_sendv) {
+                rc = send(sockfd, p->iov_base, p->iov_len, 0);
+            } else {
+                rc = qemu_recv(sockfd, p->iov_base, p->iov_len, 0);
+            }
+            if (rc == -1) {
+                if (errno == EINTR) {
+                    continue;
+                }
+                if (ret == 0) {
+                    ret = -1;
+                }
+                break;
+            }
+            if (rc == 0) {
+                break;
+            }
+            ret += rc;
+            iovlen--, p++;
+        }
+#endif
+    }
+
+    /* Undo the changes above */
+    iov->iov_base = (char *) iov->iov_base - offset;
+    iov->iov_len += offset;
+    last_iov->iov_len += diff;
+    return ret;
 }
 
-int uleb128_decode_small(const uint8_t *in, uint32_t *n)
+int qemu_recvv(int sockfd, struct iovec *iov, int len, int iov_offset)
 {
-    if (!(*in & 0x80)) {
-        *n = *in++;
-        return 1;
-    } else {
-        *n = *in++ & 0x7f;
-        /* we exceed 14 bit number */
-        if (*in & 0x80) {
-            return -1;
-        }
-        *n |= *in++ << 7;
-        return 2;
-    }
+    return do_sendv_recvv(sockfd, iov, len, iov_offset, 0);
 }
+
+int qemu_sendv(int sockfd, struct iovec *iov, int len, int iov_offset)
+{
+    return do_sendv_recvv(sockfd, iov, len, iov_offset, 1);
+}
+

def-helper.h

@@ -128,8 +128,6 @@
 #define DEF_HELPER_5(name, ret, t1, t2, t3, t4, t5) \
     DEF_HELPER_FLAGS_5(name, 0, ret, t1, t2, t3, t4, t5)
 
-/* MAX_OPC_PARAM_IARGS must be set to n if last entry is DEF_HELPER_FLAGS_n. */
-
 #endif /* DEF_HELPER_H */
 
 #ifndef GEN_HELPER

default-configs/arm-softmmu.mak

@@ -22,27 +22,8 @@ CONFIG_ADS7846=y
 CONFIG_MAX111X=y
 CONFIG_SSI=y
 CONFIG_SSI_SD=y
-CONFIG_SSI_M25P80=y
 CONFIG_LAN9118=y
 CONFIG_SMC91C111=y
 CONFIG_DS1338=y
 CONFIG_PFLASH_CFI01=y
 CONFIG_PFLASH_CFI02=y
-
-CONFIG_ARM_TIMER=y
-CONFIG_PL011=y
-CONFIG_PL022=y
-CONFIG_PL031=y
-CONFIG_PL041=y
-CONFIG_PL050=y
-CONFIG_PL061=y
-CONFIG_PL080=y
-CONFIG_PL110=y
-CONFIG_PL181=y
-CONFIG_PL190=y
-CONFIG_PL310=y
-CONFIG_CADENCE=y
-CONFIG_XGMAC=y
-
-CONFIG_VERSATILE_PCI=y
-CONFIG_VERSATILE_I2C=y

default-configs/microblaze-softmmu.mak

@@ -3,7 +3,3 @@
 CONFIG_PTIMER=y
 CONFIG_PFLASH_CFI01=y
 CONFIG_SERIAL=y
-CONFIG_XILINX=y
-CONFIG_XILINX_AXI=y
-CONFIG_SSI=y
-CONFIG_SSI_M25P80=y

default-configs/microblazeel-softmmu.mak

@@ -3,7 +3,3 @@
 CONFIG_PTIMER=y
 CONFIG_PFLASH_CFI01=y
 CONFIG_SERIAL=y
-CONFIG_XILINX=y
-CONFIG_XILINX_AXI=y
-CONFIG_SSI=y
-CONFIG_SSI_M25P80=y

default-configs/or32-linux-user.mak

@@ -1 +0,0 @@
-# Default configuration for or32-linux-user

default-configs/or32-softmmu.mak

@@ -1,4 +0,0 @@
-# Default configuration for or32-softmmu
-
-CONFIG_SERIAL=y
-CONFIG_OPENCORES_ETH=y