OpenE2K
/
qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity

Merge branch 'master' of git://git.qemu.org/qemu into prep-up 

Conflicts:
	hw/Makefile.objs
	hw/ppc_prep.c

Signed-off-by: Andreas Färber <andreas.faerber@web.de>
This commit is contained in:
Andreas Färber 2013-01-10 21:52:28 +01:00
parent 52a71bff60 a6308bc222
commit 63e3555e80
1953 changed files with 109215 additions and 41440 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
.exrc Normal file
View File

@ -0,0 +1,7 @@
"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

13
.gitignore vendored
View File

@ -1,19 +1,18 @@
config-devices.*
config-all-devices.*
config-all-disas.*
config-host.*
config-target.*
trace.h
trace.c
trace-dtrace.h
trace-dtrace.dtrace
trace/generated-tracers.h
trace/generated-tracers.c
trace/generated-tracers-dtrace.h
trace/generated-tracers-dtrace.dtrace
*-timestamp
*-softmmu
*-darwin-user
*-linux-user
*-bsd-user
libdis*
libhw32
libhw64
libuser
linux-headers/asm
qapi-generated
@ -49,6 +48,7 @@ test-qmp-output-visitor
test-string-input-visitor
test-string-output-visitor
test-visitor-serialization
fsdev/virtfs-proxy-helper
fsdev/virtfs-proxy-helper.1
fsdev/virtfs-proxy-helper.pod
.gdbinit
@ -70,6 +70,7 @@ fsdev/virtfs-proxy-helper.pod
*.tp
*.vr
*.d
!scripts/qemu-guest-agent/fsfreeze-hook.d
*.o
*.lo
*.la

3
.gitmodules vendored
View File

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

31
HACKING
View File

@ -32,7 +32,7 @@ mandatory for VMState fields.
Don't use Linux kernel internal types like u32, __u32 or __le32.
Use target_phys_addr_t for guest physical addresses except pcibus_t
Use hwaddr 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
@ -91,10 +91,11 @@ emulators.
4. String manipulation
Do not use the strncpy function. According to the man page, it does
*not* guarantee a NULL-terminated buffer, which makes it extremely dangerous
to use. Instead, use functionally equivalent function:
void pstrcpy(char *buf, int buf_size, const char *str)
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)
Don't use strcat because it can't check for buffer overflows, but:
char *pstrcat(char *buf, int buf_size, const char *s)
@ -122,3 +123,23 @@ gcc's printf attribute directive in the prototype.
This makes it so gcc's -Wformat and -Wformat-security options can do
their jobs and cross-check format strings with the number and types
of arguments.
6. C standard, implementation defined and undefined behaviors
C code in QEMU should be written to the C99 language specification. A copy
of the final version of the C99 standard with corrigenda TC1, TC2, and TC3
included, formatted as a draft, can be downloaded from:
http://www.open-std.org/jtc1/sc22/WG14/www/docs/n1256.pdf
The C language specification defines regions of undefined behavior and
implementation defined behavior (to give compiler authors enough leeway to
produce better code). In general, code in QEMU should follow the language
specification and avoid both undefined and implementation defined
constructs. ("It works fine on the gcc I tested it with" is not a valid
argument...) However there are a few areas where we allow ourselves to
assume certain behaviors because in practice all the platforms we care about
behave in the same way and writing strictly conformant code would be
painful. These are:
* you may assume that integers are 2s complement representation
* you may assume that right shift of a signed integer duplicates
the sign bit (ie it is an arithmetic shift, not a logical shift)

87
MAINTAINERS
View File

@ -132,7 +132,7 @@ Guest CPU Cores (KVM):
----------------------
Overall
M: Avi Kivity <avi@redhat.com>
M: Gleb Natapov <gleb@redhat.com>
M: Marcelo Tosatti <mtosatti@redhat.com>
L: kvm@vger.kernel.org
S: Supported
@ -150,7 +150,7 @@ S: Maintained
F: target-s390x/kvm.c
X86
M: Avi Kivity <avi@redhat.com>
M: Gleb Natapov <gleb@redhat.com>
M: Marcelo Tosatti <mtosatti@redhat.com>
L: kvm@vger.kernel.org
S: Supported
@ -268,6 +268,7 @@ S: Maintained
F: hw/xilinx_zynq.c
F: hw/zynq_slcr.c
F: hw/cadence_*
F: hw/xilinx_spips.c
CRIS Machines
-------------
@ -349,9 +350,31 @@ PowerPC Machines
405
M: Alexander Graf <agraf@suse.de>
L: qemu-ppc@nongnu.org
S: Maintained
S: Odd Fixes
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
@ -375,6 +398,19 @@ F: hw/ppc_prep.c
F: hw/prep_pci.[hc]
F: hw/pc87312.[hc]
sPAPR
M: David Gibson <david@gibson.dropbear.id.au>
M: Alexander Graf <agraf@suse.de>
L: qemu-ppc@nongnu.org
S: Supported
F: hw/spapr*
virtex_ml507
M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
L: qemu-ppc@nongnu.org
S: Odd Fixes
F: hw/virtex_ml507.c
SH4 Machines
------------
R2D
@ -399,6 +435,12 @@ 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
@ -449,9 +491,23 @@ F: hw/omap*
PCI
M: Michael S. Tsirkin <mst@redhat.com>
S: Supported
F: hw/pci/*
F: hw/pci*
F: hw/piix*
ppc4xx
M: Alexander Graf <agraf@suse.de>
L: qemu-ppc@nongnu.org
S: Odd Fixes
F: hw/ppc4xx*.[hc]
ppce500
M: Alexander Graf <agraf@suse.de>
M: Scott Wood <scottwood@freescale.com>
L: qemu-ppc@nongnu.org
S: Supported
F: hw/ppce500_*
SCSI
M: Paolo Bonzini <pbonzini@redhat.com>
S: Supported
@ -464,11 +520,22 @@ 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
@ -488,6 +555,7 @@ 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*
@ -507,6 +575,7 @@ 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
----------
@ -517,6 +586,7 @@ F: audio/
Block
M: Kevin Wolf <kwolf@redhat.com>
M: Stefan Hajnoczi <stefanha@redhat.com>
S: Supported
F: block*
F: block/
@ -526,6 +596,13 @@ 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
F: target-i386/cpu.c
Device Tree
M: Peter Crosthwaite <peter.crosthwaite@petalogix.com>
M: Alexander Graf <agraf@suse.de>
@ -569,7 +646,7 @@ F: monitor.c
Network device layer
M: Anthony Liguori <aliguori@us.ibm.com>
M: Stefan Hajnoczi <stefanha@gmail.com>
M: Stefan Hajnoczi <stefanha@redhat.com>
S: Maintained
F: net/
T: git git://github.com/stefanha/qemu.git net
@ -589,7 +666,7 @@ F: slirp/
T: git git://git.kiszka.org/qemu.git queues/slirp
Tracing
M: Stefan Hajnoczi <stefanha@gmail.com>
M: Stefan Hajnoczi <stefanha@redhat.com>
S: Maintained
F: trace/
F: scripts/tracetool.py

116
Makefile
View File

@ -8,22 +8,38 @@ ifneq ($(wildcard config-host.mak),)
# Put the all: rule here so that config-host.mak can contain dependencies.
all:
include config-host.mak
# Check that we're not trying to do an out-of-tree build from
# a tree that's been used for an in-tree build.
ifneq ($(realpath $(SRC_PATH)),$(realpath .))
ifneq ($(wildcard $(SRC_PATH)/config-host.mak),)
$(error This is an out of tree build but your source tree ($(SRC_PATH)) \
seems to have been used for an in-tree build. You can fix this by running \
"make distclean && rm -rf *-linux-user *-softmmu" in your source tree)
endif
endif
include $(SRC_PATH)/rules.mak
config-host.mak: $(SRC_PATH)/configure
@echo $@ is out-of-date, running configure
@sed -n "/.*Configured with/s/[^:]*: //p" $@ | sh
else
config-host.mak:
ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
@echo "Please call configure before running make!"
@exit 1
endif
GENERATED_HEADERS = config-host.h trace.h qemu-options.def
ifeq ($(TRACE_BACKEND),dtrace)
GENERATED_HEADERS += trace-dtrace.h
endif
GENERATED_HEADERS = config-host.h qemu-options.def
GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h
GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c trace.c
GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c
GENERATED_HEADERS += trace/generated-tracers.h
ifeq ($(TRACE_BACKEND),dtrace)
GENERATED_HEADERS += trace/generated-tracers-dtrace.h
endif
GENERATED_SOURCES += trace/generated-tracers.c
# Don't try to regenerate Makefile or configure
# We don't generate any of them
@ -52,8 +68,13 @@ SUBDIR_MAKEFLAGS=$(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)
@ -81,6 +102,7 @@ defconfig:
rm -f config-all-devices.mak $(SUBDIR_DEVICES_MAK)
-include config-all-devices.mak
-include config-all-disas.mak
all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all
@ -100,9 +122,20 @@ endif
subdir-libcacard: $(oslib-obj-y) $(trace-obj-y) qemu-timer-common.o
$(filter %-softmmu,$(SUBDIR_RULES)): $(universal-obj-y) $(trace-obj-y) $(common-obj-y) $(extra-obj-y) subdir-libdis
subdir-pixman: pixman/Makefile
$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C pixman V="$(V)" all,)
$(filter %-user,$(SUBDIR_RULES)): $(universal-obj-y) $(trace-obj-y) subdir-libdis-user subdir-libuser
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)
$(filter %-user,$(SUBDIR_RULES)): $(universal-obj-y) $(trace-obj-y) $(user-obj-y)
ROMSUBDIR_RULES=$(patsubst %,romsubdir-%, $(ROMS))
romsubdir-%:
@ -112,59 +145,45 @@ ALL_SUBDIRS=$(TARGET_DIRS) $(patsubst %,pc-bios/%, $(ROMS))
recurse-all: $(SUBDIR_RULES) $(ROMSUBDIR_RULES)
audio/audio.o audio/fmodaudio.o: QEMU_CFLAGS += $(FMOD_CFLAGS)
QEMU_CFLAGS+=$(CURL_CFLAGS)
QEMU_CFLAGS += -I$(SRC_PATH)/include
ui/cocoa.o: ui/cocoa.m
ui/sdl.o audio/sdlaudio.o ui/sdl_zoom.o hw/baum.o: QEMU_CFLAGS += $(SDL_CFLAGS)
ui/vnc.o: QEMU_CFLAGS += $(VNC_TLS_CFLAGS)
bt-host.o: QEMU_CFLAGS += $(BLUEZ_CFLAGS)
version.o: $(SRC_PATH)/version.rc config-host.h
$(call quiet-command,$(WINDRES) -I. -o $@ $<," RC $(TARGET_DIR)$@")
version-obj-$(CONFIG_WIN32) += version.o
######################################################################
# Build library with stubs
libqemustub.a: $(stub-obj-y)
######################################################################
# Support building shared library libcacard
.PHONY: libcacard.la install-libcacard
ifeq ($(LIBTOOL),)
libcacard.la:
@echo "libtool is missing, please install and rerun configure"; exit 1
install-libcacard:
@echo "libtool is missing, please install and rerun configure"; exit 1
else
libcacard.la: $(oslib-obj-y) qemu-timer-common.o $(addsuffix .lo, $(basename $(trace-obj-y)))
libcacard.la: $(oslib-obj-y) qemu-timer-common.o $(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
tools-obj-y = $(oslib-obj-y) $(trace-obj-y) qemu-tool.o qemu-timer.o \
qemu-timer-common.o main-loop.o notify.o \
iohandler.o cutils.o iov.o async.o
main-loop.o iohandler.o error.o
tools-obj-$(CONFIG_POSIX) += compatfd.o
qemu-img$(EXESUF): qemu-img.o $(tools-obj-y) $(block-obj-y)
qemu-nbd$(EXESUF): qemu-nbd.o $(tools-obj-y) $(block-obj-y)
qemu-io$(EXESUF): qemu-io.o cmd.o $(tools-obj-y) $(block-obj-y)
qemu-img$(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) $(block-obj-y) libqemustub.a
qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o
vscclient$(EXESUF): $(libcacard-y) $(oslib-obj-y) $(trace-obj-y) $(tools-obj-y) qemu-timer-common.o libcacard/vscclient.o
$(call quiet-command,$(CC) $(LDFLAGS) -o $@ $^ $(libcacard_libs) $(LIBS)," LINK $@")
vscclient$(EXESUF): LIBS += $(libcacard_libs)
vscclient$(EXESUF): $(libcacard-y) $(oslib-obj-y) $(trace-obj-y) libcacard/vscclient.o libqemustub.a
$(call LINK, $^)
fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/virtio-9p-marshal.o oslib-posix.o $(trace-obj-y)
fsdev/virtfs-proxy-helper$(EXESUF): LIBS += -lcap
@ -184,13 +203,13 @@ 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)
$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, " 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)
$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, " 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)
$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, " GEN $@")
qapi-types.c qapi-types.h :\
@ -206,27 +225,26 @@ $(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
$(qga-obj-y) qemu-ga.o: $(QGALIB_GEN)
qemu-ga$(EXESUF): qemu-ga.o $(qga-obj-y) $(tools-obj-y) $(qapi-obj-y) $(qobject-obj-y) $(version-obj-y)
QEMULIBS=libhw32 libhw64 libuser libdis libdis-user
qemu-ga$(EXESUF): $(qga-obj-y) $(oslib-obj-y) $(trace-obj-y) $(qapi-obj-y) $(qobject-obj-y) $(version-obj-y) libqemustub.a
$(call LINK, $^)
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 {} +
find . -name '*.[od]' -type f -exec rm -f {} +
rm -f *.a *.lo $(TOOLS) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
rm -Rf .libs
rm -f qemu-img-cmds.h
rm -f trace-dtrace.dtrace trace-dtrace.dtrace-timestamp
@# May not be present in GENERATED_HEADERS
rm -f trace-dtrace.h trace-dtrace.h-timestamp
rm -f trace/generated-tracers-dtrace.dtrace*
rm -f trace/generated-tracers-dtrace.h*
rm -f $(foreach f,$(GENERATED_HEADERS),$(f) $(f)-timestamp)
rm -f $(foreach f,$(GENERATED_SOURCES),$(f) $(f)-timestamp)
rm -rf qapi-generated
rm -rf qga/qapi-generated
$(MAKE) -C tests/tcg clean
for d in $(ALL_SUBDIRS) $(QEMULIBS) libcacard; do \
for d in $(ALL_SUBDIRS) libcacard; do \
if test -d $$d; then $(MAKE) -C $$d $@ || exit 1; fi; \
rm -f $$d/qemu-options.def; \
done
@ -240,7 +258,7 @@ qemu-%.tar.bz2:
distclean: clean
rm -f config-host.mak config-host.h* config-host.ld $(DOCS) qemu-options.texi qemu-img-cmds.texi qemu-monitor.texi
rm -f config-all-devices.mak
rm -f config-all-devices.mak config-all-disas.mak
rm -f roms/seabios/config.mak roms/vgabios/config.mak
rm -f qemu-doc.info qemu-doc.aux qemu-doc.cp qemu-doc.cps qemu-doc.dvi
rm -f qemu-doc.fn qemu-doc.fns qemu-doc.info qemu-doc.ky qemu-doc.kys
@ -249,9 +267,10 @@ distclean: clean
rm -f config.log
rm -f linux-headers/asm
rm -f qemu-tech.info qemu-tech.aux qemu-tech.cp qemu-tech.dvi qemu-tech.fn qemu-tech.info qemu-tech.ky qemu-tech.log qemu-tech.pdf qemu-tech.pg qemu-tech.toc qemu-tech.tp qemu-tech.vr
for d in $(TARGET_DIRS) $(QEMULIBS); do \
for d in $(TARGET_DIRS); do \
rm -rf $$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 \
@ -297,7 +316,6 @@ 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)$(bindir)"
@ -398,7 +416,9 @@ qemu-doc.dvi qemu-doc.html qemu-doc.info qemu-doc.pdf: \
# Add a dependency on the generated files, so that they are always
# rebuilt before other object files
ifneq ($(filter-out %clean,$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
Makefile: $(GENERATED_HEADERS)
endif
# Include automatically generated dependency files
# Dependencies in Makefile.objs files come from our recursive subdir rules

20
Makefile.dis
View File

@ -1,20 +0,0 @@
# Makefile for disassemblers.
include ../config-host.mak
include config.mak
include $(SRC_PATH)/rules.mak
.PHONY: all
$(call set-vpath, $(SRC_PATH))
QEMU_CFLAGS+=-I..
include $(SRC_PATH)/Makefile.objs
all: $(libdis-y)
# Dummy command so that make thinks it has done something
@true
clean:
rm -f *.o *.d *.a *~

23
Makefile.hw
View File

@ -1,23 +0,0 @@
# Makefile for qemu target independent devices.
include ../config-host.mak
include ../config-all-devices.mak
include config.mak
include $(SRC_PATH)/rules.mak
.PHONY: all
$(call set-vpath, $(SRC_PATH))
QEMU_CFLAGS+=-I..
QEMU_CFLAGS += -I$(SRC_PATH)/include
include $(SRC_PATH)/Makefile.objs
all: $(hw-obj-y)
# Dummy command so that make thinks it has done something
@true
clean:
rm -f $(addsuffix *.o, $(sort $(dir $(hw-obj-y))))
rm -f $(addsuffix *.d, $(sort $(dir $(hw-obj-y))))

153
Makefile.objs
View File

@ -1,3 +1,7 @@
#######################################################################
# Stub library, linked in tools
stub-obj-y = stubs/
#######################################################################
# Target-independent parts used in system and user emulation
universal-obj-y =
@ -17,9 +21,16 @@ qom-obj-y = qom/
universal-obj-y += $(qom-obj-y)
#######################################################################
# Core hw code (qdev core)
hw-core-obj-y += hw/
hw-core-obj-y += qemu-option.o
universal-obj-y += $(hw-core-obj-y)
#######################################################################
# oslib-obj-y is code depending on the OS (win32 vs posix)
oslib-obj-y = osdep.o
oslib-obj-y = osdep.o cutils.o qemu-timer-common.o
oslib-obj-$(CONFIG_WIN32) += oslib-win32.o qemu-thread-win32.o
oslib-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-thread-posix.o
@ -27,6 +38,8 @@ oslib-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-thread-posix.o
# coroutines
coroutine-obj-y = qemu-coroutine.o qemu-coroutine-lock.o qemu-coroutine-io.o
coroutine-obj-y += qemu-coroutine-sleep.o
# If you change this logic, please also check tests/Makefile
ifeq ($(CONFIG_UCONTEXT_COROUTINE),y)
coroutine-obj-$(CONFIG_POSIX) += coroutine-ucontext.o
else
@ -41,12 +54,14 @@ coroutine-obj-$(CONFIG_WIN32) += coroutine-win32.o
#######################################################################
# block-obj-y is code used by both qemu system emulation and qemu-img
block-obj-y = cutils.o iov.o cache-utils.o qemu-option.o module.o async.o
block-obj-y += nbd.o block.o aio.o aes.o qemu-config.o qemu-progress.o qemu-sockets.o
block-obj-y = iov.o cache-utils.o qemu-option.o module.o async.o
block-obj-y += nbd.o block.o blockjob.o aes.o qemu-config.o
block-obj-y += thread-pool.o qemu-progress.o qemu-sockets.o uri.o notify.o
block-obj-y += $(coroutine-obj-y) $(qobject-obj-y) $(version-obj-y)
block-obj-$(CONFIG_POSIX) += posix-aio-compat.o
block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
block-obj-$(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 += $(qapi-obj-y) qapi-types.o qapi-visit.o
ifeq ($(CONFIG_VIRTIO)$(CONFIG_VIRTFS)$(CONFIG_PCI),yyy)
# Lots of the fsdev/9pcode is pulled in by vl.c via qemu_fsdev_add.
@ -59,10 +74,10 @@ endif
# suppress *all* target specific code in case of system emulation, i.e. a
# single QEMU executable should support all CPUs and machines.
common-obj-y = $(block-obj-y) blockdev.o
common-obj-y += net.o net/
common-obj-y = $(block-obj-y) blockdev.o blockdev-nbd.o block/
common-obj-y += net/
common-obj-y += qom/
common-obj-y += readline.o console.o cursor.o
common-obj-y += readline.o
common-obj-y += $(oslib-obj-y)
common-obj-$(CONFIG_WIN32) += os-win32.o
common-obj-$(CONFIG_POSIX) += os-posix.o
@ -71,11 +86,10 @@ common-obj-$(CONFIG_LINUX) += fsdev/
extra-obj-$(CONFIG_LINUX) += fsdev/
common-obj-y += tcg-runtime.o host-utils.o main-loop.o
common-obj-y += input.o
common-obj-y += buffered_file.o migration.o migration-tcp.o
common-obj-y += migration.o migration-tcp.o
common-obj-y += migration.o migration-tcp.o
common-obj-y += qemu-char.o #aio.o
common-obj-y += block-migration.o iohandler.o
common-obj-y += pflib.o
common-obj-y += bitmap.o bitops.o
common-obj-y += page_cache.o
@ -86,116 +100,51 @@ common-obj-$(CONFIG_SPICE) += spice-qemu-char.o
common-obj-y += audio/
common-obj-y += hw/
extra-obj-y += hw/
common-obj-y += ui/
common-obj-y += bt-host.o bt-vhci.o
common-obj-y += iov.o acl.o
common-obj-y += dma-helpers.o
common-obj-y += acl.o
common-obj-$(CONFIG_POSIX) += compatfd.o
common-obj-y += notify.o event_notifier.o
common-obj-y += qemu-timer.o qemu-timer-common.o
common-obj-y += qtest.o
common-obj-y += vl.o
common-obj-$(CONFIG_SLIRP) += slirp/
common-obj-y += backends/
######################################################################
# libseccomp
ifeq ($(CONFIG_SECCOMP),y)
common-obj-y += qemu-seccomp.o
endif
######################################################################
# libuser
user-obj-y =
user-obj-y += envlist.o path.o
user-obj-y += tcg-runtime.o host-utils.o
user-obj-y += cutils.o iov.o cache-utils.o
user-obj-y += cache-utils.o
user-obj-y += module.o
user-obj-y += qemu-user.o
user-obj-y += $(trace-obj-y)
user-obj-y += qom/
######################################################################
# libhw
hw-obj-y = vl.o dma-helpers.o qtest.o hw/
######################################################################
# libdis
# disassemblers
# NOTE: the disassembler code is only needed for debugging
libdis-y =
libdis-$(CONFIG_ALPHA_DIS) += alpha-dis.o
libdis-$(CONFIG_ARM_DIS) += arm-dis.o
libdis-$(CONFIG_CRIS_DIS) += cris-dis.o
libdis-$(CONFIG_HPPA_DIS) += hppa-dis.o
libdis-$(CONFIG_I386_DIS) += i386-dis.o
libdis-$(CONFIG_IA64_DIS) += ia64-dis.o
libdis-$(CONFIG_M68K_DIS) += m68k-dis.o
libdis-$(CONFIG_MICROBLAZE_DIS) += microblaze-dis.o
libdis-$(CONFIG_MIPS_DIS) += mips-dis.o
libdis-$(CONFIG_PPC_DIS) += ppc-dis.o
libdis-$(CONFIG_S390_DIS) += s390-dis.o
libdis-$(CONFIG_SH4_DIS) += sh4-dis.o
libdis-$(CONFIG_SPARC_DIS) += sparc-dis.o
libdis-$(CONFIG_LM32_DIS) += lm32-dis.o
universal-obj-y += disas/
######################################################################
# trace
ifeq ($(TRACE_BACKEND),dtrace)
TRACE_H_EXTRA_DEPS=trace-dtrace.h
endif
trace.h: trace.h-timestamp $(TRACE_H_EXTRA_DEPS)
trace.h-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak
$(call quiet-command,$(TRACETOOL) \
--format=h \
--backend=$(TRACE_BACKEND) \
< $< > $@," GEN trace.h")
@cmp -s $@ trace.h || cp $@ trace.h
trace-obj-y += trace/
trace.c: trace.c-timestamp
trace.c-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak
$(call quiet-command,$(TRACETOOL) \
--format=c \
--backend=$(TRACE_BACKEND) \
< $< > $@," GEN trace.c")
@cmp -s $@ trace.c || cp $@ trace.c
trace.o: trace.c $(GENERATED_HEADERS)
trace-dtrace.h: trace-dtrace.dtrace
$(call quiet-command,dtrace -o $@ -h -s $<, " GEN trace-dtrace.h")
# Normal practice is to name DTrace probe file with a '.d' extension
# but that gets picked up by QEMU's Makefile as an external dependency
# rule file. So we use '.dtrace' instead
trace-dtrace.dtrace: trace-dtrace.dtrace-timestamp
trace-dtrace.dtrace-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak
$(call quiet-command,$(TRACETOOL) \
--format=d \
--backend=$(TRACE_BACKEND) \
< $< > $@," GEN trace-dtrace.dtrace")
@cmp -s $@ trace-dtrace.dtrace || cp $@ trace-dtrace.dtrace
trace-dtrace.o: trace-dtrace.dtrace $(GENERATED_HEADERS)
$(call quiet-command,dtrace -o $@ -G -s $<, " GEN trace-dtrace.o")
ifeq ($(LIBTOOL),)
trace-dtrace.lo: trace-dtrace.dtrace
@echo "missing libtool. please install and rerun configure."; exit 1
else
trace-dtrace.lo: trace-dtrace.dtrace
$(call quiet-command,$(LIBTOOL) --mode=compile --tag=CC dtrace -o $@ -G -s $<, " lt GEN trace-dtrace.o")
endif
trace/simple.o: trace/simple.c $(GENERATED_HEADERS)
trace-obj-$(CONFIG_TRACE_DTRACE) += trace-dtrace.o
ifneq ($(TRACE_BACKEND),dtrace)
trace-obj-y = trace.o
endif
trace-obj-$(CONFIG_TRACE_DEFAULT) += trace/default.o
trace-obj-$(CONFIG_TRACE_SIMPLE) += trace/simple.o
trace-obj-$(CONFIG_TRACE_SIMPLE) += qemu-timer-common.o
trace-obj-$(CONFIG_TRACE_STDERR) += trace/stderr.o
trace-obj-y += trace/control.o
$(trace-obj-y): $(GENERATED_HEADERS)
universal-obj-y += $(trace-obj-y)
######################################################################
# smartcard
@ -222,9 +171,8 @@ universal-obj-y += $(qapi-obj-y)
######################################################################
# guest agent
qga-obj-y = qga/ qemu-ga.o module.o
qga-obj-$(CONFIG_WIN32) += oslib-win32.o
qga-obj-$(CONFIG_POSIX) += oslib-posix.o qemu-sockets.o qemu-option.o
qga-obj-y = qga/ module.o qemu-tool.o
qga-obj-$(CONFIG_POSIX) += qemu-sockets.o qemu-option.o
vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
@ -233,12 +181,15 @@ vl.o: QEMU_CFLAGS+=$(SDL_CFLAGS)
QEMU_CFLAGS+=$(GLIB_CFLAGS)
nested-vars += \
hw-obj-y \
stub-obj-y \
qga-obj-y \
block-obj-y \
qom-obj-y \
qapi-obj-y \
block-obj-y \
user-obj-y \
common-obj-y \
extra-obj-y
universal-obj-y \
hw-core-obj-y \
extra-obj-y \
trace-obj-y
dummy := $(call unnest-vars)

35
Makefile.target
View File

@ -4,9 +4,6 @@ include ../config-host.mak
include config-devices.mak
include config-target.mak
include $(SRC_PATH)/rules.mak
ifneq ($(HWDIR),)
include $(HWDIR)/config.mak
endif
$(call set-vpath, $(SRC_PATH))
ifdef CONFIG_LINUX
@ -72,22 +69,12 @@ all: $(PROGS) stap
obj-y = exec.o translate-all.o cpu-exec.o
obj-y += tcg/tcg.o tcg/optimize.o
obj-$(CONFIG_TCG_INTERPRETER) += tci.o
obj-$(CONFIG_TCG_INTERPRETER) += disas/tci.o
obj-y += fpu/softfloat.o
obj-y += disas.o
obj-$(CONFIG_TCI_DIS) += tci-dis.o
obj-y += target-$(TARGET_BASE_ARCH)/
obj-y += disas.o
obj-$(CONFIG_GDBSTUB_XML) += gdbstub-xml.o
tci-dis.o: QEMU_CFLAGS += -I$(SRC_PATH)/tcg -I$(SRC_PATH)/tcg/tci
# HELPER_CFLAGS is used for all the legacy code compiled with static register
# variables
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 += $(HELPER_CFLAGS)
#########################################################
# Linux user emulator target
@ -132,11 +119,6 @@ obj-$(CONFIG_NO_GET_MEMORY_MAPPING) += memory_mapping-stub.o
obj-$(CONFIG_NO_CORE_DUMP) += dump-stub.o
LIBS+=-lz
QEMU_CFLAGS += $(VNC_TLS_CFLAGS)
QEMU_CFLAGS += $(VNC_SASL_CFLAGS)
QEMU_CFLAGS += $(VNC_JPEG_CFLAGS)
QEMU_CFLAGS += $(VNC_PNG_CFLAGS)
# xen support
obj-$(CONFIG_XEN) += xen-all.o xen-mapcache.o
obj-$(CONFIG_NO_XEN) += xen-stub.o
@ -154,6 +136,9 @@ GENERATED_HEADERS += hmp-commands.h qmp-commands-old.h
endif # CONFIG_SOFTMMU
# Workaround for http://gcc.gnu.org/PR55489, see configure.
%/translate.o: QEMU_CFLAGS += $(TRANSLATE_OPT_CFLAGS)
nested-vars += obj-y
# This resolves all nested paths, so it must come last
@ -164,22 +149,18 @@ all-obj-y += $(addprefix ../, $(universal-obj-y))
ifdef CONFIG_SOFTMMU
all-obj-y += $(addprefix ../, $(common-obj-y))
all-obj-y += $(addprefix ../libdis/, $(libdis-y))
all-obj-y += $(addprefix $(HWDIR)/, $(hw-obj-y))
all-obj-y += $(addprefix ../, $(trace-obj-y))
else
all-obj-y += $(addprefix ../libuser/, $(user-obj-y))
all-obj-y += $(addprefix ../libdis-user/, $(libdis-y))
all-obj-y += $(addprefix ../, $(user-obj-y))
endif #CONFIG_LINUX_USER
ifdef QEMU_PROGW
# The linker builds a windows executable. Make also a console executable.
$(QEMU_PROGW): $(all-obj-y)
$(QEMU_PROGW): $(all-obj-y) ../libqemustub.a
$(call LINK,$^)
$(QEMU_PROG): $(QEMU_PROGW)
$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG)," GEN $(TARGET_DIR)$(QEMU_PROG)")
else
$(QEMU_PROG): $(all-obj-y)
$(QEMU_PROG): $(all-obj-y) ../libqemustub.a
$(call LINK,$^)
endif

24
Makefile.user
View File

@ -1,24 +0,0 @@
# Makefile for qemu target independent user files.
include ../config-host.mak
include $(SRC_PATH)/rules.mak
-include config.mak
.PHONY: all
$(call set-vpath, $(SRC_PATH))
QEMU_CFLAGS+=-I..
QEMU_CFLAGS += -I$(SRC_PATH)/include
QEMU_CFLAGS += -DCONFIG_USER_ONLY
include $(SRC_PATH)/Makefile.objs
all: $(user-obj-y)
# Dummy command so that make thinks it has done something
@true
clean:
for d in . trace; do \
rm -f $$d/*.o $$d/*.d $$d/*.a $$d/*~; \
done

299
QMP/qemu-ga-client Executable file
View File

@ -0,0 +1,299 @@
#!/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:])

46
QMP/qmp-events.txt
View File

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

46
QMP/qmp-shell
View File

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

33
QMP/qmp.py
View File

@ -49,7 +49,6 @@ 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
@ -73,7 +72,7 @@ class QEMUMonitorProtocol:
error = socket.error
def connect(self):
def connect(self, negotiate=True):
"""
Connect to the QMP Monitor and perform capabilities negotiation.
@ -83,7 +82,9 @@ class QEMUMonitorProtocol:
@raise QMPCapabilitiesError if fails to negotiate capabilities
"""
self.__sock.connect(self.__address)
return self.__negotiate_capabilities()
self.__sockfile = self.__sock.makefile()
if negotiate:
return self.__negotiate_capabilities()
def accept(self):
"""
@ -95,6 +96,7 @@ 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):
@ -134,6 +136,26 @@ 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.
@ -161,3 +183,8 @@ class QEMUMonitorProtocol:
def close(self):
self.__sock.close()
self.__sockfile.close()
timeout = socket.timeout
def settimeout(self, timeout):
self.__sock.settimeout(timeout)

2
VERSION
View File

@ -1 +1 @@
1.1.50
1.3.50

430
a.out.h
View File

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

2
acl.c
View File

@ -24,7 +24,7 @@
#include "qemu-common.h"
#include "acl.h"
#include "qemu/acl.h"
#ifdef CONFIG_FNMATCH
#include <fnmatch.h>

2
aes.c
View File

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

268
aio-posix.c Normal file
View File

@ -0,0 +1,268 @@
/*
* QEMU aio implementation
*
* Copyright IBM, Corp. 2008
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Contributions after 2012-01-13 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu-common.h"
#include "block/block.h"
#include "qemu/queue.h"
#include "qemu/sockets.h"
struct AioHandler
{
GPollFD pfd;
IOHandler *io_read;
IOHandler *io_write;
AioFlushHandler *io_flush;
int deleted;
void *opaque;
QLIST_ENTRY(AioHandler) node;
};
static AioHandler *find_aio_handler(AioContext *ctx, int fd)
{
AioHandler *node;
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
if (node->pfd.fd == fd)
if (!node->deleted)
return node;
}
return NULL;
}
void aio_set_fd_handler(AioContext *ctx,
int fd,
IOHandler *io_read,
IOHandler *io_write,
AioFlushHandler *io_flush,
void *opaque)
{
AioHandler *node;
node = find_aio_handler(ctx, fd);
/* Are we deleting the fd handler? */
if (!io_read && !io_write) {
if (node) {
g_source_remove_poll(&ctx->source, &node->pfd);
/* If the lock is held, just mark the node as deleted */
if (ctx->walking_handlers) {
node->deleted = 1;
node->pfd.revents = 0;
} else {
/* Otherwise, delete it for real. We can't just mark it as
* deleted because deleted nodes are only cleaned up after
* releasing the walking_handlers lock.
*/
QLIST_REMOVE(node, node);
g_free(node);
}
}
} else {
if (node == NULL) {
/* Alloc and insert if it's not already there */
node = g_malloc0(sizeof(AioHandler));
node->pfd.fd = fd;
QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
g_source_add_poll(&ctx->source, &node->pfd);
}
/* Update handler with latest information */
node->io_read = io_read;
node->io_write = io_write;
node->io_flush = io_flush;
node->opaque = opaque;
node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP : 0);
node->pfd.events |= (io_write ? G_IO_OUT : 0);
}
aio_notify(ctx);
}
void aio_set_event_notifier(AioContext *ctx,
EventNotifier *notifier,
EventNotifierHandler *io_read,
AioFlushEventNotifierHandler *io_flush)
{
aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
(IOHandler *)io_read, NULL,
(AioFlushHandler *)io_flush, notifier);
}
bool aio_pending(AioContext *ctx)
{
AioHandler *node;
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
int revents;
/*
* FIXME: right now we cannot get G_IO_HUP and G_IO_ERR because
* main-loop.c is still select based (due to the slirp legacy).
* If main-loop.c ever switches to poll, G_IO_ERR should be
* tested too. Dispatching G_IO_ERR to both handlers should be
* okay, since handlers need to be ready for spurious wakeups.
*/
revents = node->pfd.revents & node->pfd.events;
if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
return true;
}
if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
return true;
}
}
return false;
}
bool aio_poll(AioContext *ctx, bool blocking)
{
static struct timeval tv0;
AioHandler *node;
fd_set rdfds, wrfds;
int max_fd = -1;
int ret;
bool busy, progress;
progress = false;
/*
* If there are callbacks left that have been queued, we need to call then.
* Do not call select in this case, because it is possible that the caller
* does not need a complete flush (as is the case for qemu_aio_wait loops).
*/
if (aio_bh_poll(ctx)) {
blocking = false;
progress = true;
}
/*
* Then dispatch any pending callbacks from the GSource.
*
* We have to walk very carefully in case qemu_aio_set_fd_handler is
* called while we're walking.
*/
node = QLIST_FIRST(&ctx->aio_handlers);
while (node) {
AioHandler *tmp;
int revents;
ctx->walking_handlers++;
revents = node->pfd.revents & node->pfd.events;
node->pfd.revents = 0;
/* See comment in aio_pending. */
if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
node->io_read(node->opaque);
progress = true;
}
if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
node->io_write(node->opaque);
progress = true;
}
tmp = node;
node = QLIST_NEXT(node, node);
ctx->walking_handlers--;
if (!ctx->walking_handlers && tmp->deleted) {
QLIST_REMOVE(tmp, node);
g_free(tmp);
}
}
if (progress && !blocking) {
return true;
}
ctx->walking_handlers++;
FD_ZERO(&rdfds);
FD_ZERO(&wrfds);
/* fill fd sets */
busy = false;
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
/* If there aren't pending AIO operations, don't invoke callbacks.
* Otherwise, if there are no AIO requests, qemu_aio_wait() would
* wait indefinitely.
*/
if (!node->deleted && node->io_flush) {
if (node->io_flush(node->opaque) == 0) {
continue;
}
busy = true;
}
if (!node->deleted && node->io_read) {
FD_SET(node->pfd.fd, &rdfds);
max_fd = MAX(max_fd, node->pfd.fd + 1);
}
if (!node->deleted && node->io_write) {
FD_SET(node->pfd.fd, &wrfds);
max_fd = MAX(max_fd, node->pfd.fd + 1);
}
}
ctx->walking_handlers--;
/* No AIO operations? Get us out of here */
if (!busy) {
return progress;
}
/* wait until next event */
ret = select(max_fd, &rdfds, &wrfds, NULL, blocking ? NULL : &tv0);
/* if we have any readable fds, dispatch event */
if (ret > 0) {
/* we have to walk very carefully in case
* qemu_aio_set_fd_handler is called while we're walking */
node = QLIST_FIRST(&ctx->aio_handlers);
while (node) {
AioHandler *tmp;
ctx->walking_handlers++;
if (!node->deleted &&
FD_ISSET(node->pfd.fd, &rdfds) &&
node->io_read) {
node->io_read(node->opaque);
progress = true;
}
if (!node->deleted &&
FD_ISSET(node->pfd.fd, &wrfds) &&
node->io_write) {
node->io_write(node->opaque);
progress = true;
}
tmp = node;
node = QLIST_NEXT(node, node);
ctx->walking_handlers--;
if (!ctx->walking_handlers && tmp->deleted) {
QLIST_REMOVE(tmp, node);
g_free(tmp);
}
}
}
return progress;
}

218
aio-win32.c Normal file
View File

@ -0,0 +1,218 @@
/*
* QEMU aio implementation
*
* Copyright IBM Corp., 2008
* Copyright Red Hat Inc., 2012
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
* Paolo Bonzini <pbonzini@redhat.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Contributions after 2012-01-13 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu-common.h"
#include "block/block.h"
#include "qemu/queue.h"
#include "qemu/sockets.h"
struct AioHandler {
EventNotifier *e;
EventNotifierHandler *io_notify;
AioFlushEventNotifierHandler *io_flush;
GPollFD pfd;
int deleted;
QLIST_ENTRY(AioHandler) node;
};
void aio_set_event_notifier(AioContext *ctx,
EventNotifier *e,
EventNotifierHandler *io_notify,
AioFlushEventNotifierHandler *io_flush)
{
AioHandler *node;
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
if (node->e == e && !node->deleted) {
break;
}
}
/* Are we deleting the fd handler? */
if (!io_notify) {
if (node) {
g_source_remove_poll(&ctx->source, &node->pfd);
/* If the lock is held, just mark the node as deleted */
if (ctx->walking_handlers) {
node->deleted = 1;
node->pfd.revents = 0;
} else {
/* Otherwise, delete it for real. We can't just mark it as
* deleted because deleted nodes are only cleaned up after
* releasing the walking_handlers lock.
*/
QLIST_REMOVE(node, node);
g_free(node);
}
}
} else {
if (node == NULL) {
/* Alloc and insert if it's not already there */
node = g_malloc0(sizeof(AioHandler));
node->e = e;
node->pfd.fd = (uintptr_t)event_notifier_get_handle(e);
node->pfd.events = G_IO_IN;
QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
g_source_add_poll(&ctx->source, &node->pfd);
}
/* Update handler with latest information */
node->io_notify = io_notify;
node->io_flush = io_flush;
}
aio_notify(ctx);
}
bool aio_pending(AioContext *ctx)
{
AioHandler *node;
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
if (node->pfd.revents && node->io_notify) {
return true;
}
}
return false;
}
bool aio_poll(AioContext *ctx, bool blocking)
{
AioHandler *node;
HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
bool busy, progress;
int count;
progress = false;
/*
* If there are callbacks left that have been queued, we need to call then.
* Do not call select in this case, because it is possible that the caller
* does not need a complete flush (as is the case for qemu_aio_wait loops).
*/
if (aio_bh_poll(ctx)) {
blocking = false;
progress = true;
}
/*
* Then dispatch any pending callbacks from the GSource.
*
* We have to walk very carefully in case qemu_aio_set_fd_handler is
* called while we're walking.
*/
node = QLIST_FIRST(&ctx->aio_handlers);
while (node) {
AioHandler *tmp;
ctx->walking_handlers++;
if (node->pfd.revents && node->io_notify) {
node->pfd.revents = 0;
node->io_notify(node->e);
progress = true;
}
tmp = node;
node = QLIST_NEXT(node, node);
ctx->walking_handlers--;
if (!ctx->walking_handlers && tmp->deleted) {
QLIST_REMOVE(tmp, node);
g_free(tmp);
}
}
if (progress && !blocking) {
return true;
}
ctx->walking_handlers++;
/* fill fd sets */
busy = false;
count = 0;
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
/* If there aren't pending AIO operations, don't invoke callbacks.
* Otherwise, if there are no AIO requests, qemu_aio_wait() would
* wait indefinitely.
*/
if (!node->deleted && node->io_flush) {
if (node->io_flush(node->e) == 0) {
continue;
}
busy = true;
}
if (!node->deleted && node->io_notify) {
events[count++] = event_notifier_get_handle(node->e);
}
}
ctx->walking_handlers--;
/* No AIO operations? Get us out of here */
if (!busy) {
return progress;
}
/* wait until next event */
while (count > 0) {
int timeout = blocking ? INFINITE : 0;
int ret = WaitForMultipleObjects(count, events, FALSE, timeout);
/* if we have any signaled events, dispatch event */
if ((DWORD) (ret - WAIT_OBJECT_0) >= count) {
break;
}
blocking = false;
/* we have to walk very carefully in case
* qemu_aio_set_fd_handler is called while we're walking */
node = QLIST_FIRST(&ctx->aio_handlers);
while (node) {
AioHandler *tmp;
ctx->walking_handlers++;
if (!node->deleted &&
event_notifier_get_handle(node->e) == events[ret - WAIT_OBJECT_0] &&
node->io_notify) {
node->io_notify(node->e);
progress = true;
}
tmp = node;
node = QLIST_NEXT(node, node);
ctx->walking_handlers--;
if (!ctx->walking_handlers && tmp->deleted) {
QLIST_REMOVE(tmp, node);
g_free(tmp);
}
}
/* Try again, but only call each handler once. */
events[ret - WAIT_OBJECT_0] = events[--count];
}
return progress;
}

194
aio.c
View File

@ -1,194 +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"
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;
}

366
arch_init.c
View File

@ -29,21 +29,26 @@
#include <sys/mman.h>
#endif
#include "config.h"
#include "monitor.h"
#include "sysemu.h"
#include "arch_init.h"
#include "monitor/monitor.h"
#include "sysemu/sysemu.h"
#include "qemu/bitops.h"
#include "qemu/bitmap.h"
#include "sysemu/arch_init.h"
#include "audio/audio.h"
#include "hw/pc.h"
#include "hw/pci.h"
#include "hw/pci/pci.h"
#include "hw/audiodev.h"
#include "kvm.h"
#include "migration.h"
#include "net.h"
#include "gdbstub.h"
#include "sysemu/kvm.h"
#include "migration/migration.h"
#include "exec/gdbstub.h"
#include "hw/smbios.h"
#include "exec-memory.h"
#include "exec/address-spaces.h"
#include "hw/pcspk.h"
#include "qemu/page_cache.h"
#include "migration/page_cache.h"
#include "qemu/config-file.h"
#include "qmp-commands.h"
#include "trace.h"
#include "exec/cpu-all.h"
#ifdef DEBUG_ARCH_INIT
#define DPRINTF(fmt, ...) \
@ -135,7 +140,6 @@ 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 */
@ -261,16 +265,21 @@ 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)
static size_t 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));
}
size_t size;
qemu_put_be64(f, offset | cont | flag);
size = 8;
if (!cont) {
qemu_put_byte(f, strlen(block->idstr));
qemu_put_buffer(f, (uint8_t *)block->idstr,
strlen(block->idstr));
size += 1 + strlen(block->idstr);
}
return size;
}
#define ENCODING_FLAG_XBZRLE 0x1
@ -317,56 +326,147 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
}
/* Send XBZRLE based compressed page */
save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_XBZRLE);
bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_XBZRLE);
qemu_put_byte(f, ENCODING_FLAG_XBZRLE);
qemu_put_be16(f, encoded_len);
qemu_put_buffer(f, XBZRLE.encoded_buf, encoded_len);
bytes_sent = encoded_len + 1 + 2;
bytes_sent += encoded_len + 1 + 2;
acct_info.xbzrle_pages++;
acct_info.xbzrle_bytes += bytes_sent;
return bytes_sent;
}
static RAMBlock *last_block;
/* This is the last block that we have visited serching for dirty pages
*/
static RAMBlock *last_seen_block;
/* This is the last block from where we have sent data */
static RAMBlock *last_sent_block;
static ram_addr_t last_offset;
static unsigned long *migration_bitmap;
static uint64_t migration_dirty_pages;
static uint32_t last_version;
static inline
ram_addr_t migration_bitmap_find_and_reset_dirty(MemoryRegion *mr,
ram_addr_t start)
{
unsigned long base = mr->ram_addr >> TARGET_PAGE_BITS;
unsigned long nr = base + (start >> TARGET_PAGE_BITS);
unsigned long size = base + (int128_get64(mr->size) >> TARGET_PAGE_BITS);
unsigned long next = find_next_bit(migration_bitmap, size, nr);
if (next < size) {
clear_bit(next, migration_bitmap);
migration_dirty_pages--;
}
return (next - base) << TARGET_PAGE_BITS;
}
static inline bool migration_bitmap_set_dirty(MemoryRegion *mr,
ram_addr_t offset)
{
bool ret;
int nr = (mr->ram_addr + offset) >> TARGET_PAGE_BITS;
ret = test_and_set_bit(nr, migration_bitmap);
if (!ret) {
migration_dirty_pages++;
}
return ret;
}
static void migration_bitmap_sync(void)
{
RAMBlock *block;
ram_addr_t addr;
uint64_t num_dirty_pages_init = migration_dirty_pages;
MigrationState *s = migrate_get_current();
static int64_t start_time;
static int64_t num_dirty_pages_period;
int64_t end_time;
if (!start_time) {
start_time = qemu_get_clock_ms(rt_clock);
}
trace_migration_bitmap_sync_start();
memory_global_sync_dirty_bitmap(get_system_memory());
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
for (addr = 0; addr < block->length; addr += TARGET_PAGE_SIZE) {
if (memory_region_test_and_clear_dirty(block->mr,
addr, TARGET_PAGE_SIZE,
DIRTY_MEMORY_MIGRATION)) {
migration_bitmap_set_dirty(block->mr, addr);
}
}
}
trace_migration_bitmap_sync_end(migration_dirty_pages
- num_dirty_pages_init);
num_dirty_pages_period += migration_dirty_pages - num_dirty_pages_init;
end_time = qemu_get_clock_ms(rt_clock);
/* more than 1 second = 1000 millisecons */
if (end_time > start_time + 1000) {
s->dirty_pages_rate = num_dirty_pages_period * 1000
/ (end_time - start_time);
start_time = end_time;
num_dirty_pages_period = 0;
}
}
/*
* ram_save_block: Writes a page of memory to the stream f
*
* Returns: 0: if the page hasn't changed
* -1: if there are no more dirty pages
* n: the amount of bytes written in other case
* Returns: The number of bytes written.
* 0 means no dirty pages
*/
static int ram_save_block(QEMUFile *f, bool last_stage)
{
RAMBlock *block = last_block;
RAMBlock *block = last_seen_block;
ram_addr_t offset = last_offset;
int bytes_sent = -1;
bool complete_round = false;
int bytes_sent = 0;
MemoryRegion *mr;
ram_addr_t current_addr;
if (!block)
block = QLIST_FIRST(&ram_list.blocks);
block = QTAILQ_FIRST(&ram_list.blocks);
do {
while (true) {
mr = block->mr;
if (memory_region_get_dirty(mr, offset, TARGET_PAGE_SIZE,
DIRTY_MEMORY_MIGRATION)) {
offset = migration_bitmap_find_and_reset_dirty(mr, offset);
if (complete_round && block == last_seen_block &&
offset >= last_offset) {
break;
}
if (offset >= block->length) {
offset = 0;
block = QTAILQ_NEXT(block, next);
if (!block) {
block = QTAILQ_FIRST(&ram_list.blocks);
complete_round = true;
}
} else {
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);
int cont = (block == last_sent_block) ?
RAM_SAVE_FLAG_CONTINUE : 0;
p = memory_region_get_ram_ptr(mr) + offset;
/* In doubt sent page as normal */
bytes_sent = -1;
if (is_dup_page(p)) {
acct_info.dup_pages++;
save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_COMPRESS);
bytes_sent = save_block_hdr(f, block, offset, cont,
RAM_SAVE_FLAG_COMPRESS);
qemu_put_byte(f, *p);
bytes_sent = 1;
bytes_sent += 1;
} else if (migrate_use_xbzrle()) {
current_addr = block->offset + offset;
bytes_sent = save_xbzrle_page(f, p, current_addr, block,
@ -376,30 +476,22 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
}
}
/* either we didn't send yet (we may have had XBZRLE overflow) */
/* XBZRLE overflow or normal page */
if (bytes_sent == -1) {
save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
bytes_sent = TARGET_PAGE_SIZE;
bytes_sent += TARGET_PAGE_SIZE;
acct_info.norm_pages++;
}
/* if page is unmodified, continue to the next */
if (bytes_sent != 0) {
if (bytes_sent > 0) {
last_sent_block = block;
break;
}
}
offset += TARGET_PAGE_SIZE;
if (offset >= block->length) {
offset = 0;
block = QLIST_NEXT(block, next);
if (!block)
block = QLIST_FIRST(&ram_list.blocks);
}
} while (block != last_block || offset != last_offset);
last_block = block;
}
last_seen_block = block;
last_offset = offset;
return bytes_sent;
@ -409,7 +501,7 @@ static uint64_t bytes_transferred;
static ram_addr_t ram_save_remaining(void)
{
return ram_list.dirty_pages;
return migration_dirty_pages;
}
uint64_t ram_bytes_remaining(void)
@ -427,46 +519,21 @@ uint64_t ram_bytes_total(void)
RAMBlock *block;
uint64_t total = 0;
QLIST_FOREACH(block, &ram_list.blocks, next)
QTAILQ_FOREACH(block, &ram_list.blocks, next)
total += block->length;
return total;
}
static int block_compar(const void *a, const void *b)
{
RAMBlock * const *ablock = a;
RAMBlock * const *bblock = b;
return strcmp((*ablock)->idstr, (*bblock)->idstr);
}
static void sort_ram_list(void)
{
RAMBlock *block, *nblock, **blocks;
int n;
n = 0;
QLIST_FOREACH(block, &ram_list.blocks, next) {
++n;
}
blocks = g_malloc(n * sizeof *blocks);
n = 0;
QLIST_FOREACH_SAFE(block, &ram_list.blocks, next, nblock) {
blocks[n++] = block;
QLIST_REMOVE(block, next);
}
qsort(blocks, n, sizeof *blocks, block_compar);
while (--n >= 0) {
QLIST_INSERT_HEAD(&ram_list.blocks, blocks[n], next);
}
g_free(blocks);
}
static void migration_end(void)
{
memory_global_dirty_log_stop();
if (migration_bitmap) {
memory_global_dirty_log_stop();
g_free(migration_bitmap);
migration_bitmap = NULL;
}
if (migrate_use_xbzrle()) {
if (XBZRLE.cache) {
cache_fini(XBZRLE.cache);
g_free(XBZRLE.cache);
g_free(XBZRLE.encoded_buf);
@ -481,17 +548,28 @@ static void ram_migration_cancel(void *opaque)
migration_end();
}
static void reset_ram_globals(void)
{
last_seen_block = NULL;
last_sent_block = NULL;
last_offset = 0;
last_version = ram_list.version;
}
#define MAX_WAIT 50 /* ms, half buffered_file limit */
static int ram_save_setup(QEMUFile *f, void *opaque)
{
ram_addr_t addr;
RAMBlock *block;
int64_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;
migration_bitmap = bitmap_new(ram_pages);
bitmap_set(migration_bitmap, 0, ram_pages);
migration_dirty_pages = ram_pages;
qemu_mutex_lock_ramlist();
bytes_transferred = 0;
last_block = NULL;
last_offset = 0;
sort_ram_list();
reset_ram_globals();
if (migrate_use_xbzrle()) {
XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
@ -506,26 +584,18 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
acct_clear();
}
/* Make sure all dirty bits are set */
QLIST_FOREACH(block, &ram_list.blocks, next) {
for (addr = 0; addr < block->length; addr += TARGET_PAGE_SIZE) {
if (!memory_region_get_dirty(block->mr, addr, TARGET_PAGE_SIZE,
DIRTY_MEMORY_MIGRATION)) {
memory_region_set_dirty(block->mr, addr, TARGET_PAGE_SIZE);
}
}
}
memory_global_dirty_log_start();
migration_bitmap_sync();
qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE);
QLIST_FOREACH(block, &ram_list.blocks, next) {
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
qemu_put_byte(f, strlen(block->idstr));
qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr));
qemu_put_be64(f, block->length);
}
qemu_mutex_unlock_ramlist();
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
return 0;
@ -533,25 +603,28 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
static int ram_save_iterate(QEMUFile *f, void *opaque)
{
uint64_t bytes_transferred_last;
double bwidth = 0;
int ret;
int i;
uint64_t expected_time;
int64_t t0;
int total_sent = 0;
bytes_transferred_last = bytes_transferred;
bwidth = qemu_get_clock_ns(rt_clock);
qemu_mutex_lock_ramlist();
if (ram_list.version != last_version) {
reset_ram_globals();
}
t0 = qemu_get_clock_ns(rt_clock);
i = 0;
while ((ret = qemu_file_rate_limit(f)) == 0) {
int bytes_sent;
bytes_sent = ram_save_block(f, false);
/* no more blocks to sent */
if (bytes_sent < 0) {
if (bytes_sent == 0) {
break;
}
bytes_transferred += bytes_sent;
total_sent += 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.
@ -559,9 +632,9 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
iterations
*/
if ((i & 63) == 0) {
uint64_t t1 = (qemu_get_clock_ns(rt_clock) - bwidth) / 1000000;
uint64_t t1 = (qemu_get_clock_ns(rt_clock) - t0) / 1000000;
if (t1 > MAX_WAIT) {
DPRINTF("big wait: " PRIu64 " milliseconds, %d iterations\n",
DPRINTF("big wait: %" PRIu64 " milliseconds, %d iterations\n",
t1, i);
break;
}
@ -570,37 +643,23 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
}
if (ret < 0) {
bytes_transferred += total_sent;
return ret;
}
bwidth = qemu_get_clock_ns(rt_clock) - bwidth;
bwidth = (bytes_transferred - bytes_transferred_last) / bwidth;
/* if we haven't transferred anything this round, force expected_time to a
* a very high value, but without crashing */
if (bwidth == 0) {
bwidth = 0.000001;
}
qemu_mutex_unlock_ramlist();
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
total_sent += 8;
bytes_transferred += total_sent;
expected_time = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
DPRINTF("ram_save_live: expected(" PRIu64 ") <= max(" PRIu64 ")?\n",
expected_time, migrate_max_downtime());
if (expected_time <= migrate_max_downtime()) {
memory_global_sync_dirty_bitmap(get_system_memory());
expected_time = ram_save_remaining() * TARGET_PAGE_SIZE / bwidth;
return expected_time <= migrate_max_downtime();
}
return 0;
return total_sent;
}
static int ram_save_complete(QEMUFile *f, void *opaque)
{
memory_global_sync_dirty_bitmap(get_system_memory());
migration_bitmap_sync();
qemu_mutex_lock_ramlist();
/* try transferring iterative blocks of memory */
@ -610,18 +669,32 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
bytes_sent = ram_save_block(f, true);
/* no more blocks to sent */
if (bytes_sent < 0) {
if (bytes_sent == 0) {
break;
}
bytes_transferred += bytes_sent;
}
memory_global_dirty_log_stop();
migration_end();
qemu_mutex_unlock_ramlist();
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
return 0;
}
static uint64_t ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
{
uint64_t remaining_size;
remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
if (remaining_size < max_size) {
migration_bitmap_sync();
remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
}
return remaining_size;
}
static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
{
int ret, rc = 0;
@ -684,7 +757,7 @@ static inline void *host_from_stream_offset(QEMUFile *f,
qemu_get_buffer(f, (uint8_t *)id, len);
id[len] = 0;
QLIST_FOREACH(block, &ram_list.blocks, next) {
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
if (!strncmp(id, block->idstr, sizeof(id)))
return memory_region_get_ram_ptr(block->mr) + offset;
}
@ -728,7 +801,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
id[len] = 0;
length = qemu_get_be64(f);
QLIST_FOREACH(block, &ram_list.blocks, next) {
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
if (!strncmp(id, block->idstr, sizeof(id))) {
if (block->length != length) {
ret = -EINVAL;
@ -763,7 +836,8 @@ 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())) {
(!kvm_enabled() || kvm_has_sync_mmu()) &&
getpagesize() <= TARGET_PAGE_SIZE) {
qemu_madvise(host, TARGET_PAGE_SIZE, QEMU_MADV_DONTNEED);
}
#endif
@ -798,8 +872,8 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
} while (!(flags & RAM_SAVE_FLAG_EOS));
done:
DPRINTF("Completed load of VM with exit code %d seq iteration " PRIu64 "\n",
ret, seq_iter);
DPRINTF("Completed load of VM with exit code %d seq iteration "
"%" PRIu64 "\n", ret, seq_iter);
return ret;
}
@ -807,6 +881,7 @@ SaveVMHandlers savevm_ram_handlers = {
.save_live_setup = ram_save_setup,
.save_live_iterate = ram_save_iterate,
.save_live_complete = ram_save_complete,
.save_live_pending = ram_save_pending,
.load_state = ram_load,
.cancel = ram_migration_cancel,
};
@ -921,11 +996,16 @@ void select_soundhw(const char *optarg)
if (is_help_option(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));
}
else {
@ -1080,3 +1160,13 @@ 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;
}

117
async.c
View File

@ -23,16 +23,14 @@
*/
#include "qemu-common.h"
#include "qemu-aio.h"
#include "main-loop.h"
/* Anchor of the list of Bottom Halves belonging to the context */
static struct QEMUBH *first_bh;
#include "block/aio.h"
#include "qemu/main-loop.h"
/***********************************************************/
/* bottom halves (can be seen as timers which expire ASAP) */
struct QEMUBH {
AioContext *ctx;
QEMUBHFunc *cb;
void *opaque;
QEMUBH *next;
@ -41,27 +39,27 @@ struct QEMUBH {
bool deleted;
};
QEMUBH *qemu_bh_new(QEMUBHFunc *cb, void *opaque)
QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
{
QEMUBH *bh;
bh = g_malloc0(sizeof(QEMUBH));
bh->ctx = ctx;
bh->cb = cb;
bh->opaque = opaque;
bh->next = first_bh;
first_bh = bh;
bh->next = ctx->first_bh;
ctx->first_bh = bh;
return bh;
}
int qemu_bh_poll(void)
int aio_bh_poll(AioContext *ctx)
{
QEMUBH *bh, **bhp, *next;
int ret;
static int nesting = 0;
nesting++;
ctx->walking_bh++;
ret = 0;
for (bh = first_bh; bh; bh = next) {
for (bh = ctx->first_bh; bh; bh = next) {
next = bh->next;
if (!bh->deleted && bh->scheduled) {
bh->scheduled = 0;
@ -72,11 +70,11 @@ int qemu_bh_poll(void)
}
}
nesting--;
ctx->walking_bh--;
/* remove deleted bhs */
if (!nesting) {
bhp = &first_bh;
if (!ctx->walking_bh) {
bhp = &ctx->first_bh;
while (*bhp) {
bh = *bhp;
if (bh->deleted) {
@ -105,8 +103,7 @@ void qemu_bh_schedule(QEMUBH *bh)
return;
bh->scheduled = 1;
bh->idle = 0;
/* stop the currently executing CPU to execute the BH ASAP */
qemu_notify_event();
aio_notify(bh->ctx);
}
void qemu_bh_cancel(QEMUBH *bh)
@ -120,23 +117,101 @@ void qemu_bh_delete(QEMUBH *bh)
bh->deleted = 1;
}
void qemu_bh_update_timeout(uint32_t *timeout)
static gboolean
aio_ctx_prepare(GSource *source, gint *timeout)
{
AioContext *ctx = (AioContext *) source;
QEMUBH *bh;
for (bh = first_bh; bh; bh = bh->next) {
for (bh = ctx->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 = MIN(10, *timeout);
*timeout = 10;
} else {
/* non-idle bottom halves will be executed
* immediately */
*timeout = 0;
break;
return true;
}
}
}
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);
}

3
audio/Makefile.objs
View File

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

2
audio/alsaaudio.c
View File

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

6
audio/audio.c
View File

@ -23,9 +23,9 @@
*/
#include "hw/hw.h"
#include "audio.h"
#include "monitor.h"
#include "qemu-timer.h"
#include "sysemu.h"
#include "monitor/monitor.h"
#include "qemu/timer.h"
#include "sysemu/sysemu.h"
#define AUDIO_CAP "audio"
#include "audio_int.h"

2
audio/audio.h
View File

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

6
audio/audio_template.h
View File

@ -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;

2
audio/noaudio.c
View File

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

4
audio/ossaudio.c
View File

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

2
audio/spiceaudio.c
View File

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

2
audio/wavaudio.c
View File

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

2
audio/wavcapture.c
View File

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

14
audio/winwaveaudio.c
View File

@ -1,7 +1,7 @@
/* public domain */
#include "qemu-common.h"
#include "sysemu.h"
#include "sysemu/sysemu.h"
#include "audio.h"
#define AUDIO_CAP "winwave"
@ -349,21 +349,15 @@ static int winwave_ctl_out (HWVoiceOut *hw, int cmd, ...)
else {
hw->poll_mode = 0;
}
if (wave->paused) {
mr = waveOutRestart (wave->hwo);
if (mr != MMSYSERR_NOERROR) {
winwave_logerr (mr, "waveOutRestart");
}
wave->paused = 0;
}
wave->paused = 0;
}
return 0;
case VOICE_DISABLE:
if (!wave->paused) {
mr = waveOutPause (wave->hwo);
mr = waveOutReset (wave->hwo);
if (mr != MMSYSERR_NOERROR) {
winwave_logerr (mr, "waveOutPause");
winwave_logerr (mr, "waveOutReset");
}
else {
wave->paused = 1;

2
backends/Makefile.objs Normal file
View File

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

224
backends/rng-egd.c Normal file
View File

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

161
backends/rng-random.c Normal file
View File

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

93
backends/rng.c Normal file
View File

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

10
balloon.c
View File

@ -24,13 +24,13 @@
* THE SOFTWARE.
*/
#include "monitor.h"
#include "cpu-common.h"
#include "kvm.h"
#include "balloon.h"
#include "monitor/monitor.h"
#include "exec/cpu-common.h"
#include "sysemu/kvm.h"
#include "sysemu/balloon.h"
#include "trace.h"
#include "qmp-commands.h"
#include "qjson.h"
#include "qapi/qmp/qjson.h"
static QEMUBalloonEvent *balloon_event_fn;
static QEMUBalloonStatus *balloon_stat_fn;

4
bitmap.c
View File

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

2
bitops.c
View File

@ -11,7 +11,7 @@
* 2 of the License, or (at your option) any later version.
*/
#include "bitops.h"
#include "qemu/bitops.h"
#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG)

119
block-migration.c
View File

@ -14,13 +14,13 @@
*/
#include "qemu-common.h"
#include "block_int.h"
#include "block/block_int.h"
#include "hw/hw.h"
#include "qemu-queue.h"
#include "qemu-timer.h"
#include "block-migration.h"
#include "migration.h"
#include "blockdev.h"
#include "qemu/queue.h"
#include "qemu/timer.h"
#include "migration/block.h"
#include "migration/migration.h"
#include "sysemu/blockdev.h"
#include <assert.h>
#define BLOCK_SIZE (BDRV_SECTORS_PER_DIRTY_CHUNK << BDRV_SECTOR_BITS)
@ -77,9 +77,7 @@ typedef struct BlkMigState {
int64_t total_sector_sum;
int prev_progress;
int bulk_completed;
long double total_time;
long double prev_time_offset;
int reads;
} BlkMigState;
static BlkMigState block_mig_state;
@ -132,12 +130,6 @@ uint64_t blk_mig_bytes_total(void)
return sum << BDRV_SECTOR_BITS;
}
static inline long double compute_read_bwidth(void)
{
assert(block_mig_state.total_time != 0);
return (block_mig_state.reads / block_mig_state.total_time) * BLOCK_SIZE;
}
static int bmds_aio_inflight(BlkMigDevState *bmds, int64_t sector)
{
int64_t chunk = sector / (int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK;
@ -191,8 +183,6 @@ static void blk_mig_read_cb(void *opaque, int ret)
blk->ret = ret;
block_mig_state.reads++;
block_mig_state.total_time += (curr_time - block_mig_state.prev_time_offset);
block_mig_state.prev_time_offset = curr_time;
QSIMPLEQ_INSERT_TAIL(&block_mig_state.blk_list, blk, entry);
@ -310,8 +300,6 @@ static void init_blk_migration(QEMUFile *f)
block_mig_state.total_sector_sum = 0;
block_mig_state.prev_progress = -1;
block_mig_state.bulk_completed = 0;
block_mig_state.total_time = 0;
block_mig_state.reads = 0;
bdrv_iterate(init_blk_migration_it, NULL);
}
@ -423,20 +411,23 @@ 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 0;
return ret;
}
/* 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 = 0;
int ret = 1;
QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
if (mig_save_device_dirty(f, bmds, is_async) == 0) {
ret = 1;
ret = mig_save_device_dirty(f, bmds, is_async);
if (ret <= 0) {
break;
}
}
@ -444,9 +435,10 @@ static int blk_mig_save_dirty_block(QEMUFile *f, int is_async)
return ret;
}
static void flush_blks(QEMUFile* f)
static int 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,
@ -457,7 +449,7 @@ static void flush_blks(QEMUFile* f)
break;
}
if (blk->ret < 0) {
qemu_file_set_error(f, blk->ret);
ret = blk->ret;
break;
}
blk_send(f, blk);
@ -474,6 +466,7 @@ static void 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)
@ -488,37 +481,13 @@ static int64_t get_remaining_dirty(void)
return dirty * BLOCK_SIZE;
}
static int is_stage2_completed(void)
{
int64_t remaining_dirty;
long double bwidth;
if (block_mig_state.bulk_completed == 1) {
remaining_dirty = get_remaining_dirty();
if (remaining_dirty == 0) {
return 1;
}
bwidth = compute_read_bwidth();
if ((remaining_dirty / bwidth) <=
migrate_max_downtime()) {
/* finish stage2 because we think that we can finish remaining work
below max_downtime */
return 1;
}
}
return 0;
}
static void blk_mig_cleanup(void)
{
BlkMigDevState *bmds;
BlkMigBlock *blk;
bdrv_drain_all();
set_dirty_tracking(0);
while ((bmds = QSIMPLEQ_FIRST(&block_mig_state.bmds_list)) != NULL) {
@ -553,9 +522,7 @@ static int block_save_setup(QEMUFile *f, void *opaque)
/* start track dirty blocks */
set_dirty_tracking(1);
flush_blks(f);
ret = qemu_file_get_error(f);
ret = flush_blks(f);
if (ret) {
blk_mig_cleanup();
return ret;
@ -575,9 +542,7 @@ static int block_save_iterate(QEMUFile *f, void *opaque)
DPRINTF("Enter save live iterate submitted %d transferred %d\n",
block_mig_state.submitted, block_mig_state.transferred);
flush_blks(f);
ret = qemu_file_get_error(f);
ret = flush_blks(f);
if (ret) {
blk_mig_cleanup();
return ret;
@ -596,16 +561,19 @@ static int block_save_iterate(QEMUFile *f, void *opaque)
block_mig_state.bulk_completed = 1;
}
} else {
if (blk_mig_save_dirty_block(f, 1) == 0) {
ret = blk_mig_save_dirty_block(f, 1);
if (ret != 0) {
/* no more dirty blocks */
break;
}
}
}
if (ret) {
blk_mig_cleanup();
return ret;
}
flush_blks(f);
ret = qemu_file_get_error(f);
ret = flush_blks(f);
if (ret) {
blk_mig_cleanup();
return ret;
@ -613,7 +581,7 @@ static int block_save_iterate(QEMUFile *f, void *opaque)
qemu_put_be64(f, BLK_MIG_FLAG_EOS);
return is_stage2_completed();
return 0;
}
static int block_save_complete(QEMUFile *f, void *opaque)
@ -623,9 +591,7 @@ static int block_save_complete(QEMUFile *f, void *opaque)
DPRINTF("Enter save live complete submitted %d transferred %d\n",
block_mig_state.submitted, block_mig_state.transferred);
flush_blks(f);
ret = qemu_file_get_error(f);
ret = flush_blks(f);
if (ret) {
blk_mig_cleanup();
return ret;
@ -637,18 +603,16 @@ static int block_save_complete(QEMUFile *f, void *opaque)
all async read completed */
assert(block_mig_state.submitted == 0);
while (blk_mig_save_dirty_block(f, 0) != 0) {
/* Do nothing */
}
do {
ret = blk_mig_save_dirty_block(f, 0);
} while (ret == 0);
blk_mig_cleanup();
/* report completion */
qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
ret = qemu_file_get_error(f);
if (ret) {
return ret;
}
/* report completion */
qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS);
DPRINTF("Block migration completed\n");
@ -657,6 +621,14 @@ static int block_save_complete(QEMUFile *f, void *opaque)
return 0;
}
static uint64_t block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
{
DPRINTF("Enter save live pending %ld\n", get_remaining_dirty());
return get_remaining_dirty();
}
static int block_load(QEMUFile *f, void *opaque, int version_id)
{
static int banner_printed;
@ -753,6 +725,7 @@ SaveVMHandlers savevm_block_handlers = {
.save_live_setup = block_save_setup,
.save_live_iterate = block_save_iterate,
.save_live_complete = block_save_complete,
.save_live_pending = block_save_pending,
.load_state = block_load,
.cancel = block_migration_cancel,
.is_active = block_is_active,

1249
block.c
View File

File diff suppressed because it is too large Load Diff

17
block/Makefile.objs
View File

@ -2,10 +2,21 @@ block-obj-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat
block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
block-obj-y += qed-check.o
block-obj-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
block-obj-y += stream.o
block-obj-$(CONFIG_WIN32) += raw-win32.o
block-obj-y += parallels.o blkdebug.o blkverify.o
block-obj-$(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
$(obj)/curl.o: QEMU_CFLAGS+=$(CURL_CFLAGS)

149
block/blkdebug.c
View File

@ -23,13 +23,17 @@
*/
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "qemu/config-file.h"
#include "block/block_int.h"
#include "qemu/module.h"
typedef struct BDRVBlkdebugState {
int state;
int new_state;
QLIST_HEAD(, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
QSIMPLEQ_HEAD(, BlkdebugRule) active_rules;
QLIST_HEAD(, BlkdebugSuspendedReq) suspended_reqs;
} BDRVBlkdebugState;
typedef struct BlkdebugAIOCB {
@ -38,9 +42,15 @@ typedef struct BlkdebugAIOCB {
int ret;
} BlkdebugAIOCB;
typedef struct BlkdebugSuspendedReq {
Coroutine *co;
char *tag;
QLIST_ENTRY(BlkdebugSuspendedReq) next;
} BlkdebugSuspendedReq;
static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb);
static AIOPool blkdebug_aio_pool = {
static const AIOCBInfo blkdebug_aiocb_info = {
.aiocb_size = sizeof(BlkdebugAIOCB),
.cancel = blkdebug_aio_cancel,
};
@ -48,6 +58,7 @@ static AIOPool blkdebug_aio_pool = {
enum {
ACTION_INJECT_ERROR,
ACTION_SET_STATE,
ACTION_SUSPEND,
};
typedef struct BlkdebugRule {
@ -64,6 +75,9 @@ typedef struct BlkdebugRule {
struct {
int new_state;
} set_state;
struct {
char *tag;
} suspend;
} options;
QLIST_ENTRY(BlkdebugRule) next;
QSIMPLEQ_ENTRY(BlkdebugRule) active_next;
@ -225,6 +239,11 @@ static int add_rule(QemuOpts *opts, void *opaque)
rule->options.set_state.new_state =
qemu_opt_get_number(opts, "new_state", 0);
break;
case ACTION_SUSPEND:
rule->options.suspend.tag =
g_strdup(qemu_opt_get(opts, "tag"));
break;
};
/* Add the rule */
@ -233,12 +252,32 @@ static int add_rule(QemuOpts *opts, void *opaque)
return 0;
}
static void remove_rule(BlkdebugRule *rule)
{
switch (rule->action) {
case ACTION_INJECT_ERROR:
case ACTION_SET_STATE:
break;
case ACTION_SUSPEND:
g_free(rule->options.suspend.tag);
break;
}
QLIST_REMOVE(rule, next);
g_free(rule);
}
static int read_config(BDRVBlkdebugState *s, const char *filename)
{
FILE *f;
int ret;
struct add_rule_data d;
/* Allow usage without config file */
if (!*filename) {
return 0;
}
f = fopen(filename, "r");
if (f == NULL) {
return -errno;
@ -334,7 +373,7 @@ static BlockDriverAIOCB *inject_error(BlockDriverState *bs,
return NULL;
}
acb = qemu_aio_get(&blkdebug_aio_pool, bs, cb, opaque);
acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque);
acb->ret = -error;
bh = qemu_bh_new(error_callback_bh, acb);
@ -388,6 +427,7 @@ static BlockDriverAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
}
static void blkdebug_close(BlockDriverState *bs)
{
BDRVBlkdebugState *s = bs->opaque;
@ -396,19 +436,39 @@ static void blkdebug_close(BlockDriverState *bs)
for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
QLIST_REMOVE(rule, next);
g_free(rule);
remove_rule(rule);
}
}
}
static void suspend_request(BlockDriverState *bs, BlkdebugRule *rule)
{
BDRVBlkdebugState *s = bs->opaque;
BlkdebugSuspendedReq r;
r = (BlkdebugSuspendedReq) {
.co = qemu_coroutine_self(),
.tag = g_strdup(rule->options.suspend.tag),
};
remove_rule(rule);
QLIST_INSERT_HEAD(&s->suspended_reqs, &r, next);
printf("blkdebug: Suspended request '%s'\n", r.tag);
qemu_coroutine_yield();
printf("blkdebug: Resuming request '%s'\n", r.tag);
QLIST_REMOVE(&r, next);
g_free(r.tag);
}
static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
int old_state, bool injected)
bool injected)
{
BDRVBlkdebugState *s = bs->opaque;
/* Only process rules for the current state */
if (rule->state && rule->state != old_state) {
if (rule->state && rule->state != s->state) {
return injected;
}
@ -423,7 +483,11 @@ static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
break;
case ACTION_SET_STATE:
s->state = rule->options.set_state.new_state;
s->new_state = rule->options.set_state.new_state;
break;
case ACTION_SUSPEND:
suspend_request(bs, rule);
break;
}
return injected;
@ -432,16 +496,70 @@ static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
static void blkdebug_debug_event(BlockDriverState *bs, BlkDebugEvent event)
{
BDRVBlkdebugState *s = bs->opaque;
struct BlkdebugRule *rule;
int old_state = s->state;
struct BlkdebugRule *rule, *next;
bool injected;
assert((int)event >= 0 && event < BLKDBG_EVENT_MAX);
injected = false;
QLIST_FOREACH(rule, &s->rules[event], next) {
injected = process_rule(bs, rule, old_state, injected);
s->new_state = s->state;
QLIST_FOREACH_SAFE(rule, &s->rules[event], next, next) {
injected = process_rule(bs, rule, injected);
}
s->state = s->new_state;
}
static int blkdebug_debug_breakpoint(BlockDriverState *bs, const char *event,
const char *tag)
{
BDRVBlkdebugState *s = bs->opaque;
struct BlkdebugRule *rule;
BlkDebugEvent blkdebug_event;
if (get_event_by_name(event, &blkdebug_event) < 0) {
return -ENOENT;
}
rule = g_malloc(sizeof(*rule));
*rule = (struct BlkdebugRule) {
.event = blkdebug_event,
.action = ACTION_SUSPEND,
.state = 0,
.options.suspend.tag = g_strdup(tag),
};
QLIST_INSERT_HEAD(&s->rules[blkdebug_event], rule, next);
return 0;
}
static int blkdebug_debug_resume(BlockDriverState *bs, const char *tag)
{
BDRVBlkdebugState *s = bs->opaque;
BlkdebugSuspendedReq *r;
QLIST_FOREACH(r, &s->suspended_reqs, next) {
if (!strcmp(r->tag, tag)) {
qemu_coroutine_enter(r->co, NULL);
return 0;
}
}
return -ENOENT;
}
static bool blkdebug_debug_is_suspended(BlockDriverState *bs, const char *tag)
{
BDRVBlkdebugState *s = bs->opaque;
BlkdebugSuspendedReq *r;
QLIST_FOREACH(r, &s->suspended_reqs, next) {
if (!strcmp(r->tag, tag)) {
return true;
}
}
return false;
}
static int64_t blkdebug_getlength(BlockDriverState *bs)
@ -462,7 +580,10 @@ static BlockDriver bdrv_blkdebug = {
.bdrv_aio_readv = blkdebug_aio_readv,
.bdrv_aio_writev = blkdebug_aio_writev,
.bdrv_debug_event = blkdebug_debug_event,
.bdrv_debug_event = blkdebug_debug_event,
.bdrv_debug_breakpoint = blkdebug_debug_breakpoint,
.bdrv_debug_resume = blkdebug_debug_resume,
.bdrv_debug_is_suspended = blkdebug_debug_is_suspended,
};
static void bdrv_blkdebug_init(void)

8
block/blkverify.c
View File

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

4
block/bochs.c
View File

@ -23,8 +23,8 @@
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "block/block_int.h"
#include "qemu/module.h"
/**************************************************************/

4
block/cloop.c
View File

@ -22,8 +22,8 @@
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include <zlib.h>
typedef struct BDRVCloopState {

259
block/commit.c Normal file
View File

@ -0,0 +1,259 @@
/*
* Live block commit
*
* Copyright Red Hat, Inc. 2012
*
* Authors:
* Jeff Cody <jcody@redhat.com>
* Based on stream.c by Stefan Hajnoczi
*
* This work is licensed under the terms of the GNU LGPL, version 2 or later.
* See the COPYING.LIB file in the top-level directory.
*
*/
#include "trace.h"
#include "block/block_int.h"
#include "block/blockjob.h"
#include "qemu/ratelimit.h"
enum {
/*
* Size of data buffer for populating the image file. This should be large
* enough to process multiple clusters in a single call, so that populating
* contiguous regions of the image is efficient.
*/
COMMIT_BUFFER_SIZE = 512 * 1024, /* in bytes */
};
#define SLICE_TIME 100000000ULL /* ns */
typedef struct CommitBlockJob {
BlockJob common;
RateLimit limit;
BlockDriverState *active;
BlockDriverState *top;
BlockDriverState *base;
BlockdevOnError on_error;
int base_flags;
int orig_overlay_flags;
} CommitBlockJob;
static int coroutine_fn commit_populate(BlockDriverState *bs,
BlockDriverState *base,
int64_t sector_num, int nb_sectors,
void *buf)
{
int ret = 0;
ret = bdrv_read(bs, sector_num, buf, nb_sectors);
if (ret) {
return ret;
}
ret = bdrv_write(base, sector_num, buf, nb_sectors);
if (ret) {
return ret;
}
return 0;
}
static void coroutine_fn commit_run(void *opaque)
{
CommitBlockJob *s = opaque;
BlockDriverState *active = s->active;
BlockDriverState *top = s->top;
BlockDriverState *base = s->base;
BlockDriverState *overlay_bs = 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 bdrv_drain_all() returns.
*/
block_job_sleep_ns(&s->common, rt_clock, delay_ns);
if (block_job_is_cancelled(&s->common)) {
break;
}
/* Copy if allocated above the base */
ret = bdrv_co_is_allocated_above(top, base, sector_num,
COMMIT_BUFFER_SIZE / BDRV_SECTOR_SIZE,
&n);
copy = (ret == 1);
trace_commit_one_iteration(s, sector_num, n, ret);
if (copy) {
if (s->common.speed) {
delay_ns = ratelimit_calculate_delay(&s->limit, n);
if (delay_ns > 0) {
goto wait;
}
}
ret = commit_populate(top, base, sector_num, n, buf);
bytes_written += n * BDRV_SECTOR_SIZE;
}
if (ret < 0) {
if (s->on_error == BLOCKDEV_ON_ERROR_STOP ||
s->on_error == BLOCKDEV_ON_ERROR_REPORT||
(s->on_error == BLOCKDEV_ON_ERROR_ENOSPC && ret == -ENOSPC)) {
goto exit_free_buf;
} else {
n = 0;
continue;
}
}
/* Publish progress */
s->common.offset += n * BDRV_SECTOR_SIZE;
}
ret = 0;
if (!block_job_is_cancelled(&s->common) && sector_num == end) {
/* success */
ret = bdrv_drop_intermediate(active, top, base);
}
exit_free_buf:
qemu_vfree(buf);
exit_restore_reopen:
/* restore base open flags here if appropriate (e.g., change the base back
* to r/o). These reopens do not need to be atomic, since we won't abort
* even on failure here */
if (s->base_flags != bdrv_get_flags(base)) {
bdrv_reopen(base, s->base_flags, NULL);
}
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);
}

4
block/cow.c
View File

@ -22,8 +22,8 @@
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "block/block_int.h"
#include "qemu/module.h"
/**************************************************************/
/* COW block driver using file system holes */

9
block/curl.c
View File

@ -22,7 +22,7 @@
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "block_int.h"
#include "block/block_int.h"
#include <curl/curl.h>
// #define DEBUG
@ -438,7 +438,7 @@ static void curl_aio_cancel(BlockDriverAIOCB *blockacb)
// Do we have to implement canceling? Seems to work without...
}
static AIOPool curl_aio_pool = {
static const AIOCBInfo curl_aiocb_info = {
.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_aio_pool, bs, cb, opaque);
acb = qemu_aio_get(&curl_aiocb_info, bs, cb, opaque);
acb->qiov = qiov;
acb->sector_num = sector_num;
@ -542,8 +542,7 @@ static void curl_close(BlockDriverState *bs)
}
if (s->multi)
curl_multi_cleanup(s->multi);
if (s->url)
free(s->url);
g_free(s->url);
}
static int64_t curl_getlength(BlockDriverState *bs)

6
block/dmg.c
View File

@ -22,9 +22,9 @@
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "block_int.h"
#include "bswap.h"
#include "module.h"
#include "block/block_int.h"
#include "qemu/bswap.h"
#include "qemu/module.h"
#include <zlib.h>
typedef struct BDRVDMGState {

624
block/gluster.c Normal file
View File

@ -0,0 +1,624 @@
/*
* GlusterFS backend for QEMU
*
* Copyright (C) 2012 Bharata B Rao <bharata@linux.vnet.ibm.com>
*
* Pipe handling mechanism in AIO implementation is derived from
* block/rbd.c. Hence,
*
* Copyright (C) 2010-2011 Christian Brunner <chb@muc.de>,
* Josh Durgin <josh.durgin@dreamhost.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Contributions after 2012-01-13 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
*/
#include <glusterfs/api/glfs.h>
#include "block/block_int.h"
#include "qemu/sockets.h"
#include "qemu/uri.h"
typedef struct GlusterAIOCB {
BlockDriverAIOCB common;
int64_t size;
int ret;
bool *finished;
QEMUBH *bh;
} GlusterAIOCB;
typedef struct BDRVGlusterState {
struct glfs *glfs;
int fds[2];
struct glfs_fd *fd;
int qemu_aio_count;
int event_reader_pos;
GlusterAIOCB *event_acb;
} BDRVGlusterState;
#define GLUSTER_FD_READ 0
#define GLUSTER_FD_WRITE 1
typedef struct GlusterConf {
char *server;
int port;
char *volname;
char *image;
char *transport;
} GlusterConf;
static void qemu_gluster_gconf_free(GlusterConf *gconf)
{
g_free(gconf->server);
g_free(gconf->volname);
g_free(gconf->image);
g_free(gconf->transport);
g_free(gconf);
}
static int parse_volume_options(GlusterConf *gconf, char *path)
{
char *p, *q;
if (!path) {
return -EINVAL;
}
/* volume */
p = q = path + strspn(path, "/");
p += strcspn(p, "/");
if (*p == '\0') {
return -EINVAL;
}
gconf->volname = g_strndup(q, p - q);
/* image */
p += strspn(p, "/");
if (*p == '\0') {
return -EINVAL;
}
gconf->image = g_strdup(p);
return 0;
}
/*
* file=gluster[+transport]://[server[:port]]/volname/image[?socket=...]
*
* 'gluster' is the protocol.
*
* 'transport' specifies the transport type used to connect to gluster
* management daemon (glusterd). Valid transport types are
* tcp, unix and rdma. If a transport type isn't specified, then tcp
* type is assumed.
*
* 'server' specifies the server where the volume file specification for
* the given volume resides. This can be either hostname, ipv4 address
* or ipv6 address. ipv6 address needs to be within square brackets [ ].
* If transport type is 'unix', then 'server' field should not be specifed.
* The 'socket' field needs to be populated with the path to unix domain
* socket.
*
* 'port' is the port number on which glusterd is listening. This is optional
* and if not specified, QEMU will send 0 which will make gluster to use the
* default port. If the transport type is unix, then 'port' should not be
* specified.
*
* 'volname' is the name of the gluster volume which contains the VM image.
*
* 'image' is the path to the actual VM image that resides on gluster volume.
*
* Examples:
*
* file=gluster://1.2.3.4/testvol/a.img
* file=gluster+tcp://1.2.3.4/testvol/a.img
* file=gluster+tcp://1.2.3.4:24007/testvol/dir/a.img
* file=gluster+tcp://[1:2:3:4:5:6:7:8]/testvol/dir/a.img
* file=gluster+tcp://[1:2:3:4:5:6:7:8]:24007/testvol/dir/a.img
* file=gluster+tcp://server.domain.com:24007/testvol/dir/a.img
* file=gluster+unix:///testvol/dir/a.img?socket=/tmp/glusterd.socket
* file=gluster+rdma://1.2.3.4:24007/testvol/a.img
*/
static int qemu_gluster_parseuri(GlusterConf *gconf, const char *filename)
{
URI *uri;
QueryParams *qp = NULL;
bool is_unix = false;
int ret = 0;
uri = uri_parse(filename);
if (!uri) {
return -EINVAL;
}
/* transport */
if (!strcmp(uri->scheme, "gluster")) {
gconf->transport = g_strdup("tcp");
} else if (!strcmp(uri->scheme, "gluster+tcp")) {
gconf->transport = g_strdup("tcp");
} else if (!strcmp(uri->scheme, "gluster+unix")) {
gconf->transport = g_strdup("unix");
is_unix = true;
} else if (!strcmp(uri->scheme, "gluster+rdma")) {
gconf->transport = g_strdup("rdma");
} else {
ret = -EINVAL;
goto out;
}
ret = parse_volume_options(gconf, uri->path);
if (ret < 0) {
goto out;
}
qp = query_params_parse(uri->query);
if (qp->n > 1 || (is_unix && !qp->n) || (!is_unix && qp->n)) {
ret = -EINVAL;
goto out;
}
if (is_unix) {
if (uri->server || uri->port) {
ret = -EINVAL;
goto out;
}
if (strcmp(qp->p[0].name, "socket")) {
ret = -EINVAL;
goto out;
}
gconf->server = g_strdup(qp->p[0].value);
} else {
gconf->server = g_strdup(uri->server);
gconf->port = uri->port;
}
out:
if (qp) {
query_params_free(qp);
}
uri_free(uri);
return ret;
}
static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename)
{
struct glfs *glfs = NULL;
int ret;
int old_errno;
ret = qemu_gluster_parseuri(gconf, filename);
if (ret < 0) {
error_report("Usage: file=gluster[+transport]://[server[:port]]/"
"volname/image[?socket=...]");
errno = -ret;
goto out;
}
glfs = glfs_new(gconf->volname);
if (!glfs) {
goto out;
}
ret = glfs_set_volfile_server(glfs, gconf->transport, gconf->server,
gconf->port);
if (ret < 0) {
goto out;
}
/*
* TODO: Use GF_LOG_ERROR instead of hard code value of 4 here when
* GlusterFS makes GF_LOG_* macros available to libgfapi users.
*/
ret = glfs_set_logging(glfs, "-", 4);
if (ret < 0) {
goto out;
}
ret = glfs_init(glfs);
if (ret) {
error_report("Gluster connection failed for server=%s port=%d "
"volume=%s image=%s transport=%s\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);

419
block/iscsi.c
View File

@ -27,8 +27,9 @@
#include <poll.h>
#include <arpa/inet.h>
#include "qemu-common.h"
#include "qemu-error.h"
#include "block_int.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "block/block_int.h"
#include "trace.h"
#include "hw/scsi-defs.h"
@ -65,21 +66,44 @@ typedef struct IscsiAIOCB {
#endif
} IscsiAIOCB;
struct IscsiTask {
IscsiLun *iscsilun;
BlockDriverState *bs;
int status;
int complete;
};
static void
iscsi_bh_cb(void *p)
{
IscsiAIOCB *acb = p;
qemu_bh_delete(acb->bh);
if (acb->canceled == 0) {
acb->common.cb(acb->common.opaque, acb->status);
}
if (acb->task != NULL) {
scsi_free_scsi_task(acb->task);
acb->task = NULL;
}
qemu_aio_release(acb);
}
static void
iscsi_schedule_bh(IscsiAIOCB *acb)
{
if (acb->bh) {
return;
}
acb->bh = qemu_bh_new(iscsi_bh_cb, acb);
qemu_bh_schedule(acb->bh);
}
static void
iscsi_abort_task_cb(struct iscsi_context *iscsi, int status, void *command_data,
void *private_data)
{
IscsiAIOCB *acb = (IscsiAIOCB *)private_data;
IscsiAIOCB *acb = private_data;
scsi_free_scsi_task(acb->task);
acb->task = NULL;
acb->status = -ECANCELED;
iscsi_schedule_bh(acb);
}
static void
@ -88,18 +112,22 @@ iscsi_aio_cancel(BlockDriverAIOCB *blockacb)
IscsiAIOCB *acb = (IscsiAIOCB *)blockacb;
IscsiLun *iscsilun = acb->iscsilun;
if (acb->status != -EINPROGRESS) {
return;
}
acb->canceled = 1;
acb->common.cb(acb->common.opaque, -ECANCELED);
/* send a task mgmt call to the target to cancel the task on the target
* this also cancels the task in libiscsi
*/
/* send a task mgmt call to the target to cancel the task on the target */
iscsi_task_mgmt_abort_task_async(iscsilun->iscsi, acb->task,
iscsi_abort_task_cb, &acb);
iscsi_abort_task_cb, acb);
while (acb->status == -EINPROGRESS) {
qemu_aio_wait();
}
}
static AIOPool iscsi_aio_pool = {
static const AIOCBInfo iscsi_aiocb_info = {
.aiocb_size = sizeof(IscsiAIOCB),
.cancel = iscsi_aio_cancel,
};
@ -133,12 +161,6 @@ 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;
}
@ -163,41 +185,6 @@ iscsi_process_write(void *arg)
}
static int
iscsi_schedule_bh(QEMUBHFunc *cb, IscsiAIOCB *acb)
{
acb->bh = qemu_bh_new(cb, acb);
if (!acb->bh) {
error_report("oom: could not create iscsi bh");
return -EIO;
}
qemu_bh_schedule(acb->bh);
return 0;
}
static void
iscsi_readv_writev_bh_cb(void *p)
{
IscsiAIOCB *acb = p;
qemu_bh_delete(acb->bh);
if (!acb->canceled) {
acb->common.cb(acb->common.opaque, acb->status);
}
qemu_aio_release(acb);
if (acb->canceled) {
return;
}
scsi_free_scsi_task(acb->task);
acb->task = NULL;
}
static void
iscsi_aio_write16_cb(struct iscsi_context *iscsi, int status,
void *command_data, void *opaque)
@ -208,8 +195,7 @@ iscsi_aio_write16_cb(struct iscsi_context *iscsi, int status,
g_free(acb->buf);
if (acb->canceled) {
qemu_aio_release(acb);
if (acb->canceled != 0) {
return;
}
@ -220,7 +206,7 @@ iscsi_aio_write16_cb(struct iscsi_context *iscsi, int status,
acb->status = -EIO;
}
iscsi_schedule_bh(iscsi_readv_writev_bh_cb, acb);
iscsi_schedule_bh(acb);
}
static int64_t sector_qemu2lun(int64_t sector, IscsiLun *iscsilun)
@ -242,13 +228,15 @@ iscsi_aio_writev(BlockDriverState *bs, int64_t sector_num,
uint64_t lba;
struct iscsi_data data;
acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
trace_iscsi_aio_writev(iscsi, sector_num, nb_sectors, opaque, acb);
acb->iscsilun = iscsilun;
acb->qiov = qiov;
acb->canceled = 0;
acb->bh = NULL;
acb->status = -EINPROGRESS;
/* XXX we should pass the iovec to write16 to avoid the extra copy */
/* this will allow us to get rid of 'buf' completely */
@ -268,10 +256,6 @@ 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);
@ -305,8 +289,7 @@ iscsi_aio_read16_cb(struct iscsi_context *iscsi, int status,
trace_iscsi_aio_read16_cb(iscsi, status, acb, acb->canceled);
if (acb->canceled) {
qemu_aio_release(acb);
if (acb->canceled != 0) {
return;
}
@ -317,7 +300,7 @@ iscsi_aio_read16_cb(struct iscsi_context *iscsi, int status,
acb->status = -EIO;
}
iscsi_schedule_bh(iscsi_readv_writev_bh_cb, acb);
iscsi_schedule_bh(acb);
}
static BlockDriverAIOCB *
@ -336,13 +319,15 @@ iscsi_aio_readv(BlockDriverState *bs, int64_t sector_num,
qemu_read_size = BDRV_SECTOR_SIZE * (size_t)nb_sectors;
acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
trace_iscsi_aio_readv(iscsi, sector_num, nb_sectors, opaque, acb);
acb->iscsilun = iscsilun;
acb->qiov = qiov;
acb->canceled = 0;
acb->bh = NULL;
acb->status = -EINPROGRESS;
acb->read_size = qemu_read_size;
acb->buf = NULL;
@ -389,7 +374,7 @@ 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,
@ -417,8 +402,7 @@ iscsi_synccache10_cb(struct iscsi_context *iscsi, int status,
{
IscsiAIOCB *acb = opaque;
if (acb->canceled) {
qemu_aio_release(acb);
if (acb->canceled != 0) {
return;
}
@ -429,7 +413,7 @@ iscsi_synccache10_cb(struct iscsi_context *iscsi, int status,
acb->status = -EIO;
}
iscsi_schedule_bh(iscsi_readv_writev_bh_cb, acb);
iscsi_schedule_bh(acb);
}
static BlockDriverAIOCB *
@ -440,10 +424,12 @@ iscsi_aio_flush(BlockDriverState *bs,
struct iscsi_context *iscsi = iscsilun->iscsi;
IscsiAIOCB *acb;
acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
acb->iscsilun = iscsilun;
acb->canceled = 0;
acb->bh = NULL;
acb->status = -EINPROGRESS;
acb->task = iscsi_synchronizecache10_task(iscsi, iscsilun->lun,
0, 0, 0, 0,
@ -467,8 +453,7 @@ iscsi_unmap_cb(struct iscsi_context *iscsi, int status,
{
IscsiAIOCB *acb = opaque;
if (acb->canceled) {
qemu_aio_release(acb);
if (acb->canceled != 0) {
return;
}
@ -479,7 +464,7 @@ iscsi_unmap_cb(struct iscsi_context *iscsi, int status,
acb->status = -EIO;
}
iscsi_schedule_bh(iscsi_readv_writev_bh_cb, acb);
iscsi_schedule_bh(acb);
}
static BlockDriverAIOCB *
@ -492,10 +477,12 @@ iscsi_aio_discard(BlockDriverState *bs,
IscsiAIOCB *acb;
struct unmap_list list[1];
acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
acb->iscsilun = iscsilun;
acb->canceled = 0;
acb->bh = NULL;
acb->status = -EINPROGRESS;
list[0].lba = sector_qemu2lun(sector_num, iscsilun);
list[0].num = nb_sectors * BDRV_SECTOR_SIZE / iscsilun->block_size;
@ -523,8 +510,7 @@ iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
{
IscsiAIOCB *acb = opaque;
if (acb->canceled) {
qemu_aio_release(acb);
if (acb->canceled != 0) {
return;
}
@ -552,7 +538,7 @@ iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
memcpy(acb->ioh->sbp, &acb->task->datain.data[2], ss);
}
iscsi_schedule_bh(iscsi_readv_writev_bh_cb, acb);
iscsi_schedule_bh(acb);
}
static BlockDriverAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
@ -566,10 +552,12 @@ static BlockDriverAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
assert(req == SG_IO);
acb = qemu_aio_get(&iscsi_aio_pool, bs, cb, opaque);
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;
@ -624,9 +612,17 @@ static BlockDriverAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
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:
@ -635,6 +631,15 @@ static int iscsi_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
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;
}
@ -654,158 +659,6 @@ 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;
@ -918,7 +771,10 @@ static int iscsi_open(BlockDriverState *bs, const char *filename, int flags)
IscsiLun *iscsilun = bs->opaque;
struct iscsi_context *iscsi = NULL;
struct iscsi_url *iscsi_url = NULL;
struct IscsiTask task;
struct scsi_task *task = NULL;
struct scsi_inquiry_standard *inq = NULL;
struct scsi_readcapacity10 *rc10 = NULL;
struct scsi_readcapacity16 *rc16 = NULL;
char *initiator_name = NULL;
int ret;
@ -931,8 +787,7 @@ 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 %s", filename,
iscsi_get_error(iscsi));
error_report("Failed to parse URL : %s", filename);
ret = -EINVAL;
goto out;
}
@ -982,33 +837,80 @@ 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);
task.iscsilun = iscsilun;
task.status = 0;
task.complete = 0;
task.bs = bs;
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;
}
iscsilun->iscsi = iscsi;
iscsilun->lun = iscsi_url->lun;
if (iscsi_full_connect_async(iscsi, iscsi_url->portal, iscsi_url->lun,
iscsi_connect_cb, &task)
!= 0) {
error_report("iSCSI: Failed to start async connect.");
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.");
ret = -EINVAL;
goto out;
}
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));
inq = scsi_datain_unmarshall(task);
if (inq == NULL) {
error_report("iSCSI: Failed to unmarshall inquiry data.");
ret = -EINVAL;
goto out;
}
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;
}
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.
@ -1027,6 +929,9 @@ out:
if (iscsi_url != NULL) {
iscsi_destroy_url(iscsi_url);
}
if (task != NULL) {
scsi_free_scsi_task(task);
}
if (ret) {
if (iscsi != NULL) {
@ -1047,6 +952,11 @@ 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",
@ -1062,6 +972,7 @@ 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,

58
linux-aio.c → block/linux-aio.c
View File

@ -8,10 +8,11 @@
* See the COPYING file in the top-level directory.
*/
#include "qemu-common.h"
#include "qemu-aio.h"
#include "block/raw-posix-aio.h"
#include "block/aio.h"
#include "qemu/queue.h"
#include "block/raw-aio.h"
#include "qemu/event_notifier.h"
#include <sys/eventfd.h>
#include <libaio.h>
/*
@ -37,7 +38,7 @@ struct qemu_laiocb {
struct qemu_laio_state {
io_context_t ctx;
int efd;
EventNotifier e;
int count;
};
@ -76,29 +77,17 @@ static void qemu_laio_process_completion(struct qemu_laio_state *s,
qemu_aio_release(laiocb);
}
static void qemu_laio_completion_cb(void *opaque)
static void qemu_laio_completion_cb(EventNotifier *e)
{
struct qemu_laio_state *s = opaque;
struct qemu_laio_state *s = container_of(e, struct qemu_laio_state, e);
while (1) {
while (event_notifier_test_and_clear(&s->e)) {
struct io_event events[MAX_EVENTS];
uint64_t val;
ssize_t ret;
struct timespec ts = { 0 };
int nevents, i;
do {
ret = read(s->efd, &val, sizeof(val));
} while (ret == -1 && errno == EINTR);
if (ret == -1 && errno == EAGAIN)
break;
if (ret != 8)
break;
do {
nevents = io_getevents(s->ctx, val, MAX_EVENTS, events, &ts);
nevents = io_getevents(s->ctx, MAX_EVENTS, MAX_EVENTS, events, &ts);
} while (nevents == -EINTR);
for (i = 0; i < nevents; i++) {
@ -112,9 +101,9 @@ static void qemu_laio_completion_cb(void *opaque)
}
}
static int qemu_laio_flush_cb(void *opaque)
static int qemu_laio_flush_cb(EventNotifier *e)
{
struct qemu_laio_state *s = opaque;
struct qemu_laio_state *s = container_of(e, struct qemu_laio_state, e);
return (s->count > 0) ? 1 : 0;
}
@ -146,11 +135,12 @@ static void laio_cancel(BlockDriverAIOCB *blockacb)
* We might be able to do this slightly more optimal by removing the
* O_NONBLOCK flag.
*/
while (laiocb->ret == -EINPROGRESS)
qemu_laio_completion_cb(laiocb->ctx);
while (laiocb->ret == -EINPROGRESS) {
qemu_laio_completion_cb(&laiocb->ctx->e);
}
}
static AIOPool laio_pool = {
static const AIOCBInfo laio_aiocb_info = {
.aiocb_size = sizeof(struct qemu_laiocb),
.cancel = laio_cancel,
};
@ -164,7 +154,7 @@ BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
struct iocb *iocbs;
off_t offset = sector_num * 512;
laiocb = qemu_aio_get(&laio_pool, bs, cb, opaque);
laiocb = qemu_aio_get(&laio_aiocb_info, bs, cb, opaque);
laiocb->nbytes = nb_sectors * 512;
laiocb->ctx = s;
laiocb->ret = -EINPROGRESS;
@ -186,7 +176,7 @@ BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
__func__, type);
goto out_free_aiocb;
}
io_set_eventfd(&laiocb->iocb, s->efd);
io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));
s->count++;
if (io_submit(s->ctx, 1, &iocbs) < 0)
@ -205,21 +195,21 @@ void *laio_init(void)
struct qemu_laio_state *s;
s = g_malloc0(sizeof(*s));
s->efd = eventfd(0, 0);
if (s->efd == -1)
if (event_notifier_init(&s->e, false) < 0) {
goto out_free_state;
fcntl(s->efd, F_SETFL, O_NONBLOCK);
}
if (io_setup(MAX_EVENTS, &s->ctx) != 0)
if (io_setup(MAX_EVENTS, &s->ctx) != 0) {
goto out_close_efd;
}
qemu_aio_set_fd_handler(s->efd, qemu_laio_completion_cb, NULL,
qemu_laio_flush_cb, s);
qemu_aio_set_event_notifier(&s->e, qemu_laio_completion_cb,
qemu_laio_flush_cb);
return s;
out_close_efd:
close(s->efd);
event_notifier_cleanup(&s->e);
out_free_state:
g_free(s);
return NULL;

322
block/mirror.c Normal file
View File

@ -0,0 +1,322 @@
/*
* Image mirroring
*
* Copyright Red Hat, Inc. 2012
*
* Authors:
* Paolo Bonzini <pbonzini@redhat.com>
*
* This work is licensed under the terms of the GNU LGPL, version 2 or later.
* See the COPYING.LIB file in the top-level directory.
*
*/
#include "trace.h"
#include "block/blockjob.h"
#include "block/block_int.h"
#include "qemu/ratelimit.h"
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 bdrv_drain_all() 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);
}

123
block/nbd.c
View File

@ -27,10 +27,11 @@
*/
#include "qemu-common.h"
#include "nbd.h"
#include "block_int.h"
#include "module.h"
#include "qemu_socket.h"
#include "block/nbd.h"
#include "qemu/uri.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "qemu/sockets.h"
#include <sys/types.h>
#include <unistd.h>
@ -55,7 +56,6 @@ 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;
@ -65,13 +65,75 @@ typedef struct BDRVNBDState {
Coroutine *recv_coroutine[MAX_NBD_REQUESTS];
struct nbd_reply reply;
/* If it begins with '/', this is a UNIX domain socket. Otherwise,
* it's a string of the form <hostname|ip4|\[ip6\]>:port
*/
int is_unix;
char *host_spec;
char *export_name; /* An NBD server may export several devices */
} BDRVNBDState;
static int nbd_config(BDRVNBDState *s, const char *filename, int flags)
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)
{
char *file;
char *export_name;
@ -79,6 +141,10 @@ static int nbd_config(BDRVNBDState *s, const char *filename, int flags)
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);
@ -98,11 +164,10 @@ static int nbd_config(BDRVNBDState *s, const char *filename, int flags)
/* are we a UNIX or TCP socket? */
if (strstart(host_spec, "unix:", &unixpath)) {
if (unixpath[0] != '/') { /* We demand an absolute path*/
goto out;
}
s->is_unix = true;
s->host_spec = g_strdup(unixpath);
} else {
s->is_unix = false;
s->host_spec = g_strdup(host_spec);
}
@ -262,7 +327,7 @@ static int nbd_establish_connection(BlockDriverState *bs)
off_t size;
size_t blocksize;
if (s->host_spec[0] == '/') {
if (s->is_unix) {
sock = unix_socket_outgoing(s->host_spec);
} else {
sock = tcp_socket_outgoing_spec(s->host_spec);
@ -320,7 +385,7 @@ 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, flags);
result = nbd_config(s, filename);
if (result != 0) {
return result;
}
@ -498,6 +563,33 @@ static int64_t nbd_getlength(BlockDriverState *bs)
static BlockDriver bdrv_nbd = {
.format_name = "nbd",
.protocol_name = "nbd",
.instance_size = sizeof(BDRVNBDState),
.bdrv_file_open = nbd_open,
.bdrv_co_readv = nbd_co_readv,
.bdrv_co_writev = nbd_co_writev,
.bdrv_close = nbd_close,
.bdrv_co_flush_to_os = nbd_co_flush,
.bdrv_co_discard = nbd_co_discard,
.bdrv_getlength = nbd_getlength,
};
static BlockDriver bdrv_nbd_tcp = {
.format_name = "nbd",
.protocol_name = "nbd+tcp",
.instance_size = sizeof(BDRVNBDState),
.bdrv_file_open = nbd_open,
.bdrv_co_readv = nbd_co_readv,
.bdrv_co_writev = nbd_co_writev,
.bdrv_close = nbd_close,
.bdrv_co_flush_to_os = nbd_co_flush,
.bdrv_co_discard = nbd_co_discard,
.bdrv_getlength = nbd_getlength,
};
static BlockDriver bdrv_nbd_unix = {
.format_name = "nbd",
.protocol_name = "nbd+unix",
.instance_size = sizeof(BDRVNBDState),
.bdrv_file_open = nbd_open,
.bdrv_co_readv = nbd_co_readv,
@ -506,12 +598,13 @@ static BlockDriver bdrv_nbd = {
.bdrv_co_flush_to_os = nbd_co_flush,
.bdrv_co_discard = nbd_co_discard,
.bdrv_getlength = nbd_getlength,
.protocol_name = "nbd",
};
static void bdrv_nbd_init(void)
{
bdrv_register(&bdrv_nbd);
bdrv_register(&bdrv_nbd_tcp);
bdrv_register(&bdrv_nbd_unix);
}
block_init(bdrv_nbd_init);

4
block/parallels.c
View File

@ -24,8 +24,8 @@
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "block/block_int.h"
#include "qemu/module.h"
/**************************************************************/

18
block/qcow.c
View File

@ -22,11 +22,11 @@
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include <zlib.h>
#include "aes.h"
#include "migration.h"
#include "block/aes.h"
#include "migration/migration.h"
/**************************************************************/
/* QEMU COW block driver with compression and encryption support */
@ -197,6 +197,15 @@ 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;
@ -868,6 +877,7 @@ 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,

2
block/qcow2-cache.c
View File

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

193
block/qcow2-cluster.c
View File

@ -25,7 +25,7 @@
#include <zlib.h>
#include "qemu-common.h"
#include "block_int.h"
#include "block/block_int.h"
#include "block/qcow2.h"
#include "trace.h"
@ -615,57 +615,67 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
return cluster_offset;
}
int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
static int perform_cow(BlockDriverState *bs, QCowL2Meta *m, Qcow2COWRegion *r)
{
BDRVQcowState *s = bs->opaque;
int i, j = 0, l2_index, ret;
uint64_t *old_cluster, start_sect, *l2_table;
uint64_t cluster_offset = m->alloc_offset;
bool cow = false;
int ret;
trace_qcow2_cluster_link_l2(qemu_coroutine_self(), m->nb_clusters);
if (m->nb_clusters == 0)
if (r->nb_sectors == 0) {
return 0;
old_cluster = g_malloc(m->nb_clusters * sizeof(uint64_t));
/* copy content of unmodified sectors */
start_sect = (m->offset & ~(s->cluster_size - 1)) >> 9;
if (m->n_start) {
cow = true;
qemu_co_mutex_unlock(&s->lock);
ret = copy_sectors(bs, start_sect, cluster_offset, 0, m->n_start);
qemu_co_mutex_lock(&s->lock);
if (ret < 0)
goto err;
}
if (m->nb_available & (s->cluster_sectors - 1)) {
cow = true;
qemu_co_mutex_unlock(&s->lock);
ret = copy_sectors(bs, start_sect, cluster_offset, m->nb_available,
align_offset(m->nb_available, s->cluster_sectors));
qemu_co_mutex_lock(&s->lock);
if (ret < 0)
goto err;
qemu_co_mutex_unlock(&s->lock);
ret = copy_sectors(bs, m->offset / BDRV_SECTOR_SIZE, m->alloc_offset,
r->offset / BDRV_SECTOR_SIZE,
r->offset / BDRV_SECTOR_SIZE + r->nb_sectors);
qemu_co_mutex_lock(&s->lock);
if (ret < 0) {
return ret;
}
/*
* Update L2 table.
*
* Before we update the L2 table to actually point to the new cluster, we
* need to be sure that the refcounts have been increased and COW was
* handled.
*/
if (cow) {
qcow2_cache_depends_on_flush(s->l2_table_cache);
qcow2_cache_depends_on_flush(s->l2_table_cache);
return 0;
}
int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
{
BDRVQcowState *s = bs->opaque;
int i, j = 0, l2_index, ret;
uint64_t *old_cluster, *l2_table;
uint64_t cluster_offset = m->alloc_offset;
trace_qcow2_cluster_link_l2(qemu_coroutine_self(), m->nb_clusters);
assert(m->nb_clusters > 0);
old_cluster = g_malloc(m->nb_clusters * sizeof(uint64_t));
/* copy content of unmodified sectors */
ret = perform_cow(bs, m, &m->cow_start);
if (ret < 0) {
goto err;
}
ret = perform_cow(bs, m, &m->cow_end);
if (ret < 0) {
goto err;
}
/* Update L2 table. */
if (s->compatible_features & QCOW2_COMPAT_LAZY_REFCOUNTS) {
qcow2_mark_dirty(bs);
}
if (qcow2_need_accurate_refcounts(s)) {
qcow2_cache_set_dependency(bs, s->l2_table_cache,
s->refcount_block_cache);
}
ret = get_cluster_table(bs, m->offset, &l2_table, &l2_index);
if (ret < 0) {
goto err;
@ -743,38 +753,16 @@ out:
}
/*
* Allocates new clusters for the given guest_offset.
*
* At most *nb_clusters are allocated, and on return *nb_clusters is updated to
* contain the number of clusters that have been allocated and are contiguous
* in the image file.
*
* If *host_offset is non-zero, it specifies the offset in the image file at
* which the new clusters must start. *nb_clusters can be 0 on return in this
* case if the cluster at host_offset is already in use. If *host_offset is
* zero, the clusters can be allocated anywhere in the image file.
*
* *host_offset is updated to contain the offset into the image file at which
* the first allocated cluster starts.
*
* Return 0 on success and -errno in error cases. -EAGAIN means that the
* function has been waiting for another request and the allocation must be
* restarted, but the whole request should not be failed.
* Check if there already is an AIO write request in flight which allocates
* the same cluster. In this case we need to wait until the previous
* request has completed and updated the L2 table accordingly.
*/
static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
uint64_t *host_offset, unsigned int *nb_clusters)
static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset,
unsigned int *nb_clusters)
{
BDRVQcowState *s = bs->opaque;
QCowL2Meta *old_alloc;
trace_qcow2_do_alloc_clusters_offset(qemu_coroutine_self(), guest_offset,
*host_offset, *nb_clusters);
/*
* Check if there already is an AIO write request in flight which allocates
* the same cluster. In this case we need to wait until the previous
* request has completed and updated the L2 table accordingly.
*/
QLIST_FOREACH(old_alloc, &s->cluster_allocs, next_in_flight) {
uint64_t start = guest_offset >> s->cluster_bits;
@ -807,6 +795,42 @@ static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
abort();
}
return 0;
}
/*
* Allocates new clusters for the given guest_offset.
*
* At most *nb_clusters are allocated, and on return *nb_clusters is updated to
* contain the number of clusters that have been allocated and are contiguous
* in the image file.
*
* If *host_offset is non-zero, it specifies the offset in the image file at
* which the new clusters must start. *nb_clusters can be 0 on return in this
* case if the cluster at host_offset is already in use. If *host_offset is
* zero, the clusters can be allocated anywhere in the image file.
*
* *host_offset is updated to contain the offset into the image file at which
* the first allocated cluster starts.
*
* Return 0 on success and -errno in error cases. -EAGAIN means that the
* function has been waiting for another request and the allocation must be
* restarted, but the whole request should not be failed.
*/
static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
uint64_t *host_offset, unsigned int *nb_clusters)
{
BDRVQcowState *s = bs->opaque;
int ret;
trace_qcow2_do_alloc_clusters_offset(qemu_coroutine_self(), guest_offset,
*host_offset, *nb_clusters);
ret = handle_dependencies(bs, guest_offset, nb_clusters);
if (ret < 0) {
return ret;
}
/* Allocate new clusters */
trace_qcow2_cluster_alloc_phys(qemu_coroutine_self());
if (*host_offset == 0) {
@ -818,7 +842,7 @@ static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
*host_offset = cluster_offset;
return 0;
} else {
int ret = qcow2_alloc_clusters_at(bs, *host_offset, *nb_clusters);
ret = qcow2_alloc_clusters_at(bs, *host_offset, *nb_clusters);
if (ret < 0) {
return ret;
}
@ -847,7 +871,7 @@ static int do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset,
* Return 0 on success and -errno in error cases
*/
int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
int n_start, int n_end, int *num, QCowL2Meta *m)
int n_start, int n_end, int *num, uint64_t *host_offset, QCowL2Meta **m)
{
BDRVQcowState *s = bs->opaque;
int l2_index, ret, sectors;
@ -919,12 +943,6 @@ again:
}
/* If there is something left to allocate, do that now */
*m = (QCowL2Meta) {
.cluster_offset = cluster_offset,
.nb_clusters = 0,
};
qemu_co_queue_init(&m->dependent_requests);
if (nb_clusters > 0) {
uint64_t alloc_offset;
uint64_t alloc_cluster_offset;
@ -957,22 +975,40 @@ again:
*
* avail_sectors: Number of sectors from the start of the first
* newly allocated to the end of the last newly allocated cluster.
*
* nb_sectors: The number of sectors from the start of the first
* newly allocated cluster to the end of the aread that the write
* request actually writes to (excluding COW at the end)
*/
int requested_sectors = n_end - keep_clusters * s->cluster_sectors;
int avail_sectors = nb_clusters
<< (s->cluster_bits - BDRV_SECTOR_BITS);
int alloc_n_start = keep_clusters == 0 ? n_start : 0;
int nb_sectors = MIN(requested_sectors, avail_sectors);
*m = (QCowL2Meta) {
.cluster_offset = keep_clusters == 0 ?
alloc_cluster_offset : cluster_offset,
if (keep_clusters == 0) {
cluster_offset = alloc_cluster_offset;
}
*m = g_malloc0(sizeof(**m));
**m = (QCowL2Meta) {
.alloc_offset = alloc_cluster_offset,
.offset = alloc_offset,
.n_start = keep_clusters == 0 ? n_start : 0,
.offset = alloc_offset & ~(s->cluster_size - 1),
.nb_clusters = nb_clusters,
.nb_available = MIN(requested_sectors, avail_sectors),
.nb_available = nb_sectors,
.cow_start = {
.offset = 0,
.nb_sectors = alloc_n_start,
},
.cow_end = {
.offset = nb_sectors * BDRV_SECTOR_SIZE,
.nb_sectors = avail_sectors - nb_sectors,
},
};
qemu_co_queue_init(&m->dependent_requests);
QLIST_INSERT_HEAD(&s->cluster_allocs, m, next_in_flight);
qemu_co_queue_init(&(*m)->dependent_requests);
QLIST_INSERT_HEAD(&s->cluster_allocs, *m, next_in_flight);
}
}
@ -984,12 +1020,13 @@ again:
assert(sectors > n_start);
*num = sectors - n_start;
*host_offset = cluster_offset;
return 0;
fail:
if (m->nb_clusters > 0) {
QLIST_REMOVE(m, next_in_flight);
if (*m && (*m)->nb_clusters > 0) {
QLIST_REMOVE(*m, next_in_flight);
}
return ret;
}

5
block/qcow2-refcount.c
View File

@ -23,7 +23,7 @@
*/
#include "qemu-common.h"
#include "block_int.h"
#include "block/block_int.h"
#include "block/qcow2.h"
static int64_t alloc_clusters_noref(BlockDriverState *bs, int64_t size);
@ -301,7 +301,8 @@ 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);
uint64_t table_clusters =
size_to_clusters(s, table_size * sizeof(uint64_t));
blocks_clusters = 1 +
((table_clusters + refcount_block_clusters - 1)
/ refcount_block_clusters);

2
block/qcow2-snapshot.c
View File

@ -23,7 +23,7 @@
*/
#include "qemu-common.h"
#include "block_int.h"
#include "block/block_int.h"
#include "block/qcow2.h"
typedef struct QEMU_PACKED QCowSnapshotHeader {

108
block/qcow2.c
View File

@ -22,13 +22,13 @@
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include <zlib.h>
#include "aes.h"
#include "block/aes.h"
#include "block/qcow2.h"
#include "qemu-error.h"
#include "qerror.h"
#include "qemu/error-report.h"
#include "qapi/qmp/qerror.h"
#include "trace.h"
/*
@ -52,6 +52,7 @@ 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
@ -221,7 +222,7 @@ static void report_unsupported_feature(BlockDriverState *bs,
* updated successfully. Therefore it is not required to check the return
* value of this function.
*/
static int qcow2_mark_dirty(BlockDriverState *bs)
int qcow2_mark_dirty(BlockDriverState *bs)
{
BDRVQcowState *s = bs->opaque;
uint64_t val;
@ -558,6 +559,14 @@ 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)
{
@ -736,21 +745,6 @@ fail:
return ret;
}
static void run_dependent_requests(BDRVQcowState *s, QCowL2Meta *m)
{
/* Take the request off the list of running requests */
if (m->nb_clusters != 0) {
QLIST_REMOVE(m, next_in_flight);
}
/* Restart all dependent requests */
if (!qemu_co_queue_empty(&m->dependent_requests)) {
qemu_co_mutex_unlock(&s->lock);
qemu_co_queue_restart_all(&m->dependent_requests);
qemu_co_mutex_lock(&s->lock);
}
}
static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
int64_t sector_num,
int remaining_sectors,
@ -765,15 +759,11 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
QEMUIOVector hd_qiov;
uint64_t bytes_done = 0;
uint8_t *cluster_data = NULL;
QCowL2Meta l2meta = {
.nb_clusters = 0,
};
QCowL2Meta *l2meta;
trace_qcow2_writev_start_req(qemu_coroutine_self(), sector_num,
remaining_sectors);
qemu_co_queue_init(&l2meta.dependent_requests);
qemu_iovec_init(&hd_qiov, qiov->niov);
s->cluster_cache_offset = -1; /* disable compressed cache */
@ -782,6 +772,8 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
while (remaining_sectors != 0) {
l2meta = NULL;
trace_qcow2_writev_start_part(qemu_coroutine_self());
index_in_cluster = sector_num & (s->cluster_sectors - 1);
n_end = index_in_cluster + remaining_sectors;
@ -791,17 +783,11 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
}
ret = qcow2_alloc_cluster_offset(bs, sector_num << 9,
index_in_cluster, n_end, &cur_nr_sectors, &l2meta);
index_in_cluster, n_end, &cur_nr_sectors, &cluster_offset, &l2meta);
if (ret < 0) {
goto fail;
}
if (l2meta.nb_clusters > 0 &&
(s->compatible_features & QCOW2_COMPAT_LAZY_REFCOUNTS)) {
qcow2_mark_dirty(bs);
}
cluster_offset = l2meta.cluster_offset;
assert((cluster_offset & 511) == 0);
qemu_iovec_reset(&hd_qiov);
@ -826,8 +812,8 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
cur_nr_sectors * 512);
}
BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
qemu_co_mutex_unlock(&s->lock);
BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
trace_qcow2_writev_data(qemu_coroutine_self(),
(cluster_offset >> 9) + index_in_cluster);
ret = bdrv_co_writev(bs->file,
@ -838,12 +824,24 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
goto fail;
}
ret = qcow2_alloc_cluster_link_l2(bs, &l2meta);
if (ret < 0) {
goto fail;
}
if (l2meta != NULL) {
ret = qcow2_alloc_cluster_link_l2(bs, l2meta);
if (ret < 0) {
goto fail;
}
run_dependent_requests(s, &l2meta);
/* Take the request off the list of running requests */
if (l2meta->nb_clusters != 0) {
QLIST_REMOVE(l2meta, next_in_flight);
}
qemu_co_mutex_unlock(&s->lock);
qemu_co_queue_restart_all(&l2meta->dependent_requests);
qemu_co_mutex_lock(&s->lock);
g_free(l2meta);
l2meta = NULL;
}
remaining_sectors -= cur_nr_sectors;
sector_num += cur_nr_sectors;
@ -853,10 +851,16 @@ static coroutine_fn int qcow2_co_writev(BlockDriverState *bs,
ret = 0;
fail:
run_dependent_requests(s, &l2meta);
qemu_co_mutex_unlock(&s->lock);
if (l2meta != NULL) {
if (l2meta->nb_clusters != 0) {
QLIST_REMOVE(l2meta, next_in_flight);
}
qemu_co_queue_restart_all(&l2meta->dependent_requests);
g_free(l2meta);
}
qemu_iovec_destroy(&hd_qiov);
qemu_vfree(cluster_data);
trace_qcow2_writev_done_req(qemu_coroutine_self(), ret);
@ -1087,6 +1091,7 @@ 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));
@ -1118,31 +1123,33 @@ static int preallocate(BlockDriverState *bs)
{
uint64_t nb_sectors;
uint64_t offset;
uint64_t host_offset = 0;
int num;
int ret;
QCowL2Meta meta;
QCowL2Meta *meta;
nb_sectors = bdrv_getlength(bs) >> 9;
offset = 0;
qemu_co_queue_init(&meta.dependent_requests);
meta.cluster_offset = 0;
while (nb_sectors) {
num = MIN(nb_sectors, INT_MAX >> 9);
ret = qcow2_alloc_cluster_offset(bs, offset, 0, num, &num, &meta);
ret = qcow2_alloc_cluster_offset(bs, offset, 0, num, &num,
&host_offset, &meta);
if (ret < 0) {
return ret;
}
ret = qcow2_alloc_cluster_link_l2(bs, &meta);
ret = qcow2_alloc_cluster_link_l2(bs, meta);
if (ret < 0) {
qcow2_free_any_clusters(bs, meta.cluster_offset, meta.nb_clusters);
qcow2_free_any_clusters(bs, meta->alloc_offset, meta->nb_clusters);
return ret;
}
/* There are no dependent requests, but we need to remove our request
* from the list of in-flight requests */
run_dependent_requests(bs->opaque, &meta);
if (meta != NULL) {
QLIST_REMOVE(meta, next_in_flight);
}
/* TODO Preallocate data if requested */
@ -1155,10 +1162,10 @@ static int preallocate(BlockDriverState *bs)
* all of the allocated clusters (otherwise we get failing reads after
* EOF). Extend the image to the last allocated sector.
*/
if (meta.cluster_offset != 0) {
if (host_offset != 0) {
uint8_t buf[512];
memset(buf, 0, 512);
ret = bdrv_write(bs->file, (meta.cluster_offset >> 9) + num - 1, buf, 1);
ret = bdrv_write(bs->file, (host_offset >> 9) + num - 1, buf, 1);
if (ret < 0) {
return ret;
}
@ -1679,6 +1686,7 @@ 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,

53
block/qcow2.h
View File

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

3
block/qed-table.c
View File

@ -13,7 +13,7 @@
*/
#include "trace.h"
#include "qemu_socket.h" /* for EINPROGRESS on Windows */
#include "qemu/sockets.h" /* for EINPROGRESS on Windows */
#include "qed.h"
typedef struct {
@ -103,7 +103,6 @@ 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;
}
/**

30
block/qed.c
View File

@ -12,11 +12,11 @@
*
*/
#include "qemu-timer.h"
#include "qemu/timer.h"
#include "trace.h"
#include "qed.h"
#include "qerror.h"
#include "migration.h"
#include "qapi/qmp/qerror.h"
#include "migration/migration.h"
static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
{
@ -30,7 +30,7 @@ static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
}
}
static AIOPool qed_aio_pool = {
static const AIOCBInfo qed_aiocb_info = {
.aiocb_size = sizeof(QEDAIOCB),
.cancel = qed_aio_cancel,
};
@ -505,6 +505,14 @@ 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;
@ -1303,7 +1311,7 @@ static BlockDriverAIOCB *qed_aio_setup(BlockDriverState *bs,
BlockDriverCompletionFunc *cb,
void *opaque, int flags)
{
QEDAIOCB *acb = qemu_aio_get(&qed_aio_pool, bs, cb, opaque);
QEDAIOCB *acb = qemu_aio_get(&qed_aiocb_info, bs, cb, opaque);
trace_qed_aio_setup(bs->opaque, acb, sector_num, nb_sectors,
opaque, flags);
@ -1363,10 +1371,21 @@ 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.
*/
@ -1553,6 +1572,7 @@ 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,

2
block/qed.h
View File

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

29
block/raw-posix-aio.h → block/raw-aio.h
View File

@ -1,5 +1,5 @@
/*
* QEMU Posix block I/O backend AIO support
* Declarations for AIO in the raw protocol
*
* 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_POSIX_AIO_H
#define QEMU_RAW_POSIX_AIO_H
#ifndef QEMU_RAW_AIO_H
#define QEMU_RAW_AIO_H
/* AIO request types */
#define QEMU_AIO_READ 0x0001
@ -27,19 +27,22 @@
#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
#endif /* QEMU_RAW_POSIX_AIO_H */
#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 */

583
block/raw-posix.c
View File

@ -22,12 +22,14 @@
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "qemu-timer.h"
#include "qemu-char.h"
#include "qemu-log.h"
#include "block_int.h"
#include "module.h"
#include "block/raw-posix-aio.h"
#include "qemu/timer.h"
#include "qemu/log.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "trace.h"
#include "block/thread-pool.h"
#include "qemu/iov.h"
#include "raw-aio.h"
#if defined(__APPLE__) && (__MACH__)
#include <paths.h>
@ -133,16 +135,36 @@ 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
@ -185,6 +207,57 @@ 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)
{
@ -196,20 +269,8 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
return ret;
}
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->open_flags = open_flags;
raw_parse_flags(bdrv_flags, &s->open_flags);
s->fd = -1;
fd = qemu_open(filename, s->open_flags, 0644);
@ -220,45 +281,13 @@ 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
/*
* 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
if (raw_set_aio(&s->aio_ctx, &s->use_aio, bdrv_flags)) {
qemu_close(fd);
return -errno;
}
#endif
#ifdef CONFIG_XFS
if (platform_test_xfs_fd(s->fd)) {
@ -267,12 +296,6 @@ static int raw_open_common(BlockDriverState *bs, const char *filename,
#endif
return 0;
out_free_buf:
qemu_vfree(s->aligned_buf);
out_close:
qemu_close(fd);
return -errno;
}
static int raw_open(BlockDriverState *bs, const char *filename, int flags)
@ -283,6 +306,113 @@ 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
{
@ -316,6 +446,267 @@ 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;
}
/*
* This looks weird, but the aio code only considers a request
* successful if it has written the full number of bytes.
*
* Now we overload aio_nbytes as aio_ioctl_cmd for the ioctl command,
* so in fact we return the ioctl command here to make posix_aio_read()
* happy..
*/
return aiocb->aio_nbytes;
}
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 *raw_aio_submit(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque, int type)
@ -330,7 +721,7 @@ 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 (s->aligned_buf) {
if ((bs->open_flags & BDRV_O_NOCACHE)) {
if (!qiov_is_aligned(bs, qiov)) {
type |= QEMU_AIO_MISALIGNED;
#ifdef CONFIG_LINUX_AIO
@ -378,8 +769,6 @@ static void raw_close(BlockDriverState *bs)
if (s->fd >= 0) {
qemu_close(s->fd);
s->fd = -1;
if (s->aligned_buf != NULL)
qemu_vfree(s->aligned_buf);
}
}
@ -735,6 +1124,9 @@ 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,
@ -937,10 +1329,19 @@ static BlockDriverAIOCB *hdev_aio_ioctl(BlockDriverState *bs,
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVRawState *s = bs->opaque;
RawPosixAIOData *acb;
if (fd_open(bs) < 0)
return NULL;
return paio_ioctl(bs, s->fd, req, buf, cb, opaque);
acb = g_slice_new(RawPosixAIOData);
acb->bs = bs;
acb->aio_type = QEMU_AIO_IOCTL;
acb->aio_fildes = s->fd;
acb->aio_offset = 0;
acb->aio_ioctl_buf = buf;
acb->aio_ioctl_cmd = req;
return thread_pool_submit_aio(aio_worker, acb, cb, opaque);
}
#elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
@ -1004,6 +1405,9 @@ 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,
@ -1125,6 +1529,9 @@ 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,
@ -1224,6 +1631,9 @@ 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,
@ -1343,6 +1753,9 @@ 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,
@ -1363,6 +1776,40 @@ static BlockDriver bdrv_host_cdrom = {
};
#endif /* __FreeBSD__ */
#ifdef CONFIG_LINUX_AIO
/**
* Return the file descriptor for Linux AIO
*
* This function is a layering violation and should be removed when it becomes
* possible to call the block layer outside the global mutex. It allows the
* caller to hijack the file descriptor so I/O can be performed outside the
* block layer.
*/
int raw_get_aio_fd(BlockDriverState *bs)
{
BDRVRawState *s;
if (!bs->drv) {
return -ENOMEDIUM;
}
if (bs->drv == bdrv_find_format("raw")) {
bs = bs->file;
}
/* raw-posix has several protocols so just check for raw_aio_readv */
if (bs->drv->bdrv_aio_readv != raw_aio_readv) {
return -ENOTSUP;
}
s = bs->opaque;
if (!s->use_aio) {
return -ENOTSUP;
}
return s->fd;
}
#endif /* CONFIG_LINUX_AIO */
static void bdrv_file_init(void)
{
/*

294
block/raw-win32.c
View File

@ -22,9 +22,13 @@
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "qemu-timer.h"
#include "block_int.h"
#include "module.h"
#include "qemu/timer.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "raw-aio.h"
#include "trace.h"
#include "block/thread-pool.h"
#include "qemu/iov.h"
#include <windows.h>
#include <winioctl.h>
@ -32,12 +36,130 @@
#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;
@ -77,6 +199,26 @@ 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;
@ -85,17 +227,15 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags)
s->type = FTYPE_FILE;
if (flags & BDRV_O_RDWR) {
access_flags = GENERIC_READ | GENERIC_WRITE;
} else {
access_flags = GENERIC_READ;
raw_parse_flags(flags, &access_flags, &overlapped);
if ((flags & BDRV_O_NATIVE_AIO) && aio == NULL) {
aio = win32_aio_init();
if (aio == NULL) {
return -EINVAL;
}
}
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);
@ -104,64 +244,53 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags)
if (err == ERROR_ACCESS_DENIED)
return -EACCES;
return -1;
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 0;
}
static int raw_read(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
static BlockDriverAIOCB *raw_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVRawState *s = bs->opaque;
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 int raw_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
BDRVRawState *s = bs->opaque;
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 int raw_flush(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
int ret;
ret = FlushFileBuffers(s->hfile);
if (ret == 0) {
return -EIO;
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);
}
}
return 0;
static BlockDriverAIOCB *raw_aio_writev(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque)
{
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);
}
}
static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs,
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVRawState *s = bs->opaque;
return paio_submit(bs, s->hfile, 0, NULL, 0, cb, opaque, QEMU_AIO_FLUSH);
}
static void raw_close(BlockDriverState *bs)
@ -174,13 +303,24 @@ static int raw_truncate(BlockDriverState *bs, int64_t offset)
{
BDRVRawState *s = bs->opaque;
LONG low, high;
DWORD dwPtrLow;
low = offset;
high = offset >> 32;
if (!SetFilePointer(s->hfile, low, &high, FILE_BEGIN))
return -EIO;
if (!SetEndOfFile(s->hfile))
/*
* An error has occurred if the return value is INVALID_SET_FILE_POINTER
* and GetLastError doesn't return NO_ERROR.
*/
dwPtrLow = SetFilePointer(s->hfile, low, &high, FILE_BEGIN);
if (dwPtrLow == INVALID_SET_FILE_POINTER && GetLastError() != NO_ERROR) {
fprintf(stderr, "SetFilePointer error: %lu\n", GetLastError());
return -EIO;
}
if (SetEndOfFile(s->hfile) == 0) {
fprintf(stderr, "SetEndOfFile error: %lu\n", GetLastError());
return -EIO;
}
return 0;
}
@ -282,9 +422,9 @@ static BlockDriver bdrv_file = {
.bdrv_close = raw_close,
.bdrv_create = raw_create,
.bdrv_read = raw_read,
.bdrv_write = raw_write,
.bdrv_co_flush_to_disk = raw_flush,
.bdrv_aio_readv = raw_aio_readv,
.bdrv_aio_writev = raw_aio_writev,
.bdrv_aio_flush = raw_aio_flush,
.bdrv_truncate = raw_truncate,
.bdrv_getlength = raw_getlength,
@ -374,18 +514,10 @@ static int hdev_open(BlockDriverState *bs, const char *filename, int flags)
}
s->type = find_device_type(bs, filename);
if (flags & BDRV_O_RDWR) {
access_flags = GENERIC_READ | GENERIC_WRITE;
} else {
access_flags = GENERIC_READ;
}
raw_parse_flags(flags, &access_flags, &overlapped);
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);
@ -413,9 +545,9 @@ static BlockDriver bdrv_host_device = {
.bdrv_close = raw_close,
.bdrv_has_zero_init = hdev_has_zero_init,
.bdrv_read = raw_read,
.bdrv_write = raw_write,
.bdrv_co_flush_to_disk = raw_flush,
.bdrv_aio_readv = raw_aio_readv,
.bdrv_aio_writev = raw_aio_writev,
.bdrv_aio_flush = raw_aio_flush,
.bdrv_getlength = raw_getlength,
.bdrv_get_allocated_file_size

14
block/raw.c
View File

@ -1,7 +1,7 @@
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "block/block_int.h"
#include "qemu/module.h"
static int raw_open(BlockDriverState *bs, int flags)
{
@ -9,6 +9,14 @@ 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)
{
@ -115,6 +123,8 @@ 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,

38
block/rbd.c
View File

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

143
block/sheepdog.c
View File

@ -13,10 +13,10 @@
*/
#include "qemu-common.h"
#include "qemu-error.h"
#include "qemu_socket.h"
#include "block_int.h"
#include "bitops.h"
#include "qemu/error-report.h"
#include "qemu/sockets.h"
#include "block/block_int.h"
#include "qemu/bitops.h"
#define SD_PROTO_VER 0x01
@ -201,12 +201,12 @@ static inline uint64_t fnv_64a_buf(void *buf, size_t len, uint64_t hval)
return hval;
}
static inline int is_data_obj_writable(SheepdogInode *inode, unsigned int idx)
static inline bool is_data_obj_writable(SheepdogInode *inode, unsigned int idx)
{
return inode->vdi_id == inode->data_vdi_id[idx];
}
static inline int is_data_obj(uint64_t oid)
static inline bool 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 int is_snapshot(struct SheepdogInode *inode)
static inline bool is_snapshot(struct SheepdogInode *inode)
{
return !!inode->snap_ctime;
}
@ -281,7 +281,7 @@ struct SheepdogAIOCB {
Coroutine *coroutine;
void (*aio_done_func)(SheepdogAIOCB *);
int canceled;
bool canceled;
int nr_pending;
};
@ -292,8 +292,8 @@ typedef struct BDRVSheepdogState {
uint32_t max_dirty_data_idx;
char name[SD_MAX_VDI_LEN];
int is_snapshot;
uint8_t cache_enabled;
bool is_snapshot;
bool cache_enabled;
char *addr;
char *port;
@ -417,10 +417,10 @@ static void sd_aio_cancel(BlockDriverAIOCB *blockacb)
*/
acb->ret = -EIO;
qemu_coroutine_enter(acb->coroutine, NULL);
acb->canceled = 1;
acb->canceled = true;
}
static AIOPool sd_aio_pool = {
static const AIOCBInfo sd_aiocb_info = {
.aiocb_size = sizeof(SheepdogAIOCB),
.cancel = sd_aio_cancel,
};
@ -431,7 +431,7 @@ static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
{
SheepdogAIOCB *acb;
acb = qemu_aio_get(&sd_aio_pool, bs, cb, opaque);
acb = qemu_aio_get(&sd_aiocb_info, bs, cb, opaque);
acb->qiov = qiov;
@ -439,7 +439,7 @@ static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
acb->nb_sectors = nb_sectors;
acb->aio_done_func = NULL;
acb->canceled = 0;
acb->canceled = false;
acb->coroutine = qemu_coroutine_self();
acb->ret = 0;
acb->nr_pending = 0;
@ -485,6 +485,7 @@ static int connect_to_sdog(const char *addr, const char *port)
if (errno == EINTR) {
goto reconnect;
}
close(fd);
break;
}
@ -612,7 +613,7 @@ static int do_req(int sockfd, SheepdogReq *hdr, void *data,
}
static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
struct iovec *iov, int niov, int create,
struct iovec *iov, int niov, bool create,
enum AIOCBState aiocb_type);
@ -645,7 +646,7 @@ static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid)
QLIST_REMOVE(aio_req, aio_siblings);
QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
ret = add_aio_request(s, aio_req, acb->qiov->iov,
acb->qiov->niov, 0, acb->aiocb_type);
acb->qiov->niov, false, acb->aiocb_type);
if (ret < 0) {
error_report("add_aio_request is failed");
free_aio_req(s, aio_req);
@ -713,16 +714,17 @@ static void coroutine_fn aio_read_response(void *opaque)
* and max_dirty_data_idx are changed to include updated
* index between them.
*/
s->inode.data_vdi_id[idx] = s->inode.vdi_id;
s->max_dirty_data_idx = MAX(idx, s->max_dirty_data_idx);
s->min_dirty_data_idx = MIN(idx, s->min_dirty_data_idx);
if (rsp.result == SD_RES_SUCCESS) {
s->inode.data_vdi_id[idx] = s->inode.vdi_id;
s->max_dirty_data_idx = MAX(idx, s->max_dirty_data_idx);
s->min_dirty_data_idx = MIN(idx, s->min_dirty_data_idx);
}
/*
* Some requests may be blocked because simultaneous
* 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, aio_req->oid);
}
break;
case AIOCB_READ_UDATA:
@ -865,14 +867,14 @@ static int parse_vdiname(BDRVSheepdogState *s, const char *filename,
s->port = 0;
}
strncpy(vdi, p, SD_MAX_VDI_LEN);
pstrcpy(vdi, SD_MAX_VDI_LEN, p);
p = strchr(vdi, ':');
if (p) {
*p++ = '\0';
*snapid = strtoul(p, NULL, 10);
if (*snapid == 0) {
strncpy(tag, p, SD_MAX_VDI_TAG_LEN);
pstrcpy(tag, SD_MAX_VDI_TAG_LEN, p);
}
} else {
*snapid = CURRENT_VDI_ID; /* search current vdi */
@ -899,7 +901,10 @@ static int find_vdi_name(BDRVSheepdogState *s, char *filename, uint32_t snapid,
return fd;
}
memset(buf, 0, sizeof(buf));
/* 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.
*/
strncpy(buf, filename, SD_MAX_VDI_LEN);
strncpy(buf + SD_MAX_VDI_LEN, tag, SD_MAX_VDI_TAG_LEN);
@ -939,7 +944,7 @@ out:
}
static int coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
struct iovec *iov, int niov, int create,
struct iovec *iov, int niov, bool create,
enum AIOCBState aiocb_type)
{
int nr_copies = s->inode.nr_copies;
@ -1018,7 +1023,7 @@ 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,
int write, int create, uint8_t cache)
bool write, bool create, bool cache)
{
SheepdogObjReq hdr;
SheepdogObjRsp *rsp = (SheepdogObjRsp *)&hdr;
@ -1067,18 +1072,18 @@ 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, uint8_t cache)
unsigned int datalen, uint64_t offset, bool cache)
{
return read_write_object(fd, buf, oid, copies, datalen, offset, 0, 0,
cache);
return read_write_object(fd, buf, oid, copies, datalen, offset, false,
false, cache);
}
static int write_object(int fd, char *buf, uint64_t oid, int copies,
unsigned int datalen, uint64_t offset, int create,
uint8_t cache)
unsigned int datalen, uint64_t offset, bool create,
bool cache)
{
return read_write_object(fd, buf, oid, copies, datalen, offset, 1, create,
cache);
return read_write_object(fd, buf, oid, copies, datalen, offset, true,
create, cache);
}
static int sd_open(BlockDriverState *bs, const char *filename, int flags)
@ -1113,19 +1118,17 @@ static int sd_open(BlockDriverState *bs, const char *filename, int flags)
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;
}
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 (snapid || tag[0] != '\0') {
dprintf("%" PRIx32 " snapshot inode was open.\n", vid);
s->is_snapshot = 1;
s->is_snapshot = true;
}
fd = connect_to_sdog(s->addr, s->port);
@ -1150,7 +1153,7 @@ 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;
strncpy(s->name, vdi, sizeof(s->name));
pstrcpy(s->name, sizeof(s->name), vdi);
qemu_co_mutex_init(&s->lock);
g_free(buf);
return 0;
@ -1178,8 +1181,11 @@ 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));
strncpy(buf, filename, SD_MAX_VDI_LEN);
pstrcpy(buf, sizeof(buf), filename);
memset(&hdr, 0, sizeof(hdr));
hdr.opcode = SD_OP_NEW_VDI;
@ -1265,7 +1271,7 @@ 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;
int prealloc = 0;
bool prealloc = false;
const char *vdiname;
s = g_malloc0(sizeof(BDRVSheepdogState));
@ -1287,9 +1293,9 @@ 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 = 0;
prealloc = false;
} else if (!strcmp(options->value.s, "full")) {
prealloc = 1;
prealloc = true;
} else {
error_report("Invalid preallocation mode: '%s'",
options->value.s);
@ -1417,7 +1423,7 @@ 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, 0, s->cache_enabled);
s->inode.nr_copies, datalen, 0, false, s->cache_enabled);
close(fd);
if (ret < 0) {
@ -1456,7 +1462,7 @@ static void coroutine_fn sd_write_done(SheepdogAIOCB *acb)
aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id),
data_len, offset, 0, 0, offset);
QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
ret = add_aio_request(s, aio_req, &iov, 1, 0, AIOCB_WRITE_UDATA);
ret = add_aio_request(s, aio_req, &iov, 1, false, AIOCB_WRITE_UDATA);
if (ret) {
free_aio_req(s, aio_req);
acb->ret = -EIO;
@ -1510,7 +1516,7 @@ static int sd_create_branch(BDRVSheepdogState *s)
memcpy(&s->inode, buf, sizeof(s->inode));
s->is_snapshot = 0;
s->is_snapshot = false;
ret = 0;
dprintf("%" PRIx32 " was newly created.\n", s->inode.vdi_id);
@ -1565,7 +1571,7 @@ static int coroutine_fn sd_co_rw_vector(void *p)
while (done != total) {
uint8_t flags = 0;
uint64_t old_oid = 0;
int create = 0;
bool create = false;
oid = vid_to_data_oid(inode->data_vdi_id[idx], idx);
@ -1580,10 +1586,10 @@ static int coroutine_fn sd_co_rw_vector(void *p)
break;
case AIOCB_WRITE_UDATA:
if (!inode->data_vdi_id[idx]) {
create = 1;
create = true;
} else if (!is_data_obj_writable(inode, idx)) {
/* Copy-On-Write */
create = 1;
create = true;
old_oid = oid;
flags = SD_FLAG_CMD_COW;
}
@ -1717,7 +1723,7 @@ 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 = 0;
s->cache_enabled = false;
closesocket(s->flush_fd);
return 0;
}
@ -1753,6 +1759,9 @@ 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);
@ -1765,7 +1774,7 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
}
ret = write_object(fd, (char *)&s->inode, vid_to_vdi_oid(s->inode.vdi_id),
s->inode.nr_copies, datalen, 0, 0, s->cache_enabled);
s->inode.nr_copies, datalen, 0, false, s->cache_enabled);
if (ret < 0) {
error_report("failed to write snapshot's inode.");
goto cleanup;
@ -1812,13 +1821,13 @@ static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
memcpy(old_s, s, sizeof(BDRVSheepdogState));
memset(vdi, 0, sizeof(vdi));
strncpy(vdi, s->name, sizeof(vdi));
pstrcpy(vdi, sizeof(vdi), s->name);
memset(tag, 0, sizeof(tag));
snapid = strtoul(snapshot_id, NULL, 10);
if (!snapid) {
strncpy(tag, s->name, sizeof(tag));
if (snapid) {
tag[0] = 0;
} else {
pstrcpy(tag, sizeof(tag), s->name);
}
ret = find_vdi_name(s, vdi, snapid, tag, &vid, 1);
@ -1852,7 +1861,7 @@ static int sd_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
goto out;
}
s->is_snapshot = 1;
s->is_snapshot = true;
g_free(buf);
g_free(old_s);
@ -1947,8 +1956,9 @@ 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);
strncpy(sn_tab[found].name, inode.tag,
MIN(sizeof(sn_tab[found].name), sizeof(inode.tag)));
pstrcpy(sn_tab[found].name,
MIN(sizeof(sn_tab[found].name), sizeof(inode.tag)),
inode.tag);
found++;
}
}
@ -1969,8 +1979,8 @@ out:
static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data,
int64_t pos, int size, int load)
{
int fd, create;
int ret = 0, remaining = size;
bool create;
int fd, ret = 0, remaining = size;
unsigned int data_len;
uint64_t vmstate_oid;
uint32_t vdi_index;
@ -1985,7 +1995,7 @@ 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);
data_len = MIN(remaining, SD_DATA_OBJ_SIZE - offset);
vmstate_oid = vid_to_vmstate_oid(s->inode.vdi_id, vdi_index);
@ -2006,6 +2016,7 @@ static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data,
}
pos += data_len;
data += data_len;
remaining -= data_len;
}
ret = size;

43
block/stream.c
View File

@ -12,7 +12,8 @@
*/
#include "trace.h"
#include "block_int.h"
#include "block/block_int.h"
#include "block/blockjob.h"
#include "qemu/ratelimit.h"
enum {
@ -30,6 +31,7 @@ typedef struct StreamBlockJob {
BlockJob common;
RateLimit limit;
BlockDriverState *base;
BlockdevOnError on_error;
char backing_file_id[1024];
} StreamBlockJob;
@ -77,13 +79,14 @@ static void coroutine_fn stream_run(void *opaque)
BlockDriverState *bs = s->common.bs;
BlockDriverState *base = s->base;
int64_t sector_num, end;
int error = 0;
int ret = 0;
int n = 0;
void *buf;
s->common.len = bdrv_getlength(bs);
if (s->common.len < 0) {
block_job_complete(&s->common, s->common.len);
block_job_completed(&s->common, s->common.len);
return;
}
@ -105,7 +108,7 @@ static void coroutine_fn stream_run(void *opaque)
wait:
/* Note that even when no rate limit is applied we need to yield
* with no pending I/O here so that qemu_aio_flush() returns.
* with no pending I/O here so that bdrv_drain_all() returns.
*/
block_job_sleep_ns(&s->common, rt_clock, delay_ns);
if (block_job_is_cancelled(&s->common)) {
@ -122,6 +125,12 @@ wait:
* known-unallocated area [sector_num, sector_num+n). */
ret = bdrv_co_is_allocated_above(bs->backing_hd, base,
sector_num, n, &n);
/* Finish early if end of backing file has been reached */
if (ret == 0 && n == 0) {
n = end - sector_num;
}
copy = (ret == 1);
}
trace_stream_one_iteration(s, sector_num, n, ret);
@ -135,7 +144,19 @@ wait:
ret = stream_populate(bs, sector_num, n, buf);
}
if (ret < 0) {
break;
BlockErrorAction action =
block_job_error_action(&s->common, s->common.bs, s->on_error,
true, -ret);
if (action == BDRV_ACTION_STOP) {
n = 0;
continue;
}
if (error == 0) {
error = ret;
}
if (action == BDRV_ACTION_REPORT) {
break;
}
}
ret = 0;
@ -147,6 +168,9 @@ 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) {
@ -160,7 +184,7 @@ wait:
}
qemu_vfree(buf);
block_job_complete(&s->common, ret);
block_job_completed(&s->common, ret);
}
static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
@ -182,11 +206,19 @@ 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;
@ -197,6 +229,7 @@ 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);

49
block/vdi.c
View File

@ -50,19 +50,16 @@
*/
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "migration.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "migration/migration.h"
#if defined(CONFIG_UUID)
#include <uuid/uuid.h>
#else
/* TODO: move uuid emulation to some central place in QEMU. */
#include "sysemu.h" /* UUID_FMT */
#include "sysemu/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. */
@ -124,18 +121,18 @@ void uuid_unparse(const uuid_t uu, char *out);
#define VDI_IS_ALLOCATED(X) ((X) < VDI_DISCARDED)
#if !defined(CONFIG_UUID)
void uuid_generate(uuid_t out)
static inline void uuid_generate(uuid_t out)
{
memset(out, 0, sizeof(uuid_t));
}
int uuid_is_null(const uuid_t uu)
static inline int uuid_is_null(const uuid_t uu)
{
uuid_t null_uuid = { 0 };
return memcmp(uu, null_uuid, sizeof(uuid_t)) == 0;
}
void uuid_unparse(const uuid_t uu, char *out)
static inline 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],
@ -454,6 +451,12 @@ 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)
{
@ -628,7 +631,6 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
VdiHeader header;
size_t i;
size_t bmap_size;
uint32_t *bmap;
logout("\n");
@ -693,21 +695,21 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options)
result = -errno;
}
bmap = NULL;
if (bmap_size > 0) {
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;
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);
}
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;
@ -762,6 +764,7 @@ 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,

112
block/vmdk.c
View File

@ -24,9 +24,9 @@
*/
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "migration.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "migration/migration.h"
#include <zlib.h>
#define VMDK3_MAGIC (('C' << 24) | ('O' << 16) | ('W' << 8) | 'D')
@ -35,6 +35,7 @@
#define VMDK4_FLAG_RGD (1 << 1)
#define VMDK4_FLAG_COMPRESS (1 << 16)
#define VMDK4_FLAG_MARKER (1 << 17)
#define VMDK4_GD_AT_END 0xffffffffffffffffULL
typedef struct {
uint32_t version;
@ -57,8 +58,8 @@ typedef struct {
int64_t desc_offset;
int64_t desc_size;
int32_t num_gtes_per_gte;
int64_t gd_offset;
int64_t rgd_offset;
int64_t gd_offset;
int64_t grain_offset;
char filler[1];
char check_bytes[4];
@ -115,6 +116,13 @@ typedef struct VmdkGrainMarker {
uint8_t data[0];
} VmdkGrainMarker;
enum {
MARKER_END_OF_STREAM = 0,
MARKER_GRAIN_TABLE = 1,
MARKER_GRAIN_DIRECTORY = 2,
MARKER_FOOTER = 3,
};
static int vmdk_probe(const uint8_t *buf, int buf_size, const char *filename)
{
uint32_t magic;
@ -292,6 +300,40 @@ 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;
@ -451,6 +493,54 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
if (header.capacity == 0 && header.desc_offset) {
return vmdk_open_desc_file(bs, flags, header.desc_offset << 9);
}
if (le64_to_cpu(header.gd_offset) == VMDK4_GD_AT_END) {
/*
* The footer takes precedence over the header, so read it in. The
* footer starts at offset -1024 from the end: One sector for the
* footer, and another one for the end-of-stream marker.
*/
struct {
struct {
uint64_t val;
uint32_t size;
uint32_t type;
uint8_t pad[512 - 16];
} QEMU_PACKED footer_marker;
uint32_t magic;
VMDK4Header header;
uint8_t pad[512 - 4 - sizeof(VMDK4Header)];
struct {
uint64_t val;
uint32_t size;
uint32_t type;
uint8_t pad[512 - 16];
} QEMU_PACKED eos_marker;
} QEMU_PACKED footer;
ret = bdrv_pread(file,
bs->file->total_sectors * 512 - 1536,
&footer, sizeof(footer));
if (ret < 0) {
return ret;
}
/* Some sanity checks for the footer */
if (be32_to_cpu(footer.magic) != VMDK4_MAGIC ||
le32_to_cpu(footer.footer_marker.size) != 0 ||
le32_to_cpu(footer.footer_marker.type) != MARKER_FOOTER ||
le64_to_cpu(footer.eos_marker.val) != 0 ||
le32_to_cpu(footer.eos_marker.size) != 0 ||
le32_to_cpu(footer.eos_marker.type) != MARKER_END_OF_STREAM)
{
return -EINVAL;
}
header = footer.header;
}
l1_entry_sectors = le32_to_cpu(header.num_gtes_per_gte)
* le64_to_cpu(header.granularity);
if (l1_entry_sectors == 0) {
@ -1002,6 +1092,7 @@ 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;
@ -1013,7 +1104,9 @@ static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
ret = get_cluster_offset(
bs, extent, NULL,
sector_num << 9, 0, &cluster_offset);
index_in_cluster = sector_num % extent->cluster_sectors;
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;
n = extent->cluster_sectors - index_in_cluster;
if (n > nb_sectors) {
n = nb_sectors;
@ -1064,6 +1157,7 @@ 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;
@ -1106,7 +1200,9 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
if (ret) {
return -EINVAL;
}
index_in_cluster = sector_num % extent->cluster_sectors;
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;
n = extent->cluster_sectors - index_in_cluster;
if (n > nb_sectors) {
n = nb_sectors;
@ -1318,8 +1414,7 @@ static int relative_path(char *dest, int dest_size,
return -1;
}
if (path_is_absolute(target)) {
dest[dest_size - 1] = '\0';
strncpy(dest, target, dest_size - 1);
pstrcpy(dest, dest_size, target);
return 0;
}
while (base[i] == target[i]) {
@ -1590,6 +1685,7 @@ 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,

37
block/vpc.c
View File

@ -23,9 +23,12 @@
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "migration.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "migration/migration.h"
#if defined(CONFIG_UUID)
#include <uuid/uuid.h>
#endif
/**************************************************************/
@ -198,7 +201,8 @@ static int vpc_open(BlockDriverState *bs, int flags)
bs->total_sectors = (int64_t)
be16_to_cpu(footer->cyls) * footer->heads * footer->secs_per_cyl;
if (bs->total_sectors >= 65535 * 16 * 255) {
/* Allow a maximum disk size of approximately 2 TB */
if (bs->total_sectors >= 65535LL * 255 * 255) {
err = -EFBIG;
goto fail;
}
@ -265,6 +269,12 @@ 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.
@ -518,19 +528,27 @@ static coroutine_fn int vpc_co_write(BlockDriverState *bs, int64_t sector_num,
* Note that the geometry doesn't always exactly match total_sectors but
* may round it down.
*
* Returns 0 on success, -EFBIG if the size is larger than 127 GB
* Returns 0 on success, -EFBIG if the size is larger than ~2 TB. Override
* the hardware EIDE and ATA-2 limit of 16 heads (max disk size of 127 GB)
* and instead allow up to 255 heads.
*/
static int calculate_geometry(int64_t total_sectors, uint16_t* cyls,
uint8_t* heads, uint8_t* secs_per_cyl)
{
uint32_t cyls_times_heads;
if (total_sectors > 65535 * 16 * 255)
/* Allow a maximum disk size of approximately 2 TB */
if (total_sectors > 65535LL * 255 * 255) {
return -EFBIG;
}
if (total_sectors > 65535 * 16 * 63) {
*secs_per_cyl = 255;
*heads = 16;
if (total_sectors > 65535 * 16 * 255) {
*heads = 255;
} else {
*heads = 16;
}
cyls_times_heads = total_sectors / *secs_per_cyl;
} else {
*secs_per_cyl = 17;
@ -733,7 +751,9 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options)
footer->type = be32_to_cpu(disk_type);
/* TODO uuid is missing */
#if defined(CONFIG_UUID)
uuid_generate(footer->uuid);
#endif
footer->checksum = be32_to_cpu(vpc_checksum(buf, HEADER_SIZE));
@ -783,6 +803,7 @@ 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,

6
block/vvfat.c
View File

@ -25,9 +25,9 @@
#include <sys/stat.h>
#include <dirent.h>
#include "qemu-common.h"
#include "block_int.h"
#include "module.h"
#include "migration.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "migration/migration.h"
#ifndef S_IWGRP
#define S_IWGRP 0

226
block/win32-aio.c Normal file
View File

@ -0,0 +1,226 @@
/*
* Block driver for RAW files (win32)
*
* Copyright (c) 2006 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu-common.h"
#include "qemu/timer.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "qemu-common.h"
#include "block/aio.h"
#include "raw-aio.h"
#include "qemu/event_notifier.h"
#include <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(p, qiov->iov[i].iov_base, qiov->iov[i].iov_len);
p += qiov->iov[i].iov_len;
}
g_free(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;
}

133
blockdev-nbd.c Normal file
View File

@ -0,0 +1,133 @@
/*
* Serving QEMU block devices via NBD
*
* Copyright (c) 2012 Red Hat, Inc.
*
* Author: Paolo Bonzini <pbonzini@redhat.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*/
#include "sysemu/blockdev.h"
#include "hw/block-common.h"
#include "monitor/monitor.h"
#include "qapi/qmp/qerror.h"
#include "sysemu/sysemu.h"
#include "qmp-commands.h"
#include "trace.h"
#include "block/nbd.h"
#include "qemu/sockets.h"
static int server_fd = -1;
static void nbd_accept(void *opaque)
{
struct sockaddr_in addr;
socklen_t addr_len = sizeof(addr);
int fd = accept(server_fd, (struct sockaddr *)&addr, &addr_len);
if (fd >= 0) {
nbd_client_new(NULL, fd, nbd_client_put);
}
}
void qmp_nbd_server_start(SocketAddress *addr, Error **errp)
{
if (server_fd != -1) {
error_setg(errp, "NBD server already running");
return;
}
server_fd = socket_listen(addr, errp);
if (server_fd != -1) {
qemu_set_fd_handler2(server_fd, NULL, nbd_accept, NULL, NULL);
}
}
/* Hook into the BlockDriverState notifiers to close the export when
* the file is closed.
*/
typedef struct NBDCloseNotifier {
Notifier n;
NBDExport *exp;
QTAILQ_ENTRY(NBDCloseNotifier) next;
} NBDCloseNotifier;
static QTAILQ_HEAD(, NBDCloseNotifier) close_notifiers =
QTAILQ_HEAD_INITIALIZER(close_notifiers);
static void nbd_close_notifier(Notifier *n, void *data)
{
NBDCloseNotifier *cn = DO_UPCAST(NBDCloseNotifier, n, n);
notifier_remove(&cn->n);
QTAILQ_REMOVE(&close_notifiers, cn, next);
nbd_export_close(cn->exp);
nbd_export_put(cn->exp);
g_free(cn);
}
static void nbd_server_put_ref(NBDExport *exp)
{
BlockDriverState *bs = nbd_export_get_blockdev(exp);
drive_put_ref(drive_get_by_blockdev(bs));
}
void qmp_nbd_server_add(const char *device, bool has_writable, bool writable,
Error **errp)
{
BlockDriverState *bs;
NBDExport *exp;
NBDCloseNotifier *n;
if (server_fd == -1) {
error_setg(errp, "NBD server not running");
return;
}
if (nbd_export_find(device)) {
error_setg(errp, "NBD server already exporting device '%s'", device);
return;
}
bs = bdrv_find(device);
if (!bs) {
error_set(errp, QERR_DEVICE_NOT_FOUND, device);
return;
}
if (!has_writable) {
writable = false;
}
if (bdrv_is_read_only(bs)) {
writable = false;
}
exp = nbd_export_new(bs, 0, -1, writable ? 0 : NBD_FLAG_READ_ONLY,
nbd_server_put_ref);
nbd_export_set_name(exp, device);
drive_get_ref(drive_get_by_blockdev(bs));
n = g_malloc0(sizeof(NBDCloseNotifier));
n->n.notify = nbd_close_notifier;
n->exp = exp;
bdrv_add_close_notifier(bs, &n->n);
QTAILQ_INSERT_TAIL(&close_notifiers, n, next);
}
void qmp_nbd_server_stop(Error **errp)
{
while (!QTAILQ_EMPTY(&close_notifiers)) {
NBDCloseNotifier *cn = QTAILQ_FIRST(&close_notifiers);
nbd_close_notifier(&cn->n, nbd_export_get_blockdev(cn->exp));
}
if (server_fd != -1) {
qemu_set_fd_handler2(server_fd, NULL, NULL, NULL, NULL);
close(server_fd);
server_fd = -1;
}
}

357
blockdev.c
View File

@ -7,18 +7,19 @@
* later. See the COPYING file in the top-level directory.
*/
#include "blockdev.h"
#include "sysemu/blockdev.h"
#include "hw/block-common.h"
#include "monitor.h"
#include "qerror.h"
#include "qemu-option.h"
#include "qemu-config.h"
#include "qemu-objects.h"
#include "sysemu.h"
#include "block_int.h"
#include "block/blockjob.h"
#include "monitor/monitor.h"
#include "qapi/qmp/qerror.h"
#include "qemu/option.h"
#include "qemu/config-file.h"
#include "qapi/qmp/types.h"
#include "sysemu/sysemu.h"
#include "block/block_int.h"
#include "qmp-commands.h"
#include "trace.h"
#include "arch_init.h"
#include "sysemu/arch_init.h"
static QTAILQ_HEAD(drivelist, DriveInfo) drives = QTAILQ_HEAD_INITIALIZER(drives);
@ -237,16 +238,16 @@ static void drive_put_ref_bh_schedule(DriveInfo *dinfo)
qemu_bh_schedule(s->bh);
}
static int parse_block_error_action(const char *buf, int is_read)
static int parse_block_error_action(const char *buf, bool is_read)
{
if (!strcmp(buf, "ignore")) {
return BLOCK_ERR_IGNORE;
return BLOCKDEV_ON_ERROR_IGNORE;
} else if (!is_read && !strcmp(buf, "enospc")) {
return BLOCK_ERR_STOP_ENOSPC;
return BLOCKDEV_ON_ERROR_ENOSPC;
} else if (!strcmp(buf, "stop")) {
return BLOCK_ERR_STOP_ANY;
return BLOCKDEV_ON_ERROR_STOP;
} else if (!strcmp(buf, "report")) {
return BLOCK_ERR_REPORT;
return BLOCKDEV_ON_ERROR_REPORT;
} else {
error_report("'%s' invalid %s error action",
buf, is_read ? "read" : "write");
@ -274,7 +275,7 @@ static bool do_check_io_limits(BlockIOLimit *io_limits)
return true;
}
DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
DriveInfo *drive_init(QemuOpts *opts, BlockInterfaceType block_default_type)
{
const char *buf;
const char *file = NULL;
@ -324,7 +325,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
return NULL;
}
} else {
type = default_to_scsi ? IF_SCSI : IF_IDE;
type = block_default_type;
}
max_devs = if_max_devs[type];
@ -432,7 +433,13 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
return NULL;
}
on_write_error = BLOCK_ERR_STOP_ENOSPC;
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;
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");
@ -445,7 +452,7 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
}
}
on_read_error = BLOCK_ERR_REPORT;
on_read_error = BLOCKDEV_ON_ERROR_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");
@ -527,6 +534,8 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi)
if_name[type], 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;
@ -559,7 +568,7 @@ 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_nofail(qemu_find_opts("device"));
if (arch_type == QEMU_ARCH_S390X) {
qemu_opt_set(opts, "driver", "virtio-blk-s390");
} else {
@ -698,6 +707,7 @@ void qmp_transaction(BlockdevActionList *dev_list, Error **errp)
int ret = 0;
BlockdevActionList *dev_entry = dev_list;
BlkTransactionStates *states, *next;
Error *local_err = NULL;
QSIMPLEQ_HEAD(snap_bdrv_states, BlkTransactionStates) snap_bdrv_states;
QSIMPLEQ_INIT(&snap_bdrv_states);
@ -777,12 +787,12 @@ void qmp_transaction(BlockdevActionList *dev_list, Error **errp)
/* create new image w/backing file */
if (mode != NEW_IMAGE_MODE_EXISTING) {
ret = bdrv_img_create(new_image_file, format,
states->old_bs->filename,
states->old_bs->drv->format_name,
NULL, -1, flags);
if (ret) {
error_set(errp, QERR_OPEN_FILE_FAILED, new_image_file);
bdrv_img_create(new_image_file, format,
states->old_bs->filename,
states->old_bs->drv->format_name,
NULL, -1, flags, &local_err);
if (error_is_set(&local_err)) {
error_propagate(errp, local_err);
goto delete_and_fail;
}
}
@ -803,6 +813,11 @@ 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 */
@ -822,7 +837,6 @@ exit:
QSIMPLEQ_FOREACH_SAFE(states, &snap_bdrv_states, entry, next) {
g_free(states);
}
return;
}
@ -1049,26 +1063,12 @@ void qmp_block_resize(const char *device, int64_t size, Error **errp)
}
}
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)
static void block_job_cb(void *opaque, int ret)
{
BlockDriverState *bs = opaque;
QObject *obj;
trace_block_stream_cb(bs, bs->job, ret);
trace_block_job_cb(bs, bs->job, ret);
assert(bs->job);
obj = qobject_from_block_job(bs->job);
@ -1088,13 +1088,18 @@ static void block_stream_cb(void *opaque, int ret)
}
void qmp_block_stream(const char *device, bool has_base,
const char *base, bool has_speed,
int64_t speed, Error **errp)
const char *base, bool has_speed, int64_t speed,
bool has_on_error, BlockdevOnError on_error,
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);
@ -1110,7 +1115,7 @@ void qmp_block_stream(const char *device, bool has_base,
}
stream_start(bs, base_bs, base, has_speed ? speed : 0,
block_stream_cb, bs, &local_err);
on_error, block_job_cb, bs, &local_err);
if (error_is_set(&local_err)) {
error_propagate(errp, local_err);
return;
@ -1124,6 +1129,199 @@ 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;
bdrv_img_create(target, format,
NULL, NULL, NULL, size, flags, &local_err);
} else {
switch (mode) {
case NEW_IMAGE_MODE_EXISTING:
ret = 0;
break;
case NEW_IMAGE_MODE_ABSOLUTE_PATHS:
/* create new image with backing file */
bdrv_img_create(target, format,
source->filename,
source->drv->format_name,
NULL, -1, flags, &local_err);
break;
default:
abort();
}
}
if (error_is_set(&local_err)) {
error_propagate(errp, local_err);
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;
@ -1140,19 +1338,28 @@ 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_DEVICE_NOT_ACTIVE, device);
error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
return;
}
block_job_set_speed(job, speed, errp);
}
void qmp_block_job_cancel(const char *device, Error **errp)
void qmp_block_job_cancel(const char *device,
bool has_force, bool force, Error **errp)
{
BlockJob *job = find_block_job(device);
if (!has_force) {
force = false;
}
if (!job) {
error_set(errp, QERR_DEVICE_NOT_ACTIVE, device);
error_set(errp, QERR_BLOCK_JOB_NOT_ACTIVE, device);
return;
}
if (job->paused && !force) {
error_set(errp, QERR_BLOCK_JOB_PAUSED, device);
return;
}
@ -1160,25 +1367,53 @@ void qmp_block_job_cancel(const char *device, Error **errp)
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;
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;
BlockJobInfoList *elem = g_new0(BlockJobInfoList, 1);
elem->value = block_job_query(bs->job);
(*prev)->next = elem;
*prev = elem;
}

283
blockjob.c Normal file
View File

@ -0,0 +1,283 @@
/*
* QEMU System Emulator block driver
*
* Copyright (c) 2011 IBM Corp.
* Copyright (c) 2012 Red Hat, Inc.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "config-host.h"
#include "qemu-common.h"
#include "trace.h"
#include "monitor/monitor.h"
#include "block/block.h"
#include "block/blockjob.h"
#include "block/block_int.h"
#include "qapi/qmp/qjson.h"
#include "block/coroutine.h"
#include "qmp-commands.h"
#include "qemu/timer.h"
void *block_job_create(const BlockJobType *job_type, BlockDriverState *bs,
int64_t speed, BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
BlockJob *job;
if (bs->job || bdrv_in_use(bs)) {
error_set(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
return NULL;
}
bdrv_set_in_use(bs, 1);
job = g_malloc0(job_type->instance_size);
job->job_type = job_type;
job->bs = bs;
job->cb = cb;
job->opaque = opaque;
job->busy = true;
bs->job = job;
/* Only set speed when necessary to avoid NotSupported error */
if (speed != 0) {
Error *local_err = NULL;
block_job_set_speed(job, speed, &local_err);
if (error_is_set(&local_err)) {
bs->job = NULL;
g_free(job);
bdrv_set_in_use(bs, 0);
error_propagate(errp, local_err);
return NULL;
}
}
return job;
}
void block_job_completed(BlockJob *job, int ret)
{
BlockDriverState *bs = job->bs;
assert(bs->job == job);
job->cb(job->opaque, ret);
bs->job = NULL;
g_free(job);
bdrv_set_in_use(bs, 0);
}
void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
{
Error *local_err = NULL;
if (!job->job_type->set_speed) {
error_set(errp, QERR_NOT_SUPPORTED);
return;
}
job->job_type->set_speed(job, speed, &local_err);
if (error_is_set(&local_err)) {
error_propagate(errp, local_err);
return;
}
job->speed = speed;
}
void block_job_complete(BlockJob *job, Error **errp)
{
if (job->paused || job->cancelled || !job->job_type->complete) {
error_set(errp, QERR_BLOCK_JOB_NOT_READY, job->bs->device_name);
return;
}
job->job_type->complete(job, errp);
}
void block_job_pause(BlockJob *job)
{
job->paused = true;
}
bool block_job_is_paused(BlockJob *job)
{
return job->paused;
}
void block_job_resume(BlockJob *job)
{
job->paused = false;
block_job_iostatus_reset(job);
if (job->co && !job->busy) {
qemu_coroutine_enter(job->co, NULL);
}
}
void block_job_cancel(BlockJob *job)
{
job->cancelled = true;
block_job_resume(job);
}
bool block_job_is_cancelled(BlockJob *job)
{
return job->cancelled;
}
void block_job_iostatus_reset(BlockJob *job)
{
job->iostatus = BLOCK_DEVICE_IO_STATUS_OK;
if (job->job_type->iostatus_reset) {
job->job_type->iostatus_reset(job);
}
}
struct BlockCancelData {
BlockJob *job;
BlockDriverCompletionFunc *cb;
void *opaque;
bool cancelled;
int ret;
};
static void block_job_cancel_cb(void *opaque, int ret)
{
struct BlockCancelData *data = opaque;
data->cancelled = block_job_is_cancelled(data->job);
data->ret = ret;
data->cb(data->opaque, ret);
}
int block_job_cancel_sync(BlockJob *job)
{
struct BlockCancelData data;
BlockDriverState *bs = job->bs;
assert(bs->job == job);
/* Set up our own callback to store the result and chain to
* the original callback.
*/
data.job = job;
data.cb = job->cb;
data.opaque = job->opaque;
data.ret = -EINPROGRESS;
job->cb = block_job_cancel_cb;
job->opaque = &data;
block_job_cancel(job);
while (data.ret == -EINPROGRESS) {
qemu_aio_wait();
}
return (data.cancelled && data.ret == 0) ? -ECANCELED : data.ret;
}
void block_job_sleep_ns(BlockJob *job, QEMUClock *clock, int64_t ns)
{
assert(job->busy);
/* Check cancellation *before* setting busy = false, too! */
if (block_job_is_cancelled(job)) {
return;
}
job->busy = false;
if (block_job_is_paused(job)) {
qemu_coroutine_yield();
} else {
co_sleep_ns(clock, ns);
}
job->busy = true;
}
BlockJobInfo *block_job_query(BlockJob *job)
{
BlockJobInfo *info = g_new0(BlockJobInfo, 1);
info->type = g_strdup(job->job_type->job_type);
info->device = g_strdup(bdrv_get_device_name(job->bs));
info->len = job->len;
info->busy = job->busy;
info->paused = job->paused;
info->offset = job->offset;
info->speed = job->speed;
info->io_status = job->iostatus;
return info;
}
static void block_job_iostatus_set_err(BlockJob *job, int error)
{
if (job->iostatus == BLOCK_DEVICE_IO_STATUS_OK) {
job->iostatus = error == ENOSPC ? BLOCK_DEVICE_IO_STATUS_NOSPACE :
BLOCK_DEVICE_IO_STATUS_FAILED;
}
}
QObject *qobject_from_block_job(BlockJob *job)
{
return qobject_from_jsonf("{ 'type': %s,"
"'device': %s,"
"'len': %" PRId64 ","
"'offset': %" PRId64 ","
"'speed': %" PRId64 " }",
job->job_type->job_type,
bdrv_get_device_name(job->bs),
job->len,
job->offset,
job->speed);
}
void block_job_ready(BlockJob *job)
{
QObject *data = qobject_from_block_job(job);
monitor_protocol_event(QEVENT_BLOCK_JOB_READY, data);
qobject_decref(data);
}
BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
BlockdevOnError on_err,
int is_read, int error)
{
BlockErrorAction action;
switch (on_err) {
case BLOCKDEV_ON_ERROR_ENOSPC:
action = (error == ENOSPC) ? BDRV_ACTION_STOP : BDRV_ACTION_REPORT;
break;
case BLOCKDEV_ON_ERROR_STOP:
action = BDRV_ACTION_STOP;
break;
case BLOCKDEV_ON_ERROR_REPORT:
action = BDRV_ACTION_REPORT;
break;
case BLOCKDEV_ON_ERROR_IGNORE:
action = BDRV_ACTION_IGNORE;
break;
default:
abort();
}
bdrv_emit_qmp_error_event(job->bs, QEVENT_BLOCK_JOB_ERROR, action, is_read);
if (action == BDRV_ACTION_STOP) {
block_job_pause(job);
block_job_iostatus_set_err(job, error);
if (bs != job->bs) {
bdrv_iostatus_set_err(bs, error);
}
}
return action;
}

2
bsd-user/elfload.c
View File

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

4
bsd-user/main.c
View File

@ -31,8 +31,8 @@
/* For tb_lock */
#include "cpu.h"
#include "tcg.h"
#include "qemu-timer.h"
#include "envlist.h"
#include "qemu/timer.h"
#include "qemu/envlist.h"
#define DEBUG_LOGFILE "/tmp/qemu.log"

24
bsd-user/qemu-types.h
View File

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

6
bsd-user/qemu.h
View File

@ -11,7 +11,7 @@
#include <stdlib.h>
#endif /* DEBUG_REMAP */
#include "qemu-types.h"
#include "exec/user/abitypes.h"
enum BSDType {
target_freebsd,
@ -23,7 +23,7 @@ extern enum BSDType bsd_type;
#include "syscall_defs.h"
#include "syscall.h"
#include "target_signal.h"
#include "gdbstub.h"
#include "exec/gdbstub.h"
#if defined(CONFIG_USE_NPTL)
#define THREAD __thread
@ -146,7 +146,7 @@ int get_osversion(void);
void fork_start(void);
void fork_end(int child);
#include "qemu-log.h"
#include "qemu/log.h"
/* strace.c */
void

5
bt-host.c
View File

@ -18,9 +18,8 @@
*/
#include "qemu-common.h"
#include "qemu-char.h"
#include "net.h"
#include "bt-host.h"
#include "bt/bt.h"
#include "qemu/main-loop.h"
#ifndef _WIN32
# include <errno.h>

9
bt-host.h
View File

@ -1,9 +0,0 @@
#ifndef BT_HOST_H
#define BT_HOST_H
struct HCIInfo;
/* bt-host.c */
struct HCIInfo *bt_host_hci(const char *id);
#endif

4
bt-vhci.c
View File

@ -18,9 +18,9 @@
*/
#include "qemu-common.h"
#include "qemu-char.h"
#include "net.h"
#include "bt/bt.h"
#include "hw/bt.h"
#include "qemu/main-loop.h"
#define VHCI_DEV "/dev/vhci"
#define VHCI_UDEV "/dev/hci_vhci"

293
buffered_file.c
View File

@ -1,293 +0,0 @@
/*
* QEMU buffered QEMUFile
*
* 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 "hw/hw.h"
#include "qemu-timer.h"
#include "qemu-char.h"
#include "buffered_file.h"
//#define DEBUG_BUFFERED_FILE
typedef struct QEMUFileBuffered
{
BufferedPutFunc *put_buffer;
BufferedPutReadyFunc *put_ready;
BufferedWaitForUnfreezeFunc *wait_for_unfreeze;
BufferedCloseFunc *close;
void *opaque;
QEMUFile *file;
int freeze_output;
size_t bytes_xfer;
size_t xfer_limit;
uint8_t *buffer;
size_t buffer_size;
size_t buffer_capacity;
QEMUTimer *timer;
} QEMUFileBuffered;
#ifdef DEBUG_BUFFERED_FILE
#define DPRINTF(fmt, ...) \
do { printf("buffered-file: " fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
do { } while (0)
#endif
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;
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 void buffered_flush(QEMUFileBuffered *s)
{
size_t offset = 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 (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");
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;
}
}
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;
}
static int buffered_put_buffer(void *opaque, const uint8_t *buf, int64_t pos, int size)
{
QEMUFileBuffered *s = opaque;
int offset = 0, error;
ssize_t ret;
DPRINTF("putting %d bytes at %" PRId64 "\n", size, pos);
error = qemu_file_get_error(s->file);
if (error) {
DPRINTF("flush when error, bailing: %s\n", strerror(-error));
return error;
}
DPRINTF("unfreezing output\n");
s->freeze_output = 0;
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;
}
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->bytes_xfer <= s->xfer_limit) {
DPRINTF("notifying client\n");
s->put_ready(s->opaque);
}
}
return offset;
}
static int buffered_close(void *opaque)
{
QEMUFileBuffered *s = opaque;
int ret;
DPRINTF("closing\n");
while (!qemu_file_get_error(s->file) && s->buffer_size) {
buffered_flush(s);
if (s->freeze_output)
s->wait_for_unfreeze(s->opaque);
}
ret = s->close(s->opaque);
qemu_del_timer(s->timer);
qemu_free_timer(s->timer);
g_free(s->buffer);
g_free(s);
return ret;
}
/*
* The meaning of the return values is:
* 0: We can continue sending
* 1: Time to stop
* negative: There has been an error
*/
static int buffered_rate_limit(void *opaque)
{
QEMUFileBuffered *s = opaque;
int ret;
ret = qemu_file_get_error(s->file);
if (ret) {
return ret;
}
if (s->freeze_output)
return 1;
if (s->bytes_xfer > s->xfer_limit)
return 1;
return 0;
}
static int64_t buffered_set_rate_limit(void *opaque, int64_t new_rate)
{
QEMUFileBuffered *s = opaque;
if (qemu_file_get_error(s->file)) {
goto out;
}
if (new_rate > SIZE_MAX) {
new_rate = SIZE_MAX;
}
s->xfer_limit = new_rate / 10;
out:
return s->xfer_limit;
}
static int64_t buffered_get_rate_limit(void *opaque)
{
QEMUFileBuffered *s = opaque;
return s->xfer_limit;
}
static void buffered_rate_tick(void *opaque)
{
QEMUFileBuffered *s = opaque;
if (qemu_file_get_error(s->file)) {
buffered_close(s);
return;
}
qemu_mod_timer(s->timer, qemu_get_clock_ms(rt_clock) + 100);
if (s->freeze_output)
return;
s->bytes_xfer = 0;
buffered_flush(s);
/* Add some checks around this */
s->put_ready(s->opaque);
}
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->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_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);
qemu_mod_timer(s->timer, qemu_get_clock_ms(rt_clock) + 100);
return s->file;
}

30
buffered_file.h
View File

@ -1,30 +0,0 @@
/*
* QEMU buffered QEMUFile
*
* 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.
*
*/
#ifndef QEMU_BUFFERED_FILE_H
#define QEMU_BUFFERED_FILE_H
#include "hw/hw.h"
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

2
cache-utils.c
View File

@ -1,4 +1,4 @@
#include "cache-utils.h"
#include "qemu/cache-utils.h"
#if defined(_ARCH_PPC)
struct qemu_cache_conf qemu_cache_conf = {

4
cmd.c
View File

@ -24,8 +24,8 @@
#include <getopt.h>
#include "cmd.h"
#include "qemu-aio.h"
#include "main-loop.h"
#include "block/aio.h"
#include "qemu/main-loop.h"
#define _(x) x /* not gettext support yet */

2
compatfd.c
View File

@ -14,7 +14,7 @@
*/
#include "qemu-common.h"
#include "compatfd.h"
#include "qemu/compatfd.h"
#include <sys/syscall.h>
#include <pthread.h>

636
configure vendored
View File

File diff suppressed because it is too large Load Diff

2
coroutine-gthread.c
View File

@ -20,7 +20,7 @@
#include <glib.h>
#include "qemu-common.h"
#include "qemu-coroutine-int.h"
#include "block/coroutine_int.h"
typedef struct {
Coroutine base;

6
coroutine-sigaltstack.c
View File

@ -31,7 +31,7 @@
#include <pthread.h>
#include <signal.h>
#include "qemu-common.h"
#include "qemu-coroutine-int.h"
#include "block/coroutine_int.h"
enum {
/* Maximum free pool size prevents holding too many freed coroutines */
@ -171,8 +171,8 @@ static Coroutine *coroutine_new(void)
CoroutineThreadState *coTS;
struct sigaction sa;
struct sigaction osa;
struct sigaltstack ss;
struct sigaltstack oss;
stack_t ss;
stack_t oss;
sigset_t sigs;
sigset_t osigs;
jmp_buf old_env;

2
coroutine-ucontext.c
View File

@ -28,7 +28,7 @@
#include <pthread.h>
#include <ucontext.h>
#include "qemu-common.h"
#include "qemu-coroutine-int.h"
#include "block/coroutine_int.h"
#ifdef CONFIG_VALGRIND_H
#include <valgrind/valgrind.h>

Some files were not shown because too many files have changed in this diff Show More