dictzip: Fix on big endian systems

The dictzip code in SLE11 received some treatment over time to support
running on big endian hosts. Somewhere in the transition to SLE12 this
support got lost. Add it back in again from the SLE11 code base.

Furthermore while at it, fix up the debug prints to not emit warnings.

[AG: BSC#937572]
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Andreas Färber <afaerber@suse.de>

.gdbinit

@@ -1,8 +0,0 @@
-# GDB may have ./.gdbinit loading disabled by default.  In that case you can
-# follow the instructions it prints.  They boil down to adding the following to
-# your home directory's ~/.gdbinit file:
-#
-#   add-auto-load-safe-path /path/to/qemu/.gdbinit
-
-# Load QEMU-specific sub-commands and settings
-source scripts/qemu-gdb.py

.gitignore

@@ -5,13 +5,18 @@
 /config-target.*
 /config.status
 /config-temp
-/trace-events-all
+/trace/generated-tracers.h
+/trace/generated-tracers.c
+/trace/generated-tracers-dtrace.h
+/trace/generated-tracers.dtrace
 /trace/generated-events.h
 /trace/generated-events.c
 /trace/generated-helpers-wrappers.h
 /trace/generated-helpers.h
 /trace/generated-helpers.c
 /trace/generated-tcg-tracers.h
+/trace/generated-ust-provider.h
+/trace/generated-ust.c
 /ui/shader/texture-blit-frag.h
 /ui/shader/texture-blit-vert.h
 *-timestamp
@@ -33,8 +38,9 @@
 /qmp-introspect.[ch]
 /qmp-marshal.c
 /qemu-doc.html
+/qemu-tech.html
 /qemu-doc.info
-/qemu-doc.txt
+/qemu-tech.info
 /qemu-img
 /qemu-nbd
 /qemu-options.def
@@ -46,16 +52,14 @@
 /qemu-bridge-helper
 /qemu-monitor.texi
 /qemu-monitor-info.texi
-/qemu-version.h
-/qemu-version.h.tmp
-/module_block.h
+/qmp-commands.txt
 /vscclient
-/vhost-user-scsi
 /fsdev/virtfs-proxy-helper
 *.[1-9]
 *.a
 *.aux
 *.cp
+*.dvi
 *.exe
 *.msi
 *.dll
@@ -77,6 +81,10 @@
 *.d
 !/scripts/qemu-guest-agent/fsfreeze-hook.d
 *.o
+*.lo
+*.la
+*.pc
+.libs
 .sdk
 *.gcda
 *.gcno
@@ -86,10 +94,6 @@
 /pc-bios/optionrom/linuxboot.bin
 /pc-bios/optionrom/linuxboot.raw
 /pc-bios/optionrom/linuxboot.img
-/pc-bios/optionrom/linuxboot_dma.asm
-/pc-bios/optionrom/linuxboot_dma.bin
-/pc-bios/optionrom/linuxboot_dma.raw
-/pc-bios/optionrom/linuxboot_dma.img
 /pc-bios/optionrom/multiboot.asm
 /pc-bios/optionrom/multiboot.bin
 /pc-bios/optionrom/multiboot.raw
@@ -100,35 +104,8 @@
 /pc-bios/optionrom/kvmvapic.img
 /pc-bios/s390-ccw/s390-ccw.elf
 /pc-bios/s390-ccw/s390-ccw.img
-/docs/interop/qemu-ga-qapi.texi
-/docs/interop/qemu-ga-ref.html
-/docs/interop/qemu-ga-ref.info*
-/docs/interop/qemu-ga-ref.txt
-/docs/interop/qemu-qmp-qapi.texi
-/docs/interop/qemu-qmp-ref.html
-/docs/interop/qemu-qmp-ref.info*
-/docs/interop/qemu-qmp-ref.txt
-/docs/version.texi
-*.tps
 .stgit-*
 cscope.*
 tags
 TAGS
-docker-src.*
 *~
-trace.h
-trace.c
-trace-ust.h
-trace-ust.h
-trace-dtrace.h
-trace-dtrace.dtrace
-trace-root.h
-trace-root.c
-trace-ust-root.h
-trace-ust-root.h
-trace-ust-all.h
-trace-ust-all.c
-trace-dtrace-root.h
-trace-dtrace-root.dtrace
-trace-ust-all.h
-trace-ust-all.c

.gitmodules

@@ -31,9 +31,3 @@
 [submodule "roms/u-boot"]
 	path = roms/u-boot
 	url = git://git.qemu-project.org/u-boot.git
-[submodule "roms/skiboot"]
-	path = roms/skiboot
-	url = git://git.qemu.org/skiboot.git
-[submodule "roms/QemuMacDrivers"]
-	path = roms/QemuMacDrivers
-	url = git://git.qemu.org/QemuMacDrivers.git

.shippable.yml

@@ -1,36 +0,0 @@
-language: c
-git:
-   submodules: false
-env:
-  global:
-    - LC_ALL=C
-  matrix:
-    - IMAGE=debian-armhf-cross
-      TARGET_LIST=arm-softmmu,arm-linux-user,armeb-linux-user
-    - IMAGE=debian-arm64-cross
-      TARGET_LIST=aarch64-softmmu,aarch64-linux-user
-    - IMAGE=debian-s390x-cross
-      TARGET_LIST=s390x-softmmu,s390x-linux-user
-    # mips64el-softmmu disabled due to libfdt problem
-    - IMAGE=debian-mipsel-cross
-      TARGET_LIST=mipsel-softmmu,mipsel-linux-user,mips64el-linux-user
-build:
-  pre_ci:
-    - make docker-image-${IMAGE} V=1
-  pre_ci_boot:
-    image_name: qemu
-    image_tag: ${IMAGE}
-    pull: false
-    options: "-e HOME=/root"
-  ci:
-    - unset CC
-    # some targets require newer up to date packages, for example TARGET_LIST matching
-    # aarch64*-softmmu|arm*-softmmu|ppc*-softmmu|microblaze*-softmmu|mips64el-softmmu)
-    # see the configure script:
-    #    error_exit "DTC (libfdt) version >= 1.4.2 not present. Your options:"
-    #    "  (1) Preferred: Install the DTC (libfdt) devel package"
-    #    "  (2) Fetch the DTC submodule, using:"
-    #    "      git submodule update --init dtc"
-    - dpkg --compare-versions `dpkg-query --showformat='${Version}' --show libfdt-dev` ge 1.4.2 || git submodule update --init dtc
-    - ./configure ${QEMU_CONFIGURE_OPTS} --target-list=${TARGET_LIST}
-    - make -j$(($(getconf _NPROCESSORS_ONLN) + 1))

.travis.yml

@@ -1,194 +1,95 @@
-sudo: false
 language: c
 python:
   - "2.4"
 compiler:
   - gcc
-cache: ccache
-addons:
-  apt:
-    packages:
-      # Build dependencies
-      - libaio-dev
-      - libattr1-dev
-      - libbrlapi-dev
-      - libcap-ng-dev
-      - libgnutls-dev
-      - libgtk-3-dev
-      - libiscsi-dev
-      - liblttng-ust-dev
-      - libnfs-dev
-      - libncurses5-dev
-      - libnss3-dev
-      - libpixman-1-dev
-      - libpng12-dev
-      - librados-dev
-      - libsdl1.2-dev
-      - libseccomp-dev
-      - libspice-protocol-dev
-      - libspice-server-dev
-      - libssh2-1-dev
-      - liburcu-dev
-      - libusb-1.0-0-dev
-      - libvte-2.90-dev
-      - sparse
-      - uuid-dev
-
-# The channel name "irc.oftc.net#qemu" is encrypted against qemu/qemu
-# to prevent IRC notifications from forks. This was created using:
-# $ travis encrypt -r "qemu/qemu" "irc.oftc.net#qemu"
+  - clang
 notifications:
   irc:
     channels:
-      - secure: "F7GDRgjuOo5IUyRLqSkmDL7kvdU4UcH3Lm/W2db2JnDHTGCqgEdaYEYKciyCLZ57vOTsTsOgesN8iUT7hNHBd1KWKjZe9KDTZWppWRYVwAwQMzVeSOsbbU4tRoJ6Pp+3qhH1Z0eGYR9ZgKYAoTumDFgSAYRp4IscKS8jkoedOqM="
+      - "irc.oftc.net#qemu"
     on_success: change
     on_failure: always
 env:
   global:
-    - TEST_CMD="make check"
+    - TEST_CMD=""
+    - EXTRA_CONFIG=""
+    # Development packages, EXTRA_PKGS saved for additional builds
+    - CORE_PKGS="libusb-1.0-0-dev libiscsi-dev librados-dev libncurses5-dev"
+    - NET_PKGS="libseccomp-dev libgnutls-dev libssh2-1-dev  libspice-server-dev libspice-protocol-dev libnss3-dev"
+    - GUI_PKGS="libgtk-3-dev libvte-2.90-dev libsdl1.2-dev libpng12-dev libpixman-1-dev"
+    - EXTRA_PKGS=""
   matrix:
-    - CONFIG=""
-    - CONFIG="--enable-debug --enable-debug-tcg --enable-trace-backends=log"
-    - CONFIG="--disable-linux-aio --disable-cap-ng --disable-attr --disable-brlapi --disable-uuid --disable-libusb"
-    - CONFIG="--enable-modules"
-    - CONFIG="--with-coroutine=ucontext"
-    - CONFIG="--with-coroutine=sigaltstack"
+    # Group major targets together with their linux-user counterparts
+    - TARGETS=alpha-softmmu,alpha-linux-user
+    - TARGETS=arm-softmmu,arm-linux-user,armeb-linux-user,aarch64-softmmu,aarch64-linux-user
+    - TARGETS=cris-softmmu,cris-linux-user
+    - TARGETS=i386-softmmu,i386-linux-user,x86_64-softmmu,x86_64-linux-user
+    - TARGETS=m68k-softmmu,m68k-linux-user
+    - TARGETS=microblaze-softmmu,microblazeel-softmmu,microblaze-linux-user,microblazeel-linux-user
+    - TARGETS=mips-softmmu,mips64-softmmu,mips64el-softmmu,mipsel-softmmu
+    - TARGETS=mips-linux-user,mips64-linux-user,mips64el-linux-user,mipsel-linux-user,mipsn32-linux-user,mipsn32el-linux-user
+    - TARGETS=or32-softmmu,or32-linux-user
+    - TARGETS=ppc-softmmu,ppc64-softmmu,ppcemb-softmmu,ppc-linux-user,ppc64-linux-user,ppc64abi32-linux-user,ppc64le-linux-user
+    - TARGETS=s390x-softmmu,s390x-linux-user
+    - TARGETS=sh4-softmmu,sh4eb-softmmu,sh4-linux-user sh4eb-linux-user
+    - TARGETS=sparc-softmmu,sparc64-softmmu,sparc-linux-user,sparc32plus-linux-user,sparc64-linux-user
+    - TARGETS=unicore32-softmmu,unicore32-linux-user
+    # Group remaining softmmu only targets into one build
+    - TARGETS=lm32-softmmu,moxie-softmmu,tricore-softmmu,xtensa-softmmu,xtensaeb-softmmu
 git:
   # we want to do this ourselves
   submodules: false
 before_install:
-  - if [ "$TRAVIS_OS_NAME" == "osx" ]; then brew update ; fi
-  - if [ "$TRAVIS_OS_NAME" == "osx" ]; then brew install libffi gettext glib pixman ; fi
   - wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
   - git submodule update --init --recursive
+  - sudo apt-get update -qq
+  - sudo apt-get install -qq ${CORE_PKGS} ${NET_PKGS} ${GUI_PKGS} ${EXTRA_PKGS}
 before_script:
-  - ./configure ${CONFIG}
+  - ./configure --target-list=${TARGETS} --enable-debug-tcg ${EXTRA_CONFIG}
 script:
-  - make -j3 && ${TEST_CMD}
+  - make -j2 && ${TEST_CMD}
 matrix:
+  # We manually include a number of additional build for non-standard bits
   include:
-    # Test with CLang for compile portability
-    - env: CONFIG=""
-      compiler: clang
-    # gprof/gcov are GCC features
-    - env: CONFIG="--enable-gprof --enable-gcov --disable-pie"
+    # Make check target (we only do this once)
+    - env:
+        - TARGETS=alpha-softmmu,arm-softmmu,aarch64-softmmu,cris-softmmu,i386-softmmu,x86_64-softmmu,m68k-softmmu,microblaze-softmmu,microblazeel-softmmu,mips-softmmu,mips64-softmmu,mips64el-softmmu,mipsel-softmmu,or32-softmmu,ppc-softmmu,ppc64-softmmu,ppcemb-softmmu,s390x-softmmu,sh4-softmmu,sh4eb-softmmu,sparc-softmmu,sparc64-softmmu,unicore32-softmmu,unicore32-linux-user,lm32-softmmu,moxie-softmmu,tricore-softmmu,xtensa-softmmu,xtensaeb-softmmu
+          TEST_CMD="make check"
       compiler: gcc
-    # We manually include builds which we disable "make check" for
-    - env: CONFIG="--enable-debug --enable-tcg-interpreter"
-           TEST_CMD=""
+    # Debug related options
+    - env: TARGETS=i386-softmmu,x86_64-softmmu
+           EXTRA_CONFIG="--enable-debug"
       compiler: gcc
-    - env: CONFIG="--enable-trace-backends=simple"
-           TEST_CMD=""
+    - env: TARGETS=i386-softmmu,x86_64-softmmu
+           EXTRA_CONFIG="--enable-debug --enable-tcg-interpreter"
       compiler: gcc
-    - env: CONFIG="--enable-trace-backends=ftrace"
-           TEST_CMD=""
+    # All the extra -dev packages
+    - env: TARGETS=i386-softmmu,x86_64-softmmu
+           EXTRA_PKGS="libaio-dev libcap-ng-dev libattr1-dev libbrlapi-dev uuid-dev libusb-1.0.0-dev"
       compiler: gcc
-    - env: CONFIG="--enable-trace-backends=ust"
-           TEST_CMD=""
+    # Currently configure doesn't force --disable-pie
+    - env: TARGETS=i386-softmmu,x86_64-softmmu
+           EXTRA_CONFIG="--enable-gprof --enable-gcov --disable-pie"
       compiler: gcc
-    - env: CONFIG=""
-      os: osx
-      compiler: clang
-    # Plain Trusty System Build
-    - env: CONFIG="--disable-linux-user"
-      sudo: required
-      addons:
-      dist: trusty
+    - env: TARGETS=i386-softmmu,x86_64-softmmu
+           EXTRA_PKGS="sparse"
+           EXTRA_CONFIG="--enable-sparse"
       compiler: gcc
-      before_install:
-        - sudo apt-get update -qq
-        - sudo apt-get build-dep -qq qemu
-        - wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
-        - git submodule update --init --recursive
-    # Plain Trusty Linux User Build
-    - env: CONFIG="--disable-system"
-      sudo: required
-      addons:
-      dist: trusty
+    # All the trace backends (apart from dtrace)
+    - env: TARGETS=i386-softmmu,x86_64-softmmu
+           EXTRA_CONFIG="--enable-trace-backends=stderr"
+      compiler: gcc
+    - env: TARGETS=i386-softmmu,x86_64-softmmu
+           EXTRA_CONFIG="--enable-trace-backends=simple"
+      compiler: gcc
+    - env: TARGETS=i386-softmmu,x86_64-softmmu
+           EXTRA_CONFIG="--enable-trace-backends=ftrace"
+      compiler: gcc
+    - env: TARGETS=i386-softmmu,x86_64-softmmu
+          EXTRA_PKGS="liblttng-ust-dev liburcu-dev"
+          EXTRA_CONFIG="--enable-trace-backends=ust"
+      compiler: gcc
+    - env: TARGETS=i386-softmmu,x86_64-softmmu
+           EXTRA_CONFIG="--enable-modules"
       compiler: gcc
-      before_install:
-        - sudo apt-get update -qq
-        - sudo apt-get build-dep -qq qemu
-        - wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
-        - git submodule update --init --recursive
-    # Trusty System build with latest stable clang
-    - sudo: required
-      addons:
-      dist: trusty
-      language: generic
-      compiler: none
-      env:
-        - COMPILER_NAME=clang CXX=clang++-3.9 CC=clang-3.9
-        - CONFIG="--disable-linux-user --cc=clang-3.9 --cxx=clang++-3.9"
-      before_install:
-        - wget -nv -O - http://llvm.org/apt/llvm-snapshot.gpg.key | sudo apt-key add -
-        - sudo apt-add-repository -y 'deb http://llvm.org/apt/trusty llvm-toolchain-trusty-3.9 main'
-        - sudo apt-get update -qq
-        - sudo apt-get install -qq -y clang-3.9
-        - sudo apt-get build-dep -qq qemu
-        - wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
-        - git submodule update --init --recursive
-      before_script:
-        - ./configure ${CONFIG} || cat config.log
-    # Trusty Linux User build with latest stable clang
-    - sudo: required
-      addons:
-      dist: trusty
-      language: generic
-      compiler: none
-      env:
-        - COMPILER_NAME=clang CXX=clang++-3.9 CC=clang-3.9
-        - CONFIG="--disable-system --cc=clang-3.9 --cxx=clang++-3.9"
-      before_install:
-        - wget -nv -O - http://llvm.org/apt/llvm-snapshot.gpg.key | sudo apt-key add -
-        - sudo apt-add-repository -y 'deb http://llvm.org/apt/trusty llvm-toolchain-trusty-3.9 main'
-        - sudo apt-get update -qq
-        - sudo apt-get install -qq -y clang-3.9
-        - sudo apt-get build-dep -qq qemu
-        - wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
-        - git submodule update --init --recursive
-      before_script:
-        - ./configure ${CONFIG} || cat config.log
-    # Using newer GCC with sanitizers
-    - addons:
-        apt:
-          sources:
-            # PPAs for newer toolchains
-            - ubuntu-toolchain-r-test
-          packages:
-            # Extra toolchains
-            - gcc-5
-            - g++-5
-            # Build dependencies
-            - libaio-dev
-            - libattr1-dev
-            - libbrlapi-dev
-            - libcap-ng-dev
-            - libgnutls-dev
-            - libgtk-3-dev
-            - libiscsi-dev
-            - liblttng-ust-dev
-            - libnfs-dev
-            - libncurses5-dev
-            - libnss3-dev
-            - libpixman-1-dev
-            - libpng12-dev
-            - librados-dev
-            - libsdl1.2-dev
-            - libseccomp-dev
-            - libspice-protocol-dev
-            - libspice-server-dev
-            - libssh2-1-dev
-            - liburcu-dev
-            - libusb-1.0-0-dev
-            - libvte-2.90-dev
-            - sparse
-            - uuid-dev
-      language: generic
-      compiler: none
-      env:
-        - COMPILER_NAME=gcc CXX=g++-5 CC=gcc-5
-        - CONFIG="--cc=gcc-5 --cxx=g++-5 --disable-pie --disable-linux-user"
-        - TEST_CMD=""
-      before_script:
-        - ./configure ${CONFIG} --extra-cflags="-g3 -O0 -fsanitize=thread -fuse-ld=gold" || cat config.log

CODING_STYLE

@@ -9,7 +9,7 @@ patches before submitting.
 Of course, the most important aspect in any coding style is whitespace.
 Crusty old coders who have trouble spotting the glasses on their noses
 can tell the difference between a tab and eight spaces from a distance
-of approximately fifteen parsecs.  Many a flamewar has been fought and
+of approximately fifteen parsecs.  Many a flamewar have been fought and
 lost on this issue.
 
 QEMU indents are four spaces.  Tabs are never used, except in Makefiles
@@ -31,11 +31,7 @@ Do not leave whitespace dangling off the ends of lines.
 
 2. Line width
 
-Lines should be 80 characters; try not to make them longer.
-
-Sometimes it is hard to do, especially when dealing with QEMU subsystems
-that use long function or symbol names.  Even in that case, do not make
-lines much longer than 80 characters.
+Lines are 80 characters; not longer.
 
 Rationale:
  - Some people like to tile their 24" screens with a 6x4 matrix of 80x24
@@ -43,8 +39,6 @@ Rationale:
    let them keep doing it.
  - Code and especially patches is much more readable if limited to a sane
    line length.  Eighty is traditional.
- - The four-space indentation makes the most common excuse ("But look
-   at all that white space on the left!") moot.
  - It is the QEMU coding style.
 
 3. Naming
@@ -116,10 +110,3 @@ if (a == 1) {
 Rationale: Yoda conditions (as in 'if (1 == a)') are awkward to read.
 Besides, good compilers already warn users when '==' is mis-typed as '=',
 even when the constant is on the right.
-
-7. Comment style
-
-We use traditional C-style /* */ comments and avoid // comments.
-
-Rationale: The // form is valid in C99, so this is purely a matter of
-consistency of style. The checkpatch script will warn you about this.

HACKING

@@ -1,28 +1,10 @@
 1. Preprocessor
 
-1.1. Variadic macros
-
 For variadic macros, stick with this C99-like syntax:
 
 #define DPRINTF(fmt, ...)                                       \
     do { printf("IRQ: " fmt, ## __VA_ARGS__); } while (0)
 
-1.2. Include directives
-
-Order include directives as follows:
-
-#include "qemu/osdep.h"  /* Always first... */
-#include <...>           /* then system headers... */
-#include "..."           /* and finally QEMU headers. */
-
-The "qemu/osdep.h" header contains preprocessor macros that affect the behavior
-of core system headers like <stdint.h>.  It must be the first include so that
-core system headers included by external libraries get the preprocessor macros
-that QEMU depends on.
-
-Do not include "qemu/osdep.h" from header files since the .c file will have
-already included it.
-
 2. C types
 
 It should be common sense to use the right type, but we have collected
@@ -175,62 +157,3 @@ 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)
-
-In addition, QEMU assumes that the compiler does not use the latitude
-given in C99 and C11 to treat aspects of signed '<<' as undefined, as
-documented in the GNU Compiler Collection manual starting at version 4.0.
-
-7. Error handling and reporting
-
-7.1 Reporting errors to the human user
-
-Do not use printf(), fprintf() or monitor_printf().  Instead, use
-error_report() or error_vreport() from error-report.h.  This ensures the
-error is reported in the right place (current monitor or stderr), and in
-a uniform format.
-
-Use error_printf() & friends to print additional information.
-
-error_report() prints the current location.  In certain common cases
-like command line parsing, the current location is tracked
-automatically.  To manipulate it manually, use the loc_*() from
-error-report.h.
-
-7.2 Propagating errors
-
-An error can't always be reported to the user right where it's detected,
-but often needs to be propagated up the call chain to a place that can
-handle it.  This can be done in various ways.
-
-The most flexible one is Error objects.  See error.h for usage
-information.
-
-Use the simplest suitable method to communicate success / failure to
-callers.  Stick to common methods: non-negative on success / -1 on
-error, non-negative / -errno, non-null / null, or Error objects.
-
-Example: when a function returns a non-null pointer on success, and it
-can fail only in one way (as far as the caller is concerned), returning
-null on failure is just fine, and certainly simpler and a lot easier on
-the eyes than propagating an Error object through an Error ** parameter.
-
-Example: when a function's callers need to report details on failure
-only the function really knows, use Error **, and set suitable errors.
-
-Do not report an error to the user when you're also returning an error
-for somebody else to handle.  Leave the reporting to the place that
-consumes the error returned.
-
-7.3 Handling errors
-
-Calling exit() is fine when handling configuration errors during
-startup.  It's problematic during normal operation.  In particular,
-monitor commands should never exit().
-
-Do not call exit() or abort() to handle an error that can be triggered
-by the guest (e.g., some unimplemented corner case in guest code
-translation or device emulation).  Guests should not be able to
-terminate QEMU.
-
-Note that &error_fatal is just another way to exit(1), and &error_abort
-is just another way to abort().

Makefile

@@ -6,7 +6,7 @@ BUILD_DIR=$(CURDIR)
 # Before including a proper config-host.mak, assume we are in the source tree
 SRC_PATH=.
 
-UNCHECKED_GOALS := %clean TAGS cscope ctags docker docker-%
+UNCHECKED_GOALS := %clean TAGS cscope ctags
 
 # All following code might depend on configuration variables
 ifneq ($(wildcard config-host.mak),)
@@ -26,12 +26,12 @@ endif
 
 CONFIG_SOFTMMU := $(if $(filter %-softmmu,$(TARGET_DIRS)),y)
 CONFIG_USER_ONLY := $(if $(filter %-user,$(TARGET_DIRS)),y)
-CONFIG_XEN := $(CONFIG_XEN_BACKEND)
 CONFIG_ALL=y
 -include config-all-devices.mak
 -include config-all-disas.mak
 
-config-host.mak: $(SRC_PATH)/configure $(SRC_PATH)/pc-bios
+include $(SRC_PATH)/rules.mak
+config-host.mak: $(SRC_PATH)/configure
 	@echo $@ is out-of-date, running configure
 	@# TODO: The next lines include code which supports a smooth
 	@# transition from old configurations without config.status.
@@ -49,155 +49,39 @@ ifneq ($(filter-out $(UNCHECKED_GOALS),$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fa
 endif
 endif
 
-include $(SRC_PATH)/rules.mak
+GENERATED_HEADERS = config-host.h qemu-options.def
+GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h qapi-event.h
+GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c qapi-event.c
+GENERATED_HEADERS += qmp-introspect.h
+GENERATED_SOURCES += qmp-introspect.c
 
-GENERATED_FILES = qemu-version.h config-host.h qemu-options.def
-GENERATED_FILES += qmp-commands.h qapi-types.h qapi-visit.h qapi-event.h
-GENERATED_FILES += qmp-marshal.c qapi-types.c qapi-visit.c qapi-event.c
-GENERATED_FILES += qmp-introspect.h
-GENERATED_FILES += qmp-introspect.c
+GENERATED_HEADERS += trace/generated-events.h
+GENERATED_SOURCES += trace/generated-events.c
 
-GENERATED_FILES += trace/generated-tcg-tracers.h
-
-GENERATED_FILES += trace/generated-helpers-wrappers.h
-GENERATED_FILES += trace/generated-helpers.h
-GENERATED_FILES += trace/generated-helpers.c
-
-ifdef CONFIG_TRACE_UST
-GENERATED_FILES += trace-ust-all.h
-GENERATED_FILES += trace-ust-all.c
+GENERATED_HEADERS += trace/generated-tracers.h
+ifeq ($(findstring dtrace,$(TRACE_BACKENDS)),dtrace)
+GENERATED_HEADERS += trace/generated-tracers-dtrace.h
 endif
+GENERATED_SOURCES += trace/generated-tracers.c
 
-GENERATED_FILES += module_block.h
+GENERATED_HEADERS += trace/generated-tcg-tracers.h
 
-TRACE_HEADERS = trace-root.h $(trace-events-subdirs:%=%/trace.h)
-TRACE_SOURCES = trace-root.c $(trace-events-subdirs:%=%/trace.c)
-TRACE_DTRACE =
-ifdef CONFIG_TRACE_DTRACE
-TRACE_HEADERS += trace-dtrace-root.h $(trace-events-subdirs:%=%/trace-dtrace.h)
-TRACE_DTRACE += trace-dtrace-root.dtrace $(trace-events-subdirs:%=%/trace-dtrace.dtrace)
+GENERATED_HEADERS += trace/generated-helpers-wrappers.h
+GENERATED_HEADERS += trace/generated-helpers.h
+GENERATED_SOURCES += trace/generated-helpers.c
+
+ifeq ($(findstring ust,$(TRACE_BACKENDS)),ust)
+GENERATED_HEADERS += trace/generated-ust-provider.h
+GENERATED_SOURCES += trace/generated-ust.c
 endif
-ifdef CONFIG_TRACE_UST
-TRACE_HEADERS += trace-ust-root.h $(trace-events-subdirs:%=%/trace-ust.h)
-endif
-
-GENERATED_FILES += $(TRACE_HEADERS)
-GENERATED_FILES += $(TRACE_SOURCES)
-GENERATED_FILES += $(BUILD_DIR)/trace-events-all
-
-trace-group-name = $(shell dirname $1 | sed -e 's/[^a-zA-Z0-9]/_/g')
-
-tracetool-y = $(SRC_PATH)/scripts/tracetool.py
-tracetool-y += $(shell find $(SRC_PATH)/scripts/tracetool -name "*.py")
-
-%/trace.h: %/trace.h-timestamp
-	@cmp $< $@ >/dev/null 2>&1 || cp $< $@
-%/trace.h-timestamp: $(SRC_PATH)/%/trace-events $(tracetool-y)
-	$(call quiet-command,$(TRACETOOL) \
-		--group=$(call trace-group-name,$@) \
-		--format=h \
-		--backends=$(TRACE_BACKENDS) \
-		$< > $@,"GEN","$(@:%-timestamp=%)")
-
-%/trace.c: %/trace.c-timestamp
-	@cmp $< $@ >/dev/null 2>&1 || cp $< $@
-%/trace.c-timestamp: $(SRC_PATH)/%/trace-events $(tracetool-y)
-	$(call quiet-command,$(TRACETOOL) \
-		--group=$(call trace-group-name,$@) \
-		--format=c \
-		--backends=$(TRACE_BACKENDS) \
-		$< > $@,"GEN","$(@:%-timestamp=%)")
-
-%/trace-ust.h: %/trace-ust.h-timestamp
-	@cmp $< $@ >/dev/null 2>&1 || cp $< $@
-%/trace-ust.h-timestamp: $(SRC_PATH)/%/trace-events $(tracetool-y)
-	$(call quiet-command,$(TRACETOOL) \
-		--group=$(call trace-group-name,$@) \
-		--format=ust-events-h \
-		--backends=$(TRACE_BACKENDS) \
-		$< > $@,"GEN","$(@:%-timestamp=%)")
-
-%/trace-dtrace.dtrace: %/trace-dtrace.dtrace-timestamp
-	@cmp $< $@ >/dev/null 2>&1 || cp $< $@
-%/trace-dtrace.dtrace-timestamp: $(SRC_PATH)/%/trace-events $(BUILD_DIR)/config-host.mak $(tracetool-y)
-	$(call quiet-command,$(TRACETOOL) \
-		--group=$(call trace-group-name,$@) \
-		--format=d \
-		--backends=$(TRACE_BACKENDS) \
-		$< > $@,"GEN","$(@:%-timestamp=%)")
-
-%/trace-dtrace.h: %/trace-dtrace.dtrace $(tracetool-y)
-	$(call quiet-command,dtrace -o $@ -h -s $<, "GEN","$@")
-
-%/trace-dtrace.o: %/trace-dtrace.dtrace $(tracetool-y)
-
-
-trace-root.h: trace-root.h-timestamp
-	@cmp $< $@ >/dev/null 2>&1 || cp $< $@
-trace-root.h-timestamp: $(SRC_PATH)/trace-events $(tracetool-y)
-	$(call quiet-command,$(TRACETOOL) \
-		--group=root \
-		--format=h \
-		--backends=$(TRACE_BACKENDS) \
-		$< > $@,"GEN","$(@:%-timestamp=%)")
-
-trace-root.c: trace-root.c-timestamp
-	@cmp $< $@ >/dev/null 2>&1 || cp $< $@
-trace-root.c-timestamp: $(SRC_PATH)/trace-events $(tracetool-y)
-	$(call quiet-command,$(TRACETOOL) \
-		--group=root \
-		--format=c \
-		--backends=$(TRACE_BACKENDS) \
-		$< > $@,"GEN","$(@:%-timestamp=%)")
-
-trace-ust-root.h: trace-ust-root.h-timestamp
-	@cmp $< $@ >/dev/null 2>&1 || cp $< $@
-trace-ust-root.h-timestamp: $(SRC_PATH)/trace-events $(tracetool-y)
-	$(call quiet-command,$(TRACETOOL) \
-		--group=root \
-		--format=ust-events-h \
-		--backends=$(TRACE_BACKENDS) \
-		$< > $@,"GEN","$(@:%-timestamp=%)")
-
-trace-ust-all.h: trace-ust-all.h-timestamp
-	@cmp $< $@ >/dev/null 2>&1 || cp $< $@
-trace-ust-all.h-timestamp: $(trace-events-files) $(tracetool-y)
-	$(call quiet-command,$(TRACETOOL) \
-		--group=all \
-		--format=ust-events-h \
-		--backends=$(TRACE_BACKENDS) \
-		$(trace-events-files) > $@,"GEN","$(@:%-timestamp=%)")
-
-trace-ust-all.c: trace-ust-all.c-timestamp
-	@cmp $< $@ >/dev/null 2>&1 || cp $< $@
-trace-ust-all.c-timestamp: $(trace-events-files) $(tracetool-y)
-	$(call quiet-command,$(TRACETOOL) \
-		--group=all \
-		--format=ust-events-c \
-		--backends=$(TRACE_BACKENDS) \
-		$(trace-events-files) > $@,"GEN","$(@:%-timestamp=%)")
-
-trace-dtrace-root.dtrace: trace-dtrace-root.dtrace-timestamp
-	@cmp $< $@ >/dev/null 2>&1 || cp $< $@
-trace-dtrace-root.dtrace-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak $(tracetool-y)
-	$(call quiet-command,$(TRACETOOL) \
-		--group=root \
-		--format=d \
-		--backends=$(TRACE_BACKENDS) \
-		$< > $@,"GEN","$(@:%-timestamp=%)")
-
-trace-dtrace-root.h: trace-dtrace-root.dtrace
-	$(call quiet-command,dtrace -o $@ -h -s $<, "GEN","$@")
-
-trace-dtrace-root.o: trace-dtrace-root.dtrace
 
 # Don't try to regenerate Makefile or configure
 # We don't generate any of them
 Makefile: ;
 configure: ;
 
-.PHONY: all clean cscope distclean html info install install-doc \
-	pdf txt recurse-all speed test dist msi FORCE
+.PHONY: all clean cscope distclean dvi html info install install-doc \
+	pdf recurse-all speed test dist msi
 
 $(call set-vpath, $(SRC_PATH))
 
@@ -206,9 +90,11 @@ LIBS+=-lz $(LIBS_TOOLS)
 HELPERS-$(CONFIG_LINUX) = qemu-bridge-helper$(EXESUF)
 
 ifdef BUILD_DOCS
-DOCS=qemu-doc.html qemu-doc.txt qemu.1 qemu-img.1 qemu-nbd.8 qemu-ga.8
-DOCS+=docs/interop/qemu-qmp-ref.html docs/interop/qemu-qmp-ref.txt docs/interop/qemu-qmp-ref.7
-DOCS+=docs/interop/qemu-ga-ref.html docs/interop/qemu-ga-ref.txt docs/interop/qemu-ga-ref.7
+DOCS=qemu-doc.html qemu-tech.html qemu.1 qemu-img.1 qemu-nbd.8 qemu-ga.8
+DOCS+=qmp-commands.txt
+ifdef CONFIG_LINUX
+DOCS+=kvm_stat.1
+endif
 ifdef CONFIG_VIRTFS
 DOCS+=fsdev/virtfs-proxy-helper.1
 endif
@@ -222,20 +108,20 @@ 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' > $@,"GEN","$@")
+	$(call quiet-command,echo '# no devices' > $@,"  GEN   $@")
 else
 config-all-devices.mak: $(SUBDIR_DEVICES_MAK)
 	$(call quiet-command, sed -n \
              's|^\([^=]*\)=\(.*\)$$|\1:=$$(findstring y,$$(\1)\2)|p' \
              $(SUBDIR_DEVICES_MAK) | sort -u > $@, \
-             "GEN","$@")
+             "  GEN   $@")
 endif
 
 -include $(SUBDIR_DEVICES_MAK_DEP)
 
-%/config-devices.mak: default-configs/%.mak $(SRC_PATH)/scripts/make_device_config.sh
+%/config-devices.mak: default-configs/%.mak
 	$(call quiet-command, \
-            $(SHELL) $(SRC_PATH)/scripts/make_device_config.sh $< $*-config-devices.mak.d $@ > $@.tmp,"GEN","$@.tmp")
+            $(SHELL) $(SRC_PATH)/scripts/make_device_config.sh $< $*-config-devices.mak.d $@ > $@.tmp, "  GEN   $@.tmp")
 	$(call quiet-command, if test -f $@; then \
 	  if cmp -s $@.old $@; then \
 	    mv $@.tmp $@; \
@@ -252,7 +138,7 @@ endif
 	 else \
 	  mv $@.tmp $@; \
 	  cp -p $@ $@.old; \
-	 fi,"GEN","$@");
+	 fi, "  GEN   $@");
 
 defconfig:
 	rm -f config-all-devices.mak $(SUBDIR_DEVICES_MAK)
@@ -263,65 +149,35 @@ endif
 
 dummy := $(call unnest-vars,, \
                 stub-obj-y \
-                chardev-obj-y \
                 util-obj-y \
                 qga-obj-y \
                 ivshmem-client-obj-y \
                 ivshmem-server-obj-y \
-                libvhost-user-obj-y \
-                vhost-user-scsi-obj-y \
                 qga-vss-dll-obj-y \
                 block-obj-y \
                 block-obj-m \
                 crypto-obj-y \
                 crypto-aes-obj-y \
                 qom-obj-y \
-                io-obj-y \
                 common-obj-y \
-                common-obj-m \
-                trace-obj-y)
+                common-obj-m)
 
 ifneq ($(wildcard config-host.mak),)
-include $(SRC_PATH)/tests/Makefile.include
+include $(SRC_PATH)/tests/Makefile
 endif
 
 all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all modules
 
-qemu-version.h: FORCE
-	$(call quiet-command, \
-		(cd $(SRC_PATH); \
-		printf '#define QEMU_PKGVERSION '; \
-		if test -n "$(PKGVERSION)"; then \
-			printf '"$(PKGVERSION)"\n'; \
-		else \
-			if test -d .git; then \
-				printf '" ('; \
-				git describe --match 'v*' 2>/dev/null | tr -d '\n'; \
-				if ! git diff-index --quiet HEAD &>/dev/null; then \
-					printf -- '-dirty'; \
-				fi; \
-				printf ')"\n'; \
-			else \
-				printf '""\n'; \
-			fi; \
-		fi) > $@.tmp)
-	$(call quiet-command, if ! cmp -s $@ $@.tmp; then \
-	  mv $@.tmp $@; \
-	 else \
-	  rm $@.tmp; \
-	 fi)
-
 config-host.h: config-host.h-timestamp
 config-host.h-timestamp: config-host.mak
-qemu-options.def: $(SRC_PATH)/qemu-options.hx $(SRC_PATH)/scripts/hxtool
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"GEN","$@")
+qemu-options.def: $(SRC_PATH)/qemu-options.hx
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $@")
 
 SUBDIR_RULES=$(patsubst %,subdir-%, $(TARGET_DIRS))
 SOFTMMU_SUBDIR_RULES=$(filter %-softmmu,$(SUBDIR_RULES))
 
 $(SOFTMMU_SUBDIR_RULES): $(block-obj-y)
 $(SOFTMMU_SUBDIR_RULES): $(crypto-obj-y)
-$(SOFTMMU_SUBDIR_RULES): $(io-obj-y)
 $(SOFTMMU_SUBDIR_RULES): config-all-devices.mak
 
 subdir-%:
@@ -346,46 +202,47 @@ subdir-dtc:dtc/libfdt dtc/tests
 dtc/%:
 	mkdir -p $@
 
-$(SUBDIR_RULES): libqemuutil.a libqemustub.a $(common-obj-y) $(chardev-obj-y) \
-	$(qom-obj-y) $(crypto-aes-obj-$(CONFIG_USER_ONLY))
+$(SUBDIR_RULES): libqemuutil.a libqemustub.a $(common-obj-y) $(qom-obj-y) $(crypto-aes-obj-$(CONFIG_USER_ONLY))
 
 ROMSUBDIR_RULES=$(patsubst %,romsubdir-%, $(ROMS))
-# Only keep -O and -g cflags
 romsubdir-%:
-	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C pc-bios/$* V="$(V)" TARGET_DIR="$*/" CFLAGS="$(filter -O% -g%,$(CFLAGS))",)
+	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C pc-bios/$* V="$(V)" TARGET_DIR="$*/",)
 
 ALL_SUBDIRS=$(TARGET_DIRS) $(patsubst %,pc-bios/%, $(ROMS))
 
 recurse-all: $(SUBDIR_RULES) $(ROMSUBDIR_RULES)
 
-$(BUILD_DIR)/version.o: $(SRC_PATH)/version.rc config-host.h
-	$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"RC","version.o")
+$(BUILD_DIR)/version.o: $(SRC_PATH)/version.rc config-host.h | $(BUILD_DIR)/version.lo
+	$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"  RC    version.o")
+$(BUILD_DIR)/version.lo: $(SRC_PATH)/version.rc config-host.h
+	$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"  RC    version.lo")
 
-Makefile: $(version-obj-y)
+Makefile: $(version-obj-y) $(version-lobj-y)
 
 ######################################################################
 # Build libraries
 
 libqemustub.a: $(stub-obj-y)
-libqemuutil.a: $(util-obj-y) $(trace-obj-y)
+libqemuutil.a: $(util-obj-y)
+
+block-modules = $(foreach o,$(block-obj-m),"$(basename $(subst /,-,$o))",) NULL
+util/module.o-cflags = -D'CONFIG_BLOCK_MODULES=$(block-modules)'
 
 ######################################################################
 
-COMMON_LDADDS = libqemuutil.a libqemustub.a
-
 qemu-img.o: qemu-img-cmds.h
 
-qemu-img$(EXESUF): qemu-img.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS)
-qemu-nbd$(EXESUF): qemu-nbd.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS)
-qemu-io$(EXESUF): qemu-io.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS)
+qemu-img$(EXESUF): qemu-img.o $(block-obj-y) $(crypto-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
+qemu-nbd$(EXESUF): qemu-nbd.o $(block-obj-y) $(crypto-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
+qemu-io$(EXESUF): qemu-io.o $(block-obj-y) $(crypto-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
 
-qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o $(COMMON_LDADDS)
+qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o
 
-fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/9p-marshal.o fsdev/9p-iov-marshal.o $(COMMON_LDADDS)
+fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/virtio-9p-marshal.o libqemuutil.a libqemustub.a
 fsdev/virtfs-proxy-helper$(EXESUF): LIBS += -lcap
 
-qemu-img-cmds.h: $(SRC_PATH)/qemu-img-cmds.hx $(SRC_PATH)/scripts/hxtool
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"GEN","$@")
+qemu-img-cmds.h: $(SRC_PATH)/qemu-img-cmds.hx
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $@")
 
 qemu-ga$(EXESUF): LIBS = $(LIBS_QGA)
 qemu-ga$(EXESUF): QEMU_CFLAGS += -I qga/qapi-generated
@@ -398,54 +255,52 @@ qga/qapi-generated/qga-qapi-types.c qga/qapi-generated/qga-qapi-types.h :\
 $(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py \
 		$(gen-out-type) -o qga/qapi-generated -p "qga-" $<, \
-		"GEN","$@")
+		"  GEN   $@")
 qga/qapi-generated/qga-qapi-visit.c qga/qapi-generated/qga-qapi-visit.h :\
 $(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py \
 		$(gen-out-type) -o qga/qapi-generated -p "qga-" $<, \
-		"GEN","$@")
+		"  GEN   $@")
 qga/qapi-generated/qga-qmp-commands.h qga/qapi-generated/qga-qmp-marshal.c :\
 $(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py \
 		$(gen-out-type) -o qga/qapi-generated -p "qga-" $<, \
-		"GEN","$@")
+		"  GEN   $@")
 
 qapi-modules = $(SRC_PATH)/qapi-schema.json $(SRC_PATH)/qapi/common.json \
                $(SRC_PATH)/qapi/block.json $(SRC_PATH)/qapi/block-core.json \
-               $(SRC_PATH)/qapi/event.json $(SRC_PATH)/qapi/introspect.json \
-               $(SRC_PATH)/qapi/crypto.json $(SRC_PATH)/qapi/rocker.json \
-               $(SRC_PATH)/qapi/trace.json
+               $(SRC_PATH)/qapi/event.json $(SRC_PATH)/qapi/introspect.json
 
 qapi-types.c qapi-types.h :\
 $(qapi-modules) $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py \
 		$(gen-out-type) -o "." -b $<, \
-		"GEN","$@")
+		"  GEN   $@")
 qapi-visit.c qapi-visit.h :\
 $(qapi-modules) $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py \
 		$(gen-out-type) -o "." -b $<, \
-		"GEN","$@")
+		"  GEN   $@")
 qapi-event.c qapi-event.h :\
 $(qapi-modules) $(SRC_PATH)/scripts/qapi-event.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-event.py \
 		$(gen-out-type) -o "." $<, \
-		"GEN","$@")
+		"  GEN   $@")
 qmp-commands.h qmp-marshal.c :\
 $(qapi-modules) $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py \
-		$(gen-out-type) -o "." $<, \
-		"GEN","$@")
+		$(gen-out-type) -o "." -m $<, \
+		"  GEN   $@")
 qmp-introspect.h qmp-introspect.c :\
 $(qapi-modules) $(SRC_PATH)/scripts/qapi-introspect.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-introspect.py \
 		$(gen-out-type) -o "." $<, \
-		"GEN","$@")
+		"  GEN   $@")
 
 QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
 $(qga-obj-y) qemu-ga.o: $(QGALIB_GEN)
 
-qemu-ga$(EXESUF): $(qga-obj-y) $(COMMON_LDADDS)
+qemu-ga$(EXESUF): $(qga-obj-y) libqemuutil.a libqemustub.a
 	$(call LINK, $^)
 
 ifdef QEMU_GA_MSI_ENABLED
@@ -459,7 +314,7 @@ $(QEMU_GA_MSI): config-host.mak
 
 $(QEMU_GA_MSI):  $(SRC_PATH)/qga/installer/qemu-ga.wxs
 	$(call quiet-command,QEMU_GA_VERSION="$(QEMU_GA_VERSION)" QEMU_GA_MANUFACTURER="$(QEMU_GA_MANUFACTURER)" QEMU_GA_DISTRO="$(QEMU_GA_DISTRO)" BUILD_DIR="$(BUILD_DIR)" \
-	wixl -o $@ $(QEMU_GA_MSI_ARCH) $(QEMU_GA_MSI_WITH_VSS) $(QEMU_GA_MSI_MINGW_DLL_PATH) $<,"WIXL","$@")
+	wixl -o $@ $(QEMU_GA_MSI_ARCH) $(QEMU_GA_MSI_WITH_VSS) $(QEMU_GA_MSI_MINGW_DLL_PATH) $<, "  WIXL  $@")
 else
 msi:
 	@echo "MSI build not configured or dependency resolution failed (reconfigure with --enable-guest-agent-msi option)"
@@ -470,39 +325,33 @@ ifneq ($(EXESUF),)
 qemu-ga: qemu-ga$(EXESUF) $(QGA_VSS_PROVIDER) $(QEMU_GA_MSI)
 endif
 
-ivshmem-client$(EXESUF): $(ivshmem-client-obj-y) $(COMMON_LDADDS)
+ivshmem-client$(EXESUF): $(ivshmem-client-obj-y)
 	$(call LINK, $^)
-ivshmem-server$(EXESUF): $(ivshmem-server-obj-y) $(COMMON_LDADDS)
+ivshmem-server$(EXESUF): $(ivshmem-server-obj-y) libqemuutil.a libqemustub.a
 	$(call LINK, $^)
-vhost-user-scsi$(EXESUF): $(vhost-user-scsi-obj-y)
-	$(call LINK, $^)
-
-module_block.h: $(SRC_PATH)/scripts/modules/module_block.py config-host.mak
-	$(call quiet-command,$(PYTHON) $< $@ \
-	$(addprefix $(SRC_PATH)/,$(patsubst %.mo,%.c,$(block-obj-m))), \
-	"GEN","$@")
 
 clean:
 # avoid old build problems by removing potentially incorrect old files
 	rm -f config.mak op-i386.h opc-i386.h gen-op-i386.h op-arm.h opc-arm.h gen-op-arm.h
 	rm -f qemu-options.def
 	rm -f *.msi
-	find . \( -name '*.so' -o -name '*.dll' -o -name '*.mo' -o -name '*.[oda]' \) -type f -exec rm {} +
+	find . \( -name '*.l[oa]' -o -name '*.so' -o -name '*.dll' -o -name '*.mo' -o -name '*.[oda]' \) -type f -exec rm {} +
 	rm -f $(filter-out %.tlb,$(TOOLS)) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
 	rm -f fsdev/*.pod
+	rm -rf .libs */.libs
 	rm -f qemu-img-cmds.h
 	rm -f ui/shader/*-vert.h ui/shader/*-frag.h
-	@# May not be present in GENERATED_FILES
+	@# May not be present in GENERATED_HEADERS
 	rm -f trace/generated-tracers-dtrace.dtrace*
 	rm -f trace/generated-tracers-dtrace.h*
-	rm -f $(foreach f,$(GENERATED_FILES),$(f) $(f)-timestamp)
+	rm -f $(foreach f,$(GENERATED_HEADERS),$(f) $(f)-timestamp)
+	rm -f $(foreach f,$(GENERATED_SOURCES),$(f) $(f)-timestamp)
 	rm -rf qapi-generated
 	rm -rf qga/qapi-generated
 	for d in $(ALL_SUBDIRS); do \
 	if test -d $$d; then $(MAKE) -C $$d $@ || exit 1; fi; \
 	rm -f $$d/qemu-options.def; \
         done
-	rm -f $(SUBDIR_DEVICES_MAK) config-all-devices.mak
 
 VERSION ?= $(shell cat VERSION)
 
@@ -516,18 +365,13 @@ distclean: clean
 	rm -f config-all-devices.mak config-all-disas.mak config.status
 	rm -f po/*.mo tests/qemu-iotests/common.env
 	rm -f roms/seabios/config.mak roms/vgabios/config.mak
-	rm -f qemu-doc.info qemu-doc.aux qemu-doc.cp qemu-doc.cps
+	rm -f qemu-doc.info qemu-doc.aux qemu-doc.cp qemu-doc.cps qemu-doc.dvi
 	rm -f qemu-doc.fn qemu-doc.fns qemu-doc.info qemu-doc.ky qemu-doc.kys
 	rm -f qemu-doc.log qemu-doc.pdf qemu-doc.pg qemu-doc.toc qemu-doc.tp
-	rm -f qemu-doc.vr qemu-doc.txt
+	rm -f qemu-doc.vr
 	rm -f config.log
 	rm -f linux-headers/asm
-	rm -f docs/version.texi
-	rm -f docs/interop/qemu-ga-qapi.texi docs/interop/qemu-qmp-qapi.texi
-	rm -f docs/interop/qemu-qmp-ref.7 docs/interop/qemu-ga-ref.7
-	rm -f docs/interop/qemu-qmp-ref.txt docs/interop/qemu-ga-ref.txt
-	rm -f docs/interop/qemu-qmp-ref.pdf docs/interop/qemu-ga-ref.pdf
-	rm -f docs/interop/qemu-qmp-ref.html docs/interop/qemu-ga-ref.html
+	rm -f qemu-tech.info qemu-tech.aux qemu-tech.cp qemu-tech.dvi qemu-tech.fn qemu-tech.info qemu-tech.ky qemu-tech.log qemu-tech.pdf qemu-tech.pg qemu-tech.toc qemu-tech.tp qemu-tech.vr
 	for d in $(TARGET_DIRS); do \
 	rm -rf $$d || exit 1 ; \
         done
@@ -543,36 +387,31 @@ bepo    cz
 ifdef INSTALL_BLOBS
 BLOBS=bios.bin bios-256k.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
 vgabios-stdvga.bin vgabios-vmware.bin vgabios-qxl.bin vgabios-virtio.bin \
-acpi-dsdt.aml \
+acpi-dsdt.aml q35-acpi-dsdt.aml \
 ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin QEMU,cgthree.bin \
 pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
 pxe-pcnet.rom pxe-rtl8139.rom pxe-virtio.rom \
 efi-e1000.rom efi-eepro100.rom efi-ne2k_pci.rom \
 efi-pcnet.rom efi-rtl8139.rom efi-virtio.rom \
-efi-e1000e.rom efi-vmxnet3.rom \
 qemu-icon.bmp qemu_logo_no_text.svg \
 bamboo.dtb petalogix-s3adsp1800.dtb petalogix-ml605.dtb \
-multiboot.bin linuxboot.bin linuxboot_dma.bin kvmvapic.bin \
+multiboot.bin linuxboot.bin kvmvapic.bin \
+s390-zipl.rom \
 s390-ccw.img \
-spapr-rtas.bin slof.bin skiboot.lid \
+spapr-rtas.bin slof.bin \
 palcode-clipper \
-u-boot.e500 \
-qemu_vga.ndrv
+u-boot.e500
 else
 BLOBS=
 endif
 
 install-doc: $(DOCS)
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) qemu-doc.html "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) qemu-doc.txt "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) docs/interop/qemu-qmp-ref.html "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) docs/interop/qemu-qmp-ref.txt "$(DESTDIR)$(qemu_docdir)"
+	$(INSTALL_DATA) qemu-doc.html  qemu-tech.html "$(DESTDIR)$(qemu_docdir)"
+	$(INSTALL_DATA) qmp-commands.txt "$(DESTDIR)$(qemu_docdir)"
 ifdef CONFIG_POSIX
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
 	$(INSTALL_DATA) qemu.1 "$(DESTDIR)$(mandir)/man1"
-	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man7"
-	$(INSTALL_DATA) docs/interop/qemu-qmp-ref.7 "$(DESTDIR)$(mandir)/man7"
 ifneq ($(TOOLS),)
 	$(INSTALL_DATA) qemu-img.1 "$(DESTDIR)$(mandir)/man1"
 	$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man8"
@@ -580,9 +419,6 @@ ifneq ($(TOOLS),)
 endif
 ifneq (,$(findstring qemu-ga,$(TOOLS)))
 	$(INSTALL_DATA) qemu-ga.8 "$(DESTDIR)$(mandir)/man8"
-	$(INSTALL_DATA) docs/interop/qemu-ga-ref.html "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) docs/interop/qemu-ga-ref.txt "$(DESTDIR)$(qemu_docdir)"
-	$(INSTALL_DATA) docs/interop/qemu-ga-ref.7 "$(DESTDIR)$(mandir)/man7"
 endif
 endif
 ifdef CONFIG_VIRTFS
@@ -601,7 +437,8 @@ endif
 endif
 
 
-install: all $(if $(BUILD_DOCS),install-doc) install-datadir install-localstatedir
+install: all $(if $(BUILD_DOCS),install-doc) \
+install-datadir install-localstatedir
 ifneq ($(TOOLS),)
 	$(call install-prog,$(subst qemu-ga,qemu-ga$(EXESUF),$(TOOLS)),$(DESTDIR)$(bindir))
 endif
@@ -628,7 +465,7 @@ endif
 	set -e; for x in $(KEYMAPS); do \
 		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/keymaps/$$x "$(DESTDIR)$(qemu_datadir)/keymaps"; \
 	done
-	$(INSTALL_DATA) $(BUILD_DIR)/trace-events-all "$(DESTDIR)$(qemu_datadir)/trace-events-all"
+	$(INSTALL_DATA) $(SRC_PATH)/trace-events "$(DESTDIR)$(qemu_datadir)/trace-events"
 	for d in $(TARGET_DIRS); do \
 	$(MAKE) $(SUBDIR_MAKEFLAGS) TARGET_DIR=$$d/ -C $$d $@ || exit 1 ; \
         done
@@ -639,12 +476,12 @@ test speed: all
 
 .PHONY: ctags
 ctags:
-	rm -f tags
+	rm -f $@
 	find "$(SRC_PATH)" -name '*.[hc]' -exec ctags --append {} +
 
 .PHONY: TAGS
 TAGS:
-	rm -f TAGS
+	rm -f $@
 	find "$(SRC_PATH)" -name '*.[hc]' -exec etags --append {} +
 
 cscope:
@@ -657,89 +494,95 @@ ui/shader/%-vert.h: $(SRC_PATH)/ui/shader/%.vert $(SRC_PATH)/scripts/shaderinclu
 	@mkdir -p $(dir $@)
 	$(call quiet-command,\
 		perl $(SRC_PATH)/scripts/shaderinclude.pl $< > $@,\
-		"VERT","$@")
+		"  VERT  $@")
 
 ui/shader/%-frag.h: $(SRC_PATH)/ui/shader/%.frag $(SRC_PATH)/scripts/shaderinclude.pl
 	@mkdir -p $(dir $@)
 	$(call quiet-command,\
 		perl $(SRC_PATH)/scripts/shaderinclude.pl $< > $@,\
-		"FRAG","$@")
+		"  FRAG  $@")
 
 ui/console-gl.o: $(SRC_PATH)/ui/console-gl.c \
 	ui/shader/texture-blit-vert.h ui/shader/texture-blit-frag.h
 
 # documentation
 MAKEINFO=makeinfo
-MAKEINFOINCLUDES= -I docs -I $(<D) -I $(@D)
-MAKEINFOFLAGS=--no-split --number-sections $(MAKEINFOINCLUDES)
-TEXI2PODFLAGS=$(MAKEINFOINCLUDES) "-DVERSION=$(VERSION)"
-TEXI2PDFFLAGS=$(if $(V),,--quiet) -I $(SRC_PATH) $(MAKEINFOINCLUDES)
+MAKEINFOFLAGS=--no-headers --no-split --number-sections
+TEXIFLAG=$(if $(V),,--quiet)
+%.dvi: %.texi
+	$(call quiet-command,texi2dvi $(TEXIFLAG) -I . $<,"  GEN   $@")
 
-docs/version.texi: $(SRC_PATH)/VERSION
-	$(call quiet-command,echo "@set VERSION $(VERSION)" > $@,"GEN","$@")
+%.html: %.texi
+	$(call quiet-command,LC_ALL=C $(MAKEINFO) $(MAKEINFOFLAGS) --html $< -o $@, \
+	"  GEN   $@")
 
-%.html: %.texi docs/version.texi
-	$(call quiet-command,LC_ALL=C $(MAKEINFO) $(MAKEINFOFLAGS) --no-headers \
-	--html $< -o $@,"GEN","$@")
+%.info: %.texi
+	$(call quiet-command,$(MAKEINFO) $< -o $@,"  GEN   $@")
 
-%.info: %.texi docs/version.texi
-	$(call quiet-command,$(MAKEINFO) $(MAKEINFOFLAGS) $< -o $@,"GEN","$@")
+%.pdf: %.texi
+	$(call quiet-command,texi2pdf $(TEXIFLAG) -I . $<,"  GEN   $@")
 
-%.txt: %.texi docs/version.texi
-	$(call quiet-command,LC_ALL=C $(MAKEINFO) $(MAKEINFOFLAGS) --no-headers \
-	--plaintext $< -o $@,"GEN","$@")
+qemu-options.texi: $(SRC_PATH)/qemu-options.hx
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")
 
-%.pdf: %.texi docs/version.texi
-	$(call quiet-command,texi2pdf $(TEXI2PDFFLAGS) $< -o $@,"GEN","$@")
+qemu-monitor.texi: $(SRC_PATH)/hmp-commands.hx
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")
 
-qemu-options.texi: $(SRC_PATH)/qemu-options.hx $(SRC_PATH)/scripts/hxtool
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"GEN","$@")
+qemu-monitor-info.texi: $(SRC_PATH)/hmp-commands-info.hx
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")
 
-qemu-monitor.texi: $(SRC_PATH)/hmp-commands.hx $(SRC_PATH)/scripts/hxtool
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"GEN","$@")
+qmp-commands.txt: $(SRC_PATH)/qmp-commands.hx
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -q < $< > $@,"  GEN   $@")
 
-qemu-monitor-info.texi: $(SRC_PATH)/hmp-commands-info.hx $(SRC_PATH)/scripts/hxtool
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"GEN","$@")
-
-qemu-img-cmds.texi: $(SRC_PATH)/qemu-img-cmds.hx $(SRC_PATH)/scripts/hxtool
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"GEN","$@")
-
-docs/interop/qemu-qmp-qapi.texi docs/interop/qemu-ga-qapi.texi: $(SRC_PATH)/scripts/qapi2texi.py $(qapi-py)
-
-docs/interop/qemu-qmp-qapi.texi: $(qapi-modules)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi2texi.py $< > $@,"GEN","$@")
-
-docs/interop/qemu-ga-qapi.texi: $(SRC_PATH)/qga/qapi-schema.json
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi2texi.py $< > $@,"GEN","$@")
+qemu-img-cmds.texi: $(SRC_PATH)/qemu-img-cmds.hx
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"  GEN   $@")
 
 qemu.1: qemu-doc.texi qemu-options.texi qemu-monitor.texi qemu-monitor-info.texi
-qemu.1: qemu-option-trace.texi
-qemu-img.1: qemu-img.texi qemu-option-trace.texi qemu-img-cmds.texi
+	$(call quiet-command, \
+	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu.pod && \
+	  $(POD2MAN) --section=1 --center=" " --release=" " qemu.pod > $@, \
+	  "  GEN   $@")
+
+qemu-img.1: qemu-img.texi qemu-img-cmds.texi
+	$(call quiet-command, \
+	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu-img.pod && \
+	  $(POD2MAN) --section=1 --center=" " --release=" " qemu-img.pod > $@, \
+	  "  GEN   $@")
+
 fsdev/virtfs-proxy-helper.1: fsdev/virtfs-proxy-helper.texi
-qemu-nbd.8: qemu-nbd.texi qemu-option-trace.texi
+	$(call quiet-command, \
+	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< fsdev/virtfs-proxy-helper.pod && \
+	  $(POD2MAN) --section=1 --center=" " --release=" " fsdev/virtfs-proxy-helper.pod > $@, \
+	  "  GEN   $@")
+
+qemu-nbd.8: qemu-nbd.texi
+	$(call quiet-command, \
+	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu-nbd.pod && \
+	  $(POD2MAN) --section=8 --center=" " --release=" " qemu-nbd.pod > $@, \
+	  "  GEN   $@")
+
 qemu-ga.8: qemu-ga.texi
+	$(call quiet-command, \
+	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu-ga.pod && \
+	  $(POD2MAN) --section=8 --center=" " --release=" " qemu-ga.pod > $@, \
+	  "  GEN   $@")
 
-html: qemu-doc.html docs/interop/qemu-qmp-ref.html docs/interop/qemu-ga-ref.html
-info: qemu-doc.info docs/interop/qemu-qmp-ref.info docs/interop/qemu-ga-ref.info
-pdf: qemu-doc.pdf docs/interop/qemu-qmp-ref.pdf docs/interop/qemu-ga-ref.pdf
-txt: qemu-doc.txt docs/interop/qemu-qmp-ref.txt docs/interop/qemu-ga-ref.txt
+kvm_stat.1: scripts/kvm/kvm_stat.texi
+	$(call quiet-command, \
+	  perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< kvm_stat.pod && \
+	  $(POD2MAN) --section=1 --center=" " --release=" " kvm_stat.pod > $@, \
+	  "  GEN   $@")
 
-qemu-doc.html qemu-doc.info qemu-doc.pdf qemu-doc.txt: \
-	qemu-img.texi qemu-nbd.texi qemu-options.texi qemu-option-trace.texi \
+dvi: qemu-doc.dvi qemu-tech.dvi
+html: qemu-doc.html qemu-tech.html
+info: qemu-doc.info qemu-tech.info
+pdf: qemu-doc.pdf qemu-tech.pdf
+
+qemu-doc.dvi qemu-doc.html qemu-doc.info qemu-doc.pdf: \
+	qemu-img.texi qemu-nbd.texi qemu-options.texi \
 	qemu-monitor.texi qemu-img-cmds.texi qemu-ga.texi \
 	qemu-monitor-info.texi
 
-docs/interop/qemu-ga-ref.dvi docs/interop/qemu-ga-ref.html \
-    docs/interop/qemu-ga-ref.info docs/interop/qemu-ga-ref.pdf \
-    docs/interop/qemu-ga-ref.txt docs/interop/qemu-ga-ref.7: \
-	docs/interop/qemu-ga-ref.texi docs/interop/qemu-ga-qapi.texi
-
-docs/interop/qemu-qmp-ref.dvi docs/interop/qemu-qmp-ref.html \
-    docs/interop/qemu-qmp-ref.info docs/interop/qemu-qmp-ref.pdf \
-    docs/interop/qemu-qmp-ref.txt docs/interop/qemu-qmp-ref.7: \
-	docs/interop/qemu-qmp-ref.texi docs/interop/qemu-qmp-qapi.texi
-
-
 ifdef CONFIG_WIN32
 
 INSTALLER = qemu-setup-$(VERSION)$(EXESUF)
@@ -798,55 +641,10 @@ endif # CONFIG_WIN
 
 # Add a dependency on the generated files, so that they are always
 # rebuilt before other object files
-ifneq ($(wildcard config-host.mak),)
 ifneq ($(filter-out $(UNCHECKED_GOALS),$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fail))
-Makefile: $(GENERATED_FILES)
+Makefile: $(GENERATED_HEADERS)
 endif
-endif
-
-.SECONDARY: $(TRACE_HEADERS) $(TRACE_HEADERS:%=%-timestamp) \
-	$(TRACE_SOURCES) $(TRACE_SOURCES:%=%-timestamp) \
-	$(TRACE_DTRACE) $(TRACE_DTRACE:%=%-timestamp)
 
 # Include automatically generated dependency files
 # Dependencies in Makefile.objs files come from our recursive subdir rules
 -include $(wildcard *.d tests/*.d)
-
-include $(SRC_PATH)/tests/docker/Makefile.include
-
-.PHONY: help
-help:
-	@echo  'Generic targets:'
-	@echo  '  all             - Build all'
-	@echo  '  dir/file.o      - Build specified target only'
-	@echo  '  install         - Install QEMU, documentation and tools'
-	@echo  '  ctags/TAGS      - Generate tags file for editors'
-	@echo  '  cscope          - Generate cscope index'
-	@echo  ''
-	@$(if $(TARGET_DIRS), \
-		echo 'Architecture specific targets:'; \
-		$(foreach t, $(TARGET_DIRS), \
-		printf "  %-30s - Build for %s\\n" $(patsubst %,subdir-%,$(t)) $(t);) \
-		echo '')
-	@echo  'Cleaning targets:'
-	@echo  '  clean           - Remove most generated files but keep the config'
-	@echo  '  distclean       - Remove all generated files'
-	@echo  '  dist            - Build a distributable tarball'
-	@echo  ''
-	@echo  'Test targets:'
-	@echo  '  check           - Run all tests (check-help for details)'
-	@echo  '  docker          - Help about targets running tests inside Docker containers'
-	@echo  ''
-	@echo  'Documentation targets:'
-	@echo  '  html info pdf txt'
-	@echo  '                  - Build documentation in specified format'
-	@echo  ''
-ifdef CONFIG_WIN32
-	@echo  'Windows targets:'
-	@echo  '  installer       - Build NSIS-based installer for QEMU'
-ifdef QEMU_GA_MSI_ENABLED
-	@echo  '  msi             - Build MSI-based installer for qemu-ga'
-endif
-	@echo  ''
-endif
-	@echo  '  make V=0|1 [targets] 0 => quiet build (default), 1 => verbose build'

Makefile.objs

@@ -1,19 +1,19 @@
 #######################################################################
 # Common libraries for tools and emulators
-stub-obj-y = stubs/ crypto/
+stub-obj-y = stubs/
 util-obj-y = util/ qobject/ qapi/
 util-obj-y += qmp-introspect.o qapi-types.o qapi-visit.o qapi-event.o
 
-chardev-obj-y = chardev/
-
 #######################################################################
 # block-obj-y is code used by both qemu system emulation and qemu-img
 
-block-obj-y += nbd/
-block-obj-y += block.o blockjob.o
+block-obj-y = async.o thread-pool.o
+block-obj-y += nbd.o block.o blockjob.o
+block-obj-y += main-loop.o iohandler.o qemu-timer.o
+block-obj-$(CONFIG_POSIX) += aio-posix.o
+block-obj-$(CONFIG_WIN32) += aio-win32.o
 block-obj-y += block/
 block-obj-y += qemu-io-cmds.o
-block-obj-$(CONFIG_REPLICATION) += replication.o
 
 block-obj-m = block/
 
@@ -28,11 +28,6 @@ crypto-aes-obj-y = crypto/
 
 qom-obj-y = qom/
 
-#######################################################################
-# io-obj-y is code used by both qemu system emulation and qemu-img
-
-io-obj-y = io/
-
 ######################################################################
 # Target independent part of system emulation. The long term path is to
 # suppress *all* target specific code in case of system emulation, i.e. a
@@ -49,9 +44,15 @@ common-obj-$(CONFIG_POSIX) += os-posix.o
 common-obj-$(CONFIG_LINUX) += fsdev/
 
 common-obj-y += migration/
+common-obj-y += qemu-char.o #aio.o
+common-obj-y += page_cache.o
+common-obj-y += qjson.o
+
+common-obj-$(CONFIG_SPICE) += spice-qemu-char.o
 
 common-obj-y += audio/
 common-obj-y += hw/
+common-obj-y += accel.o
 
 common-obj-y += replay/
 
@@ -67,7 +68,6 @@ common-obj-y += tpm.o
 common-obj-$(CONFIG_SLIRP) += slirp/
 
 common-obj-y += backends/
-common-obj-y += chardev/
 
 common-obj-$(CONFIG_SECCOMP) += qemu-seccomp.o
 
@@ -83,7 +83,8 @@ endif
 
 #######################################################################
 # Target-independent parts used in system and user emulation
-common-obj-y += cpus-common.o
+common-obj-y += qemu-log.o
+common-obj-y += tcg-runtime.o
 common-obj-y += hw/
 common-obj-y += qom/
 common-obj-y += disas/
@@ -91,6 +92,7 @@ common-obj-y += disas/
 ######################################################################
 # Resource file for Windows executables
 version-obj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.o
+version-lobj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.lo
 
 ######################################################################
 # tracing
@@ -109,70 +111,3 @@ qga-vss-dll-obj-y = qga/
 # contrib
 ivshmem-client-obj-y = contrib/ivshmem-client/
 ivshmem-server-obj-y = contrib/ivshmem-server/
-libvhost-user-obj-y = contrib/libvhost-user/
-vhost-user-scsi.o-cflags := $(LIBISCSI_CFLAGS)
-vhost-user-scsi.o-libs := $(LIBISCSI_LIBS)
-vhost-user-scsi-obj-y = contrib/vhost-user-scsi/
-vhost-user-scsi-obj-y += contrib/libvhost-user/libvhost-user.o
-
-######################################################################
-trace-events-subdirs =
-trace-events-subdirs += util
-trace-events-subdirs += crypto
-trace-events-subdirs += io
-trace-events-subdirs += migration
-trace-events-subdirs += block
-trace-events-subdirs += backends
-trace-events-subdirs += chardev
-trace-events-subdirs += hw/block
-trace-events-subdirs += hw/block/dataplane
-trace-events-subdirs += hw/char
-trace-events-subdirs += hw/intc
-trace-events-subdirs += hw/net
-trace-events-subdirs += hw/virtio
-trace-events-subdirs += hw/audio
-trace-events-subdirs += hw/misc
-trace-events-subdirs += hw/usb
-trace-events-subdirs += hw/scsi
-trace-events-subdirs += hw/nvram
-trace-events-subdirs += hw/display
-trace-events-subdirs += hw/input
-trace-events-subdirs += hw/timer
-trace-events-subdirs += hw/dma
-trace-events-subdirs += hw/sparc
-trace-events-subdirs += hw/sd
-trace-events-subdirs += hw/isa
-trace-events-subdirs += hw/mem
-trace-events-subdirs += hw/i386
-trace-events-subdirs += hw/i386/xen
-trace-events-subdirs += hw/9pfs
-trace-events-subdirs += hw/ppc
-trace-events-subdirs += hw/pci
-trace-events-subdirs += hw/s390x
-trace-events-subdirs += hw/vfio
-trace-events-subdirs += hw/acpi
-trace-events-subdirs += hw/arm
-trace-events-subdirs += hw/alpha
-trace-events-subdirs += hw/xen
-trace-events-subdirs += ui
-trace-events-subdirs += audio
-trace-events-subdirs += net
-trace-events-subdirs += target/arm
-trace-events-subdirs += target/i386
-trace-events-subdirs += target/mips
-trace-events-subdirs += target/sparc
-trace-events-subdirs += target/s390x
-trace-events-subdirs += target/ppc
-trace-events-subdirs += qom
-trace-events-subdirs += linux-user
-trace-events-subdirs += qapi
-trace-events-subdirs += accel/tcg
-trace-events-subdirs += accel/kvm
-
-trace-events-files = $(SRC_PATH)/trace-events $(trace-events-subdirs:%=$(SRC_PATH)/%/trace-events)
-
-trace-obj-y = trace-root.o
-trace-obj-y += $(trace-events-subdirs:%=%/trace.o)
-trace-obj-$(CONFIG_TRACE_UST) += trace-ust-all.o
-trace-obj-$(CONFIG_TRACE_DTRACE) += trace-dtrace-root.o
-trace-obj-$(CONFIG_TRACE_DTRACE) += $(trace-events-subdirs:%=%/trace-dtrace.o)

Makefile.target

@@ -11,7 +11,7 @@ $(call set-vpath, $(SRC_PATH):$(BUILD_DIR))
 ifdef CONFIG_LINUX
 QEMU_CFLAGS += -I../linux-headers
 endif
-QEMU_CFLAGS += -I.. -I$(SRC_PATH)/target/$(TARGET_BASE_ARCH) -DNEED_CPU_H
+QEMU_CFLAGS += -I.. -I$(SRC_PATH)/target-$(TARGET_BASE_ARCH) -DNEED_CPU_H
 
 QEMU_CFLAGS+=-I$(SRC_PATH)/include
 
@@ -26,7 +26,7 @@ ifneq (,$(findstring -mwindows,$(libs_softmmu)))
 # Terminate program name with a 'w' because the linker builds a windows executable.
 QEMU_PROGW=qemu-system-$(TARGET_NAME)w$(EXESUF)
 $(QEMU_PROG): $(QEMU_PROGW)
-	$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG),"GEN","$(TARGET_DIR)$(QEMU_PROG)")
+	$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG),"  GEN   $(TARGET_DIR)$(QEMU_PROG)")
 QEMU_PROG_BUILD = $(QEMU_PROGW)
 else
 QEMU_PROG_BUILD = $(QEMU_PROG)
@@ -36,6 +36,10 @@ endif
 PROGS=$(QEMU_PROG) $(QEMU_PROGW)
 STPFILES=
 
+ifdef CONFIG_LINUX_USER
+PROGS+=$(QEMU_PROG)-binfmt
+endif
+
 config-target.h: config-target.h-timestamp
 config-target.h-timestamp: config-target.mak
 
@@ -48,38 +52,34 @@ else
 TARGET_TYPE=system
 endif
 
-$(QEMU_PROG).stp-installed: $(BUILD_DIR)/trace-events-all
+$(QEMU_PROG).stp-installed: $(SRC_PATH)/trace-events
 	$(call quiet-command,$(TRACETOOL) \
-		--group=all \
 		--format=stap \
 		--backends=$(TRACE_BACKENDS) \
 		--binary=$(bindir)/$(QEMU_PROG) \
 		--target-name=$(TARGET_NAME) \
 		--target-type=$(TARGET_TYPE) \
-		$< > $@,"GEN","$(TARGET_DIR)$(QEMU_PROG).stp-installed")
+		< $< > $@,"  GEN   $(TARGET_DIR)$(QEMU_PROG).stp-installed")
 
-$(QEMU_PROG).stp: $(BUILD_DIR)/trace-events-all
+$(QEMU_PROG).stp: $(SRC_PATH)/trace-events
 	$(call quiet-command,$(TRACETOOL) \
-		--group=all \
 		--format=stap \
 		--backends=$(TRACE_BACKENDS) \
 		--binary=$(realpath .)/$(QEMU_PROG) \
 		--target-name=$(TARGET_NAME) \
 		--target-type=$(TARGET_TYPE) \
-		$< > $@,"GEN","$(TARGET_DIR)$(QEMU_PROG).stp")
+		< $< > $@,"  GEN   $(TARGET_DIR)$(QEMU_PROG).stp")
 
-$(QEMU_PROG)-simpletrace.stp: $(BUILD_DIR)/trace-events-all
+$(QEMU_PROG)-simpletrace.stp: $(SRC_PATH)/trace-events
 	$(call quiet-command,$(TRACETOOL) \
-		--group=all \
 		--format=simpletrace-stap \
 		--backends=$(TRACE_BACKENDS) \
 		--probe-prefix=qemu.$(TARGET_TYPE).$(TARGET_NAME) \
-		$< > $@,"GEN","$(TARGET_DIR)$(QEMU_PROG)-simpletrace.stp")
+		< $< > $@,"  GEN   $(TARGET_DIR)$(QEMU_PROG)-simpletrace.stp")
 
 else
 stap:
 endif
-.PHONY: stap
 
 all: $(PROGS) stap
 
@@ -88,17 +88,18 @@ all: $(PROGS) stap
 
 #########################################################
 # cpu emulator library
-obj-y += exec.o
-obj-y += accel/
+obj-y = exec.o translate-all.o cpu-exec.o
+obj-y += translate-common.o
+obj-y += cpu-exec-common.o
 obj-y += tcg/tcg.o tcg/tcg-op.o tcg/optimize.o
-obj-y += tcg/tcg-common.o tcg/tcg-runtime.o
-obj-$(CONFIG_TCG_INTERPRETER) += tcg/tci.o
+obj-$(CONFIG_TCG_INTERPRETER) += tci.o
+obj-y += tcg/tcg-common.o
 obj-$(CONFIG_TCG_INTERPRETER) += disas/tci.o
 obj-y += fpu/softfloat.o
-obj-y += target/$(TARGET_BASE_ARCH)/
+obj-y += target-$(TARGET_BASE_ARCH)/
 obj-y += disas.o
 obj-$(call notempty,$(TARGET_XML_FILES)) += gdbstub-xml.o
-obj-$(call lnot,$(CONFIG_HAX)) += hax-stub.o
+obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o
 
 obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decContext.o
 obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decNumber.o
@@ -111,12 +112,12 @@ obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal128.o
 
 ifdef CONFIG_LINUX_USER
 
-QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) \
-             -I$(SRC_PATH)/linux-user/host/$(ARCH) \
-             -I$(SRC_PATH)/linux-user
+QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) -I$(SRC_PATH)/linux-user
 
 obj-y += linux-user/
-obj-y += gdbstub.o thunk.o user-exec.o user-exec-stub.o
+obj-y += gdbstub.o thunk.o user-exec.o
+
+obj-binfmt-y += linux-user/
 
 endif #CONFIG_LINUX_USER
 
@@ -129,7 +130,7 @@ QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR) \
 			 -I$(SRC_PATH)/bsd-user/$(HOST_VARIANT_DIR)
 
 obj-y += bsd-user/
-obj-y += gdbstub.o user-exec.o user-exec-stub.o
+obj-y += gdbstub.o user-exec.o
 
 endif #CONFIG_BSD_USER
 
@@ -139,12 +140,19 @@ ifdef CONFIG_SOFTMMU
 obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o numa.o
 obj-y += qtest.o bootdevice.o
 obj-y += hw/
-obj-y += memory.o
+obj-$(CONFIG_KVM) += kvm-all.o
+obj-y += memory.o cputlb.o
 obj-y += memory_mapping.o
 obj-y += dump.o
-obj-y += migration/ram.o
+obj-y += migration/ram.o migration/savevm.o
 LIBS := $(libs_softmmu) $(LIBS)
 
+# xen support
+obj-$(CONFIG_XEN) += xen-common.o
+obj-$(CONFIG_XEN_I386) += xen-hvm.o xen-mapcache.o
+obj-$(call lnot,$(CONFIG_XEN)) += xen-common-stub.o
+obj-$(call lnot,$(CONFIG_XEN_I386)) += xen-hvm-stub.o
+
 # Hardware support
 ifeq ($(TARGET_NAME), sparc64)
 obj-y += hw/sparc64/
@@ -152,67 +160,71 @@ else
 obj-y += hw/$(TARGET_BASE_ARCH)/
 endif
 
-GENERATED_FILES += hmp-commands.h hmp-commands-info.h
+GENERATED_HEADERS += hmp-commands.h hmp-commands-info.h qmp-commands-old.h
 
 endif # CONFIG_SOFTMMU
 
 # Workaround for http://gcc.gnu.org/PR55489, see configure.
 %/translate.o: QEMU_CFLAGS += $(TRANSLATE_OPT_CFLAGS)
 
+ifdef CONFIG_LINUX_USER
+dummy := $(call unnest-vars,,obj-y obj-binfmt-y)
+else
 dummy := $(call unnest-vars,,obj-y)
+endif
 all-obj-y := $(obj-y)
 
 target-obj-y :=
 block-obj-y :=
 common-obj-y :=
-chardev-obj-y :=
 include $(SRC_PATH)/Makefile.objs
 dummy := $(call unnest-vars,,target-obj-y)
 target-obj-y-save := $(target-obj-y)
 dummy := $(call unnest-vars,.., \
                block-obj-y \
                block-obj-m \
-               chardev-obj-y \
                crypto-obj-y \
                crypto-aes-obj-y \
                qom-obj-y \
-               io-obj-y \
                common-obj-y \
                common-obj-m)
 target-obj-y := $(target-obj-y-save)
 all-obj-y += $(common-obj-y)
 all-obj-y += $(target-obj-y)
 all-obj-y += $(qom-obj-y)
-all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y) $(chardev-obj-y)
+all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y)
 all-obj-$(CONFIG_USER_ONLY) += $(crypto-aes-obj-y)
 all-obj-$(CONFIG_SOFTMMU) += $(crypto-obj-y)
-all-obj-$(CONFIG_SOFTMMU) += $(io-obj-y)
 
 $(QEMU_PROG_BUILD): config-devices.mak
 
-COMMON_LDADDS = ../libqemuutil.a ../libqemustub.a
-
 # build either PROG or PROGW
-$(QEMU_PROG_BUILD): $(all-obj-y) $(COMMON_LDADDS)
+$(QEMU_PROG_BUILD): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
 	$(call LINK, $(filter-out %.mak, $^))
 ifdef CONFIG_DARWIN
-	$(call quiet-command,Rez -append $(SRC_PATH)/pc-bios/qemu.rsrc -o $@,"REZ","$(TARGET_DIR)$@")
-	$(call quiet-command,SetFile -a C $@,"SETFILE","$(TARGET_DIR)$@")
+	$(call quiet-command,Rez -append $(SRC_PATH)/pc-bios/qemu.rsrc -o $@,"  REZ   $(TARGET_DIR)$@")
+	$(call quiet-command,SetFile -a C $@,"  SETFILE $(TARGET_DIR)$@")
 endif
 
+$(QEMU_PROG)-binfmt: $(obj-binfmt-y)
+	$(call LINK,$^)
+
 gdbstub-xml.c: $(TARGET_XML_FILES) $(SRC_PATH)/scripts/feature_to_c.sh
-	$(call quiet-command,rm -f $@ && $(SHELL) $(SRC_PATH)/scripts/feature_to_c.sh $@ $(TARGET_XML_FILES),"GEN","$(TARGET_DIR)$@")
+	$(call quiet-command,rm -f $@ && $(SHELL) $(SRC_PATH)/scripts/feature_to_c.sh $@ $(TARGET_XML_FILES),"  GEN   $(TARGET_DIR)$@")
 
-hmp-commands.h: $(SRC_PATH)/hmp-commands.hx $(SRC_PATH)/scripts/hxtool
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"GEN","$(TARGET_DIR)$@")
+hmp-commands.h: $(SRC_PATH)/hmp-commands.hx
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")
 
-hmp-commands-info.h: $(SRC_PATH)/hmp-commands-info.hx $(SRC_PATH)/scripts/hxtool
-	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"GEN","$(TARGET_DIR)$@")
+hmp-commands-info.h: $(SRC_PATH)/hmp-commands-info.hx
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")
 
-clean: clean-target
+qmp-commands-old.h: $(SRC_PATH)/qmp-commands.hx
+	$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"  GEN   $(TARGET_DIR)$@")
+
+clean:
 	rm -f *.a *~ $(PROGS)
 	rm -f $(shell find . -name '*.[od]')
-	rm -f hmp-commands.h gdbstub-xml.c
+	rm -f hmp-commands.h qmp-commands-old.h gdbstub-xml.c
 ifdef CONFIG_TRACE_SYSTEMTAP
 	rm -f *.stp
 endif
@@ -227,5 +239,5 @@ ifdef CONFIG_TRACE_SYSTEMTAP
 	$(INSTALL_DATA) $(QEMU_PROG)-simpletrace.stp "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset/$(QEMU_PROG)-simpletrace.stp"
 endif
 
-GENERATED_FILES += config-target.h
-Makefile: $(GENERATED_FILES)
+GENERATED_HEADERS += config-target.h
+Makefile: $(GENERATED_HEADERS)

README

@@ -42,10 +42,11 @@ of other UNIX targets. The simple steps to build QEMU are:
   ../configure
   make
 
+Complete details of the process for building and configuring QEMU for
+all supported host platforms can be found in the qemu-tech.html file.
 Additional information can also be found online via the QEMU website:
 
   http://qemu-project.org/Hosts/Linux
-  http://qemu-project.org/Hosts/Mac
   http://qemu-project.org/Hosts/W32
 
 

VERSION

@@ -1 +1 @@
-2.9.50
+2.5.0

accel.c

@@ -23,7 +23,6 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
 #include "sysemu/accel.h"
 #include "hw/boards.h"
 #include "qemu-common.h"
@@ -33,6 +32,16 @@
 #include "sysemu/qtest.h"
 #include "hw/xen/xen.h"
 #include "qom/object.h"
+#include "hw/boards.h"
+
+int tcg_tb_size;
+static bool tcg_allowed = true;
+
+static int tcg_init(MachineState *ms)
+{
+    tcg_exec_init(tcg_tb_size * 1024 * 1024);
+    return 0;
+}
 
 static const TypeInfo accel_type = {
     .name = TYPE_ACCEL,
@@ -67,7 +76,7 @@ static int accel_init_machine(AccelClass *acc, MachineState *ms)
     return ret;
 }
 
-void configure_accelerator(MachineState *ms)
+int configure_accelerator(MachineState *ms)
 {
     const char *p;
     char buf[10];
@@ -118,11 +127,31 @@ void configure_accelerator(MachineState *ms)
     if (init_failed) {
         fprintf(stderr, "Back to %s accelerator.\n", acc->name);
     }
+
+    return !accel_initialised;
 }
 
+
+static void tcg_accel_class_init(ObjectClass *oc, void *data)
+{
+    AccelClass *ac = ACCEL_CLASS(oc);
+    ac->name = "tcg";
+    ac->init_machine = tcg_init;
+    ac->allowed = &tcg_allowed;
+}
+
+#define TYPE_TCG_ACCEL ACCEL_CLASS_NAME("tcg")
+
+static const TypeInfo tcg_accel_type = {
+    .name = TYPE_TCG_ACCEL,
+    .parent = TYPE_ACCEL,
+    .class_init = tcg_accel_class_init,
+};
+
 static void register_accel_types(void)
 {
     type_register_static(&accel_type);
+    type_register_static(&tcg_accel_type);
 }
 
 type_init(register_accel_types);

accel/Makefile.objs

@@ -1,4 +0,0 @@
-obj-$(CONFIG_SOFTMMU) += accel.o
-obj-y += kvm/
-obj-y += tcg/
-obj-y += stubs/

accel/kvm/Makefile.objs

@@ -1 +0,0 @@
-obj-$(CONFIG_KVM) += kvm-all.o

accel/kvm/trace-events

@@ -1,15 +0,0 @@
-# Trace events for debugging and performance instrumentation
-
-# kvm-all.c
-kvm_ioctl(int type, void *arg) "type 0x%x, arg %p"
-kvm_vm_ioctl(int type, void *arg) "type 0x%x, arg %p"
-kvm_vcpu_ioctl(int cpu_index, int type, void *arg) "cpu_index %d, type 0x%x, arg %p"
-kvm_run_exit(int cpu_index, uint32_t reason) "cpu_index %d, reason %d"
-kvm_device_ioctl(int fd, int type, void *arg) "dev fd %d, type 0x%x, arg %p"
-kvm_failed_reg_get(uint64_t id, const char *msg) "Warning: Unable to retrieve ONEREG %" PRIu64 " from KVM: %s"
-kvm_failed_reg_set(uint64_t id, const char *msg) "Warning: Unable to set ONEREG %" PRIu64 " to KVM: %s"
-kvm_irqchip_commit_routes(void) ""
-kvm_irqchip_add_msi_route(char *name, int vector, int virq) "dev %s vector %d virq %d"
-kvm_irqchip_update_msi_route(int virq) "Updating MSI route virq=%d"
-kvm_irqchip_release_virq(int virq) "virq %d"
-

accel/stubs/Makefile.objs

@@ -1 +0,0 @@
-obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o

accel/tcg/Makefile.objs

@@ -1,3 +0,0 @@
-obj-$(CONFIG_SOFTMMU) += tcg-all.o
-obj-$(CONFIG_SOFTMMU) += cputlb.o
-obj-y += cpu-exec.o cpu-exec-common.o translate-all.o translate-common.o

accel/tcg/cpu-exec.c

@@ -1,683 +0,0 @@
-/*
- *  emulator main execution loop
- *
- *  Copyright (c) 2003-2005 Fabrice Bellard
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this library; if not, see <http://www.gnu.org/licenses/>.
- */
-#include "qemu/osdep.h"
-#include "cpu.h"
-#include "trace.h"
-#include "disas/disas.h"
-#include "exec/exec-all.h"
-#include "tcg.h"
-#include "qemu/atomic.h"
-#include "sysemu/qtest.h"
-#include "qemu/timer.h"
-#include "exec/address-spaces.h"
-#include "qemu/rcu.h"
-#include "exec/tb-hash.h"
-#include "exec/log.h"
-#include "qemu/main-loop.h"
-#if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY)
-#include "hw/i386/apic.h"
-#endif
-#include "sysemu/cpus.h"
-#include "sysemu/replay.h"
-
-/* -icount align implementation. */
-
-typedef struct SyncClocks {
-    int64_t diff_clk;
-    int64_t last_cpu_icount;
-    int64_t realtime_clock;
-} SyncClocks;
-
-#if !defined(CONFIG_USER_ONLY)
-/* Allow the guest to have a max 3ms advance.
- * The difference between the 2 clocks could therefore
- * oscillate around 0.
- */
-#define VM_CLOCK_ADVANCE 3000000
-#define THRESHOLD_REDUCE 1.5
-#define MAX_DELAY_PRINT_RATE 2000000000LL
-#define MAX_NB_PRINTS 100
-
-static void align_clocks(SyncClocks *sc, const CPUState *cpu)
-{
-    int64_t cpu_icount;
-
-    if (!icount_align_option) {
-        return;
-    }
-
-    cpu_icount = cpu->icount_extra + cpu->icount_decr.u16.low;
-    sc->diff_clk += cpu_icount_to_ns(sc->last_cpu_icount - cpu_icount);
-    sc->last_cpu_icount = cpu_icount;
-
-    if (sc->diff_clk > VM_CLOCK_ADVANCE) {
-#ifndef _WIN32
-        struct timespec sleep_delay, rem_delay;
-        sleep_delay.tv_sec = sc->diff_clk / 1000000000LL;
-        sleep_delay.tv_nsec = sc->diff_clk % 1000000000LL;
-        if (nanosleep(&sleep_delay, &rem_delay) < 0) {
-            sc->diff_clk = rem_delay.tv_sec * 1000000000LL + rem_delay.tv_nsec;
-        } else {
-            sc->diff_clk = 0;
-        }
-#else
-        Sleep(sc->diff_clk / SCALE_MS);
-        sc->diff_clk = 0;
-#endif
-    }
-}
-
-static void print_delay(const SyncClocks *sc)
-{
-    static float threshold_delay;
-    static int64_t last_realtime_clock;
-    static int nb_prints;
-
-    if (icount_align_option &&
-        sc->realtime_clock - last_realtime_clock >= MAX_DELAY_PRINT_RATE &&
-        nb_prints < MAX_NB_PRINTS) {
-        if ((-sc->diff_clk / (float)1000000000LL > threshold_delay) ||
-            (-sc->diff_clk / (float)1000000000LL <
-             (threshold_delay - THRESHOLD_REDUCE))) {
-            threshold_delay = (-sc->diff_clk / 1000000000LL) + 1;
-            printf("Warning: The guest is now late by %.1f to %.1f seconds\n",
-                   threshold_delay - 1,
-                   threshold_delay);
-            nb_prints++;
-            last_realtime_clock = sc->realtime_clock;
-        }
-    }
-}
-
-static void init_delay_params(SyncClocks *sc,
-                              const CPUState *cpu)
-{
-    if (!icount_align_option) {
-        return;
-    }
-    sc->realtime_clock = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL_RT);
-    sc->diff_clk = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) - sc->realtime_clock;
-    sc->last_cpu_icount = cpu->icount_extra + cpu->icount_decr.u16.low;
-    if (sc->diff_clk < max_delay) {
-        max_delay = sc->diff_clk;
-    }
-    if (sc->diff_clk > max_advance) {
-        max_advance = sc->diff_clk;
-    }
-
-    /* Print every 2s max if the guest is late. We limit the number
-       of printed messages to NB_PRINT_MAX(currently 100) */
-    print_delay(sc);
-}
-#else
-static void align_clocks(SyncClocks *sc, const CPUState *cpu)
-{
-}
-
-static void init_delay_params(SyncClocks *sc, const CPUState *cpu)
-{
-}
-#endif /* CONFIG USER ONLY */
-
-/* Execute a TB, and fix up the CPU state afterwards if necessary */
-static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb)
-{
-    CPUArchState *env = cpu->env_ptr;
-    uintptr_t ret;
-    TranslationBlock *last_tb;
-    int tb_exit;
-    uint8_t *tb_ptr = itb->tc_ptr;
-
-    qemu_log_mask_and_addr(CPU_LOG_EXEC, itb->pc,
-                           "Trace %p [%d: " TARGET_FMT_lx "] %s\n",
-                           itb->tc_ptr, cpu->cpu_index, itb->pc,
-                           lookup_symbol(itb->pc));
-
-#if defined(DEBUG_DISAS)
-    if (qemu_loglevel_mask(CPU_LOG_TB_CPU)
-        && qemu_log_in_addr_range(itb->pc)) {
-        qemu_log_lock();
-#if defined(TARGET_I386)
-        log_cpu_state(cpu, CPU_DUMP_CCOP);
-#else
-        log_cpu_state(cpu, 0);
-#endif
-        qemu_log_unlock();
-    }
-#endif /* DEBUG_DISAS */
-
-    cpu->can_do_io = !use_icount;
-    ret = tcg_qemu_tb_exec(env, tb_ptr);
-    cpu->can_do_io = 1;
-    last_tb = (TranslationBlock *)(ret & ~TB_EXIT_MASK);
-    tb_exit = ret & TB_EXIT_MASK;
-    trace_exec_tb_exit(last_tb, tb_exit);
-
-    if (tb_exit > TB_EXIT_IDX1) {
-        /* We didn't start executing this TB (eg because the instruction
-         * counter hit zero); we must restore the guest PC to the address
-         * of the start of the TB.
-         */
-        CPUClass *cc = CPU_GET_CLASS(cpu);
-        qemu_log_mask_and_addr(CPU_LOG_EXEC, last_tb->pc,
-                               "Stopped execution of TB chain before %p ["
-                               TARGET_FMT_lx "] %s\n",
-                               last_tb->tc_ptr, last_tb->pc,
-                               lookup_symbol(last_tb->pc));
-        if (cc->synchronize_from_tb) {
-            cc->synchronize_from_tb(cpu, last_tb);
-        } else {
-            assert(cc->set_pc);
-            cc->set_pc(cpu, last_tb->pc);
-        }
-    }
-    return ret;
-}
-
-#ifndef CONFIG_USER_ONLY
-/* Execute the code without caching the generated code. An interpreter
-   could be used if available. */
-static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
-                             TranslationBlock *orig_tb, bool ignore_icount)
-{
-    TranslationBlock *tb;
-
-    /* Should never happen.
-       We only end up here when an existing TB is too long.  */
-    if (max_cycles > CF_COUNT_MASK)
-        max_cycles = CF_COUNT_MASK;
-
-    tb_lock();
-    tb = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base, orig_tb->flags,
-                     max_cycles | CF_NOCACHE
-                         | (ignore_icount ? CF_IGNORE_ICOUNT : 0));
-    tb->orig_tb = orig_tb;
-    tb_unlock();
-
-    /* execute the generated code */
-    trace_exec_tb_nocache(tb, tb->pc);
-    cpu_tb_exec(cpu, tb);
-
-    tb_lock();
-    tb_phys_invalidate(tb, -1);
-    tb_free(tb);
-    tb_unlock();
-}
-#endif
-
-static void cpu_exec_step(CPUState *cpu)
-{
-    CPUClass *cc = CPU_GET_CLASS(cpu);
-    CPUArchState *env = (CPUArchState *)cpu->env_ptr;
-    TranslationBlock *tb;
-    target_ulong cs_base, pc;
-    uint32_t flags;
-
-    cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
-    if (sigsetjmp(cpu->jmp_env, 0) == 0) {
-        mmap_lock();
-        tb_lock();
-        tb = tb_gen_code(cpu, pc, cs_base, flags,
-                         1 | CF_NOCACHE | CF_IGNORE_ICOUNT);
-        tb->orig_tb = NULL;
-        tb_unlock();
-        mmap_unlock();
-
-        cc->cpu_exec_enter(cpu);
-        /* execute the generated code */
-        trace_exec_tb_nocache(tb, pc);
-        cpu_tb_exec(cpu, tb);
-        cc->cpu_exec_exit(cpu);
-
-        tb_lock();
-        tb_phys_invalidate(tb, -1);
-        tb_free(tb);
-        tb_unlock();
-    } else {
-        /* We may have exited due to another problem here, so we need
-         * to reset any tb_locks we may have taken but didn't release.
-         * The mmap_lock is dropped by tb_gen_code if it runs out of
-         * memory.
-         */
-#ifndef CONFIG_SOFTMMU
-        tcg_debug_assert(!have_mmap_lock());
-#endif
-        tb_lock_reset();
-    }
-}
-
-void cpu_exec_step_atomic(CPUState *cpu)
-{
-    start_exclusive();
-
-    /* Since we got here, we know that parallel_cpus must be true.  */
-    parallel_cpus = false;
-    cpu_exec_step(cpu);
-    parallel_cpus = true;
-
-    end_exclusive();
-}
-
-struct tb_desc {
-    target_ulong pc;
-    target_ulong cs_base;
-    CPUArchState *env;
-    tb_page_addr_t phys_page1;
-    uint32_t flags;
-};
-
-static bool tb_cmp(const void *p, const void *d)
-{
-    const TranslationBlock *tb = p;
-    const struct tb_desc *desc = d;
-
-    if (tb->pc == desc->pc &&
-        tb->page_addr[0] == desc->phys_page1 &&
-        tb->cs_base == desc->cs_base &&
-        tb->flags == desc->flags &&
-        !atomic_read(&tb->invalid)) {
-        /* check next page if needed */
-        if (tb->page_addr[1] == -1) {
-            return true;
-        } else {
-            tb_page_addr_t phys_page2;
-            target_ulong virt_page2;
-
-            virt_page2 = (desc->pc & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE;
-            phys_page2 = get_page_addr_code(desc->env, virt_page2);
-            if (tb->page_addr[1] == phys_page2) {
-                return true;
-            }
-        }
-    }
-    return false;
-}
-
-TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
-                                   target_ulong cs_base, uint32_t flags)
-{
-    tb_page_addr_t phys_pc;
-    struct tb_desc desc;
-    uint32_t h;
-
-    desc.env = (CPUArchState *)cpu->env_ptr;
-    desc.cs_base = cs_base;
-    desc.flags = flags;
-    desc.pc = pc;
-    phys_pc = get_page_addr_code(desc.env, pc);
-    desc.phys_page1 = phys_pc & TARGET_PAGE_MASK;
-    h = tb_hash_func(phys_pc, pc, flags);
-    return qht_lookup(&tcg_ctx.tb_ctx.htable, tb_cmp, &desc, h);
-}
-
-static inline TranslationBlock *tb_find(CPUState *cpu,
-                                        TranslationBlock *last_tb,
-                                        int tb_exit)
-{
-    CPUArchState *env = (CPUArchState *)cpu->env_ptr;
-    TranslationBlock *tb;
-    target_ulong cs_base, pc;
-    uint32_t flags;
-    bool have_tb_lock = false;
-
-    /* we record a subset of the CPU state. It will
-       always be the same before a given translated block
-       is executed. */
-    cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
-    tb = atomic_rcu_read(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)]);
-    if (unlikely(!tb || tb->pc != pc || tb->cs_base != cs_base ||
-                 tb->flags != flags)) {
-        tb = tb_htable_lookup(cpu, pc, cs_base, flags);
-        if (!tb) {
-
-            /* mmap_lock is needed by tb_gen_code, and mmap_lock must be
-             * taken outside tb_lock. As system emulation is currently
-             * single threaded the locks are NOPs.
-             */
-            mmap_lock();
-            tb_lock();
-            have_tb_lock = true;
-
-            /* There's a chance that our desired tb has been translated while
-             * taking the locks so we check again inside the lock.
-             */
-            tb = tb_htable_lookup(cpu, pc, cs_base, flags);
-            if (!tb) {
-                /* if no translated code available, then translate it now */
-                tb = tb_gen_code(cpu, pc, cs_base, flags, 0);
-            }
-
-            mmap_unlock();
-        }
-
-        /* We add the TB in the virtual pc hash table for the fast lookup */
-        atomic_set(&cpu->tb_jmp_cache[tb_jmp_cache_hash_func(pc)], tb);
-    }
-#ifndef CONFIG_USER_ONLY
-    /* We don't take care of direct jumps when address mapping changes in
-     * system emulation. So it's not safe to make a direct jump to a TB
-     * spanning two pages because the mapping for the second page can change.
-     */
-    if (tb->page_addr[1] != -1) {
-        last_tb = NULL;
-    }
-#endif
-    /* See if we can patch the calling TB. */
-    if (last_tb && !qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) {
-        if (!have_tb_lock) {
-            tb_lock();
-            have_tb_lock = true;
-        }
-        if (!tb->invalid) {
-            tb_add_jump(last_tb, tb_exit, tb);
-        }
-    }
-    if (have_tb_lock) {
-        tb_unlock();
-    }
-    return tb;
-}
-
-static inline bool cpu_handle_halt(CPUState *cpu)
-{
-    if (cpu->halted) {
-#if defined(TARGET_I386) && !defined(CONFIG_USER_ONLY)
-        if ((cpu->interrupt_request & CPU_INTERRUPT_POLL)
-            && replay_interrupt()) {
-            X86CPU *x86_cpu = X86_CPU(cpu);
-            qemu_mutex_lock_iothread();
-            apic_poll_irq(x86_cpu->apic_state);
-            cpu_reset_interrupt(cpu, CPU_INTERRUPT_POLL);
-            qemu_mutex_unlock_iothread();
-        }
-#endif
-        if (!cpu_has_work(cpu)) {
-            return true;
-        }
-
-        cpu->halted = 0;
-    }
-
-    return false;
-}
-
-static inline void cpu_handle_debug_exception(CPUState *cpu)
-{
-    CPUClass *cc = CPU_GET_CLASS(cpu);
-    CPUWatchpoint *wp;
-
-    if (!cpu->watchpoint_hit) {
-        QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
-            wp->flags &= ~BP_WATCHPOINT_HIT;
-        }
-    }
-
-    cc->debug_excp_handler(cpu);
-}
-
-static inline bool cpu_handle_exception(CPUState *cpu, int *ret)
-{
-    if (cpu->exception_index >= 0) {
-        if (cpu->exception_index >= EXCP_INTERRUPT) {
-            /* exit request from the cpu execution loop */
-            *ret = cpu->exception_index;
-            if (*ret == EXCP_DEBUG) {
-                cpu_handle_debug_exception(cpu);
-            }
-            cpu->exception_index = -1;
-            return true;
-        } else {
-#if defined(CONFIG_USER_ONLY)
-            /* if user mode only, we simulate a fake exception
-               which will be handled outside the cpu execution
-               loop */
-#if defined(TARGET_I386)
-            CPUClass *cc = CPU_GET_CLASS(cpu);
-            cc->do_interrupt(cpu);
-#endif
-            *ret = cpu->exception_index;
-            cpu->exception_index = -1;
-            return true;
-#else
-            if (replay_exception()) {
-                CPUClass *cc = CPU_GET_CLASS(cpu);
-                qemu_mutex_lock_iothread();
-                cc->do_interrupt(cpu);
-                qemu_mutex_unlock_iothread();
-                cpu->exception_index = -1;
-            } else if (!replay_has_interrupt()) {
-                /* give a chance to iothread in replay mode */
-                *ret = EXCP_INTERRUPT;
-                return true;
-            }
-#endif
-        }
-#ifndef CONFIG_USER_ONLY
-    } else if (replay_has_exception()
-               && cpu->icount_decr.u16.low + cpu->icount_extra == 0) {
-        /* try to cause an exception pending in the log */
-        cpu_exec_nocache(cpu, 1, tb_find(cpu, NULL, 0), true);
-        *ret = -1;
-        return true;
-#endif
-    }
-
-    return false;
-}
-
-static inline bool cpu_handle_interrupt(CPUState *cpu,
-                                        TranslationBlock **last_tb)
-{
-    CPUClass *cc = CPU_GET_CLASS(cpu);
-
-    if (unlikely(atomic_read(&cpu->interrupt_request))) {
-        int interrupt_request;
-        qemu_mutex_lock_iothread();
-        interrupt_request = cpu->interrupt_request;
-        if (unlikely(cpu->singlestep_enabled & SSTEP_NOIRQ)) {
-            /* Mask out external interrupts for this step. */
-            interrupt_request &= ~CPU_INTERRUPT_SSTEP_MASK;
-        }
-        if (interrupt_request & CPU_INTERRUPT_DEBUG) {
-            cpu->interrupt_request &= ~CPU_INTERRUPT_DEBUG;
-            cpu->exception_index = EXCP_DEBUG;
-            qemu_mutex_unlock_iothread();
-            return true;
-        }
-        if (replay_mode == REPLAY_MODE_PLAY && !replay_has_interrupt()) {
-            /* Do nothing */
-        } else if (interrupt_request & CPU_INTERRUPT_HALT) {
-            replay_interrupt();
-            cpu->interrupt_request &= ~CPU_INTERRUPT_HALT;
-            cpu->halted = 1;
-            cpu->exception_index = EXCP_HLT;
-            qemu_mutex_unlock_iothread();
-            return true;
-        }
-#if defined(TARGET_I386)
-        else if (interrupt_request & CPU_INTERRUPT_INIT) {
-            X86CPU *x86_cpu = X86_CPU(cpu);
-            CPUArchState *env = &x86_cpu->env;
-            replay_interrupt();
-            cpu_svm_check_intercept_param(env, SVM_EXIT_INIT, 0, 0);
-            do_cpu_init(x86_cpu);
-            cpu->exception_index = EXCP_HALTED;
-            qemu_mutex_unlock_iothread();
-            return true;
-        }
-#else
-        else if (interrupt_request & CPU_INTERRUPT_RESET) {
-            replay_interrupt();
-            cpu_reset(cpu);
-            qemu_mutex_unlock_iothread();
-            return true;
-        }
-#endif
-        /* The target hook has 3 exit conditions:
-           False when the interrupt isn't processed,
-           True when it is, and we should restart on a new TB,
-           and via longjmp via cpu_loop_exit.  */
-        else {
-            if (cc->cpu_exec_interrupt(cpu, interrupt_request)) {
-                replay_interrupt();
-                *last_tb = NULL;
-            }
-            /* The target hook may have updated the 'cpu->interrupt_request';
-             * reload the 'interrupt_request' value */
-            interrupt_request = cpu->interrupt_request;
-        }
-        if (interrupt_request & CPU_INTERRUPT_EXITTB) {
-            cpu->interrupt_request &= ~CPU_INTERRUPT_EXITTB;
-            /* ensure that no TB jump will be modified as
-               the program flow was changed */
-            *last_tb = NULL;
-        }
-
-        /* If we exit via cpu_loop_exit/longjmp it is reset in cpu_exec */
-        qemu_mutex_unlock_iothread();
-    }
-
-    /* Finally, check if we need to exit to the main loop.  */
-    if (unlikely(atomic_read(&cpu->exit_request)
-        || (use_icount && cpu->icount_decr.u16.low + cpu->icount_extra == 0))) {
-        atomic_set(&cpu->exit_request, 0);
-        cpu->exception_index = EXCP_INTERRUPT;
-        return true;
-    }
-
-    return false;
-}
-
-static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
-                                    TranslationBlock **last_tb, int *tb_exit)
-{
-    uintptr_t ret;
-    int32_t insns_left;
-
-    trace_exec_tb(tb, tb->pc);
-    ret = cpu_tb_exec(cpu, tb);
-    tb = (TranslationBlock *)(ret & ~TB_EXIT_MASK);
-    *tb_exit = ret & TB_EXIT_MASK;
-    if (*tb_exit != TB_EXIT_REQUESTED) {
-        *last_tb = tb;
-        return;
-    }
-
-    *last_tb = NULL;
-    insns_left = atomic_read(&cpu->icount_decr.u32);
-    atomic_set(&cpu->icount_decr.u16.high, 0);
-    if (insns_left < 0) {
-        /* Something asked us to stop executing chained TBs; just
-         * continue round the main loop. Whatever requested the exit
-         * will also have set something else (eg exit_request or
-         * interrupt_request) which we will handle next time around
-         * the loop.  But we need to ensure the zeroing of icount_decr
-         * comes before the next read of cpu->exit_request
-         * or cpu->interrupt_request.
-         */
-        smp_mb();
-        return;
-    }
-
-    /* Instruction counter expired.  */
-    assert(use_icount);
-#ifndef CONFIG_USER_ONLY
-    /* Ensure global icount has gone forward */
-    cpu_update_icount(cpu);
-    /* Refill decrementer and continue execution.  */
-    insns_left = MIN(0xffff, cpu->icount_budget);
-    cpu->icount_decr.u16.low = insns_left;
-    cpu->icount_extra = cpu->icount_budget - insns_left;
-    if (!cpu->icount_extra) {
-        /* Execute any remaining instructions, then let the main loop
-         * handle the next event.
-         */
-        if (insns_left > 0) {
-            cpu_exec_nocache(cpu, insns_left, tb, false);
-        }
-    }
-#endif
-}
-
-/* main execution loop */
-
-int cpu_exec(CPUState *cpu)
-{
-    CPUClass *cc = CPU_GET_CLASS(cpu);
-    int ret;
-    SyncClocks sc = { 0 };
-
-    /* replay_interrupt may need current_cpu */
-    current_cpu = cpu;
-
-    if (cpu_handle_halt(cpu)) {
-        return EXCP_HALTED;
-    }
-
-    rcu_read_lock();
-
-    cc->cpu_exec_enter(cpu);
-
-    /* Calculate difference between guest clock and host clock.
-     * This delay includes the delay of the last cycle, so
-     * what we have to do is sleep until it is 0. As for the
-     * advance/delay we gain here, we try to fix it next time.
-     */
-    init_delay_params(&sc, cpu);
-
-    /* prepare setjmp context for exception handling */
-    if (sigsetjmp(cpu->jmp_env, 0) != 0) {
-#if defined(__clang__) || !QEMU_GNUC_PREREQ(4, 6)
-        /* Some compilers wrongly smash all local variables after
-         * siglongjmp. There were bug reports for gcc 4.5.0 and clang.
-         * Reload essential local variables here for those compilers.
-         * Newer versions of gcc would complain about this code (-Wclobbered). */
-        cpu = current_cpu;
-        cc = CPU_GET_CLASS(cpu);
-#else /* buggy compiler */
-        /* Assert that the compiler does not smash local variables. */
-        g_assert(cpu == current_cpu);
-        g_assert(cc == CPU_GET_CLASS(cpu));
-#endif /* buggy compiler */
-        cpu->can_do_io = 1;
-        tb_lock_reset();
-        if (qemu_mutex_iothread_locked()) {
-            qemu_mutex_unlock_iothread();
-        }
-    }
-
-    /* if an exception is pending, we execute it here */
-    while (!cpu_handle_exception(cpu, &ret)) {
-        TranslationBlock *last_tb = NULL;
-        int tb_exit = 0;
-
-        while (!cpu_handle_interrupt(cpu, &last_tb)) {
-            TranslationBlock *tb = tb_find(cpu, last_tb, tb_exit);
-            cpu_loop_exec_tb(cpu, tb, &last_tb, &tb_exit);
-            /* Try to align the host and virtual clocks
-               if the guest is in advance */
-            align_clocks(&sc, cpu);
-        }
-    }
-
-    cc->cpu_exec_exit(cpu);
-    rcu_read_unlock();
-
-    return ret;
-}

accel/tcg/tcg-all.c

@@ -1,61 +0,0 @@
-/*
- * QEMU System Emulator, accelerator interfaces
- *
- * Copyright (c) 2003-2008 Fabrice Bellard
- * Copyright (c) 2014 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 "qemu/osdep.h"
-#include "sysemu/accel.h"
-#include "sysemu/sysemu.h"
-#include "qom/object.h"
-
-int tcg_tb_size;
-static bool tcg_allowed = true;
-
-static int tcg_init(MachineState *ms)
-{
-    tcg_exec_init(tcg_tb_size * 1024 * 1024);
-    return 0;
-}
-
-static void tcg_accel_class_init(ObjectClass *oc, void *data)
-{
-    AccelClass *ac = ACCEL_CLASS(oc);
-    ac->name = "tcg";
-    ac->init_machine = tcg_init;
-    ac->allowed = &tcg_allowed;
-}
-
-#define TYPE_TCG_ACCEL ACCEL_CLASS_NAME("tcg")
-
-static const TypeInfo tcg_accel_type = {
-    .name = TYPE_TCG_ACCEL,
-    .parent = TYPE_ACCEL,
-    .class_init = tcg_accel_class_init,
-};
-
-static void register_accel_types(void)
-{
-    type_register_static(&tcg_accel_type);
-}
-
-type_init(register_accel_types);

accel/tcg/trace-events

@@ -1,10 +0,0 @@
-# Trace events for debugging and performance instrumentation
-
-# TCG related tracing (mostly disabled by default)
-# cpu-exec.c
-disable exec_tb(void *tb, uintptr_t pc) "tb:%p pc=0x%"PRIxPTR
-disable exec_tb_nocache(void *tb, uintptr_t pc) "tb:%p pc=0x%"PRIxPTR
-disable exec_tb_exit(void *last_tb, unsigned int flags) "tb:%p flags=%x"
-
-# translate-all.c
-translate_block(void *tb, uintptr_t pc, uint8_t *tb_code) "tb:%p, pc:0x%"PRIxPTR", tb_code:%p"

aio-posix.c

@@ -0,0 +1,494 @@
+/*
+ * 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"
+#ifdef CONFIG_EPOLL
+#include <sys/epoll.h>
+#endif
+
+struct AioHandler
+{
+    GPollFD pfd;
+    IOHandler *io_read;
+    IOHandler *io_write;
+    int deleted;
+    void *opaque;
+    bool is_external;
+    QLIST_ENTRY(AioHandler) node;
+};
+
+#ifdef CONFIG_EPOLL
+
+/* The fd number threashold to switch to epoll */
+#define EPOLL_ENABLE_THRESHOLD 64
+
+static void aio_epoll_disable(AioContext *ctx)
+{
+    ctx->epoll_available = false;
+    if (!ctx->epoll_enabled) {
+        return;
+    }
+    ctx->epoll_enabled = false;
+    close(ctx->epollfd);
+}
+
+static inline int epoll_events_from_pfd(int pfd_events)
+{
+    return (pfd_events & G_IO_IN ? EPOLLIN : 0) |
+           (pfd_events & G_IO_OUT ? EPOLLOUT : 0) |
+           (pfd_events & G_IO_HUP ? EPOLLHUP : 0) |
+           (pfd_events & G_IO_ERR ? EPOLLERR : 0);
+}
+
+static bool aio_epoll_try_enable(AioContext *ctx)
+{
+    AioHandler *node;
+    struct epoll_event event;
+
+    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
+        int r;
+        if (node->deleted || !node->pfd.events) {
+            continue;
+        }
+        event.events = epoll_events_from_pfd(node->pfd.events);
+        event.data.ptr = node;
+        r = epoll_ctl(ctx->epollfd, EPOLL_CTL_ADD, node->pfd.fd, &event);
+        if (r) {
+            return false;
+        }
+    }
+    ctx->epoll_enabled = true;
+    return true;
+}
+
+static void aio_epoll_update(AioContext *ctx, AioHandler *node, bool is_new)
+{
+    struct epoll_event event;
+    int r;
+
+    if (!ctx->epoll_enabled) {
+        return;
+    }
+    if (!node->pfd.events) {
+        r = epoll_ctl(ctx->epollfd, EPOLL_CTL_DEL, node->pfd.fd, &event);
+        if (r) {
+            aio_epoll_disable(ctx);
+        }
+    } else {
+        event.data.ptr = node;
+        event.events = epoll_events_from_pfd(node->pfd.events);
+        if (is_new) {
+            r = epoll_ctl(ctx->epollfd, EPOLL_CTL_ADD, node->pfd.fd, &event);
+            if (r) {
+                aio_epoll_disable(ctx);
+            }
+        } else {
+            r = epoll_ctl(ctx->epollfd, EPOLL_CTL_MOD, node->pfd.fd, &event);
+            if (r) {
+                aio_epoll_disable(ctx);
+            }
+        }
+    }
+}
+
+static int aio_epoll(AioContext *ctx, GPollFD *pfds,
+                     unsigned npfd, int64_t timeout)
+{
+    AioHandler *node;
+    int i, ret = 0;
+    struct epoll_event events[128];
+
+    assert(npfd == 1);
+    assert(pfds[0].fd == ctx->epollfd);
+    if (timeout > 0) {
+        ret = qemu_poll_ns(pfds, npfd, timeout);
+    }
+    if (timeout <= 0 || ret > 0) {
+        ret = epoll_wait(ctx->epollfd, events,
+                         sizeof(events) / sizeof(events[0]),
+                         timeout);
+        if (ret <= 0) {
+            goto out;
+        }
+        for (i = 0; i < ret; i++) {
+            int ev = events[i].events;
+            node = events[i].data.ptr;
+            node->pfd.revents = (ev & EPOLLIN ? G_IO_IN : 0) |
+                (ev & EPOLLOUT ? G_IO_OUT : 0) |
+                (ev & EPOLLHUP ? G_IO_HUP : 0) |
+                (ev & EPOLLERR ? G_IO_ERR : 0);
+        }
+    }
+out:
+    return ret;
+}
+
+static bool aio_epoll_enabled(AioContext *ctx)
+{
+    /* Fall back to ppoll when external clients are disabled. */
+    return !aio_external_disabled(ctx) && ctx->epoll_enabled;
+}
+
+static bool aio_epoll_check_poll(AioContext *ctx, GPollFD *pfds,
+                                 unsigned npfd, int64_t timeout)
+{
+    if (!ctx->epoll_available) {
+        return false;
+    }
+    if (aio_epoll_enabled(ctx)) {
+        return true;
+    }
+    if (npfd >= EPOLL_ENABLE_THRESHOLD) {
+        if (aio_epoll_try_enable(ctx)) {
+            return true;
+        } else {
+            aio_epoll_disable(ctx);
+        }
+    }
+    return false;
+}
+
+#else
+
+static void aio_epoll_update(AioContext *ctx, AioHandler *node, bool is_new)
+{
+}
+
+static int aio_epoll(AioContext *ctx, GPollFD *pfds,
+                     unsigned npfd, int64_t timeout)
+{
+    assert(false);
+}
+
+static bool aio_epoll_enabled(AioContext *ctx)
+{
+    return false;
+}
+
+static bool aio_epoll_check_poll(AioContext *ctx, GPollFD *pfds,
+                          unsigned npfd, int64_t timeout)
+{
+    return false;
+}
+
+#endif
+
+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,
+                        bool is_external,
+                        IOHandler *io_read,
+                        IOHandler *io_write,
+                        void *opaque)
+{
+    AioHandler *node;
+    bool is_new = false;
+    bool deleted = false;
+
+    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);
+                deleted = true;
+            }
+        }
+    } else {
+        if (node == NULL) {
+            /* Alloc and insert if it's not already there */
+            node = g_new0(AioHandler, 1);
+            node->pfd.fd = fd;
+            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
+
+            g_source_add_poll(&ctx->source, &node->pfd);
+            is_new = true;
+        }
+        /* Update handler with latest information */
+        node->io_read = io_read;
+        node->io_write = io_write;
+        node->opaque = opaque;
+        node->is_external = is_external;
+
+        node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP | G_IO_ERR : 0);
+        node->pfd.events |= (io_write ? G_IO_OUT | G_IO_ERR : 0);
+    }
+
+    aio_epoll_update(ctx, node, is_new);
+    aio_notify(ctx);
+    if (deleted) {
+        g_free(node);
+    }
+}
+
+void aio_set_event_notifier(AioContext *ctx,
+                            EventNotifier *notifier,
+                            bool is_external,
+                            EventNotifierHandler *io_read)
+{
+    aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
+                       is_external, (IOHandler *)io_read, NULL, notifier);
+}
+
+bool aio_prepare(AioContext *ctx)
+{
+    return false;
+}
+
+bool aio_pending(AioContext *ctx)
+{
+    AioHandler *node;
+
+    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
+        int revents;
+
+        revents = node->pfd.revents & node->pfd.events;
+        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
+            return true;
+        }
+        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
+            return true;
+        }
+    }
+
+    return false;
+}
+
+bool aio_dispatch(AioContext *ctx)
+{
+    AioHandler *node;
+    bool progress = false;
+
+    /*
+     * If there are callbacks left that have been queued, we need to call them.
+     * Do not call select in this case, because it is possible that the caller
+     * does not need a complete flush (as is the case for aio_poll loops).
+     */
+    if (aio_bh_poll(ctx)) {
+        progress = true;
+    }
+
+    /*
+     * We have to walk very carefully in case aio_set_fd_handler is
+     * called while we're walking.
+     */
+    node = QLIST_FIRST(&ctx->aio_handlers);
+    while (node) {
+        AioHandler *tmp;
+        int revents;
+
+        ctx->walking_handlers++;
+
+        revents = node->pfd.revents & node->pfd.events;
+        node->pfd.revents = 0;
+
+        if (!node->deleted &&
+            (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) &&
+            node->io_read) {
+            node->io_read(node->opaque);
+
+            /* aio_notify() does not count as progress */
+            if (node->opaque != &ctx->notifier) {
+                progress = true;
+            }
+        }
+        if (!node->deleted &&
+            (revents & (G_IO_OUT | G_IO_ERR)) &&
+            node->io_write) {
+            node->io_write(node->opaque);
+            progress = true;
+        }
+
+        tmp = node;
+        node = QLIST_NEXT(node, node);
+
+        ctx->walking_handlers--;
+
+        if (!ctx->walking_handlers && tmp->deleted) {
+            QLIST_REMOVE(tmp, node);
+            g_free(tmp);
+        }
+    }
+
+    /* Run our timers */
+    progress |= timerlistgroup_run_timers(&ctx->tlg);
+
+    return progress;
+}
+
+/* These thread-local variables are used only in a small part of aio_poll
+ * around the call to the poll() system call.  In particular they are not
+ * used while aio_poll is performing callbacks, which makes it much easier
+ * to think about reentrancy!
+ *
+ * Stack-allocated arrays would be perfect but they have size limitations;
+ * heap allocation is expensive enough that we want to reuse arrays across
+ * calls to aio_poll().  And because poll() has to be called without holding
+ * any lock, the arrays cannot be stored in AioContext.  Thread-local data
+ * has none of the disadvantages of these three options.
+ */
+static __thread GPollFD *pollfds;
+static __thread AioHandler **nodes;
+static __thread unsigned npfd, nalloc;
+static __thread Notifier pollfds_cleanup_notifier;
+
+static void pollfds_cleanup(Notifier *n, void *unused)
+{
+    g_assert(npfd == 0);
+    g_free(pollfds);
+    g_free(nodes);
+    nalloc = 0;
+}
+
+static void add_pollfd(AioHandler *node)
+{
+    if (npfd == nalloc) {
+        if (nalloc == 0) {
+            pollfds_cleanup_notifier.notify = pollfds_cleanup;
+            qemu_thread_atexit_add(&pollfds_cleanup_notifier);
+            nalloc = 8;
+        } else {
+            g_assert(nalloc <= INT_MAX);
+            nalloc *= 2;
+        }
+        pollfds = g_renew(GPollFD, pollfds, nalloc);
+        nodes = g_renew(AioHandler *, nodes, nalloc);
+    }
+    nodes[npfd] = node;
+    pollfds[npfd] = (GPollFD) {
+        .fd = node->pfd.fd,
+        .events = node->pfd.events,
+    };
+    npfd++;
+}
+
+bool aio_poll(AioContext *ctx, bool blocking)
+{
+    AioHandler *node;
+    int i, ret;
+    bool progress;
+    int64_t timeout;
+
+    aio_context_acquire(ctx);
+    progress = false;
+
+    /* aio_notify can avoid the expensive event_notifier_set if
+     * everything (file descriptors, bottom halves, timers) will
+     * be re-evaluated before the next blocking poll().  This is
+     * already true when aio_poll is called with blocking == false;
+     * if blocking == true, it is only true after poll() returns,
+     * so disable the optimization now.
+     */
+    if (blocking) {
+        atomic_add(&ctx->notify_me, 2);
+    }
+
+    ctx->walking_handlers++;
+
+    assert(npfd == 0);
+
+    /* fill pollfds */
+    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
+        if (!node->deleted && node->pfd.events
+            && !aio_epoll_enabled(ctx)
+            && aio_node_check(ctx, node->is_external)) {
+            add_pollfd(node);
+        }
+    }
+
+    timeout = blocking ? aio_compute_timeout(ctx) : 0;
+
+    /* wait until next event */
+    if (timeout) {
+        aio_context_release(ctx);
+    }
+    if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) {
+        AioHandler epoll_handler;
+
+        epoll_handler.pfd.fd = ctx->epollfd;
+        epoll_handler.pfd.events = G_IO_IN | G_IO_OUT | G_IO_HUP | G_IO_ERR;
+        npfd = 0;
+        add_pollfd(&epoll_handler);
+        ret = aio_epoll(ctx, pollfds, npfd, timeout);
+    } else  {
+        ret = qemu_poll_ns(pollfds, npfd, timeout);
+    }
+    if (blocking) {
+        atomic_sub(&ctx->notify_me, 2);
+    }
+    if (timeout) {
+        aio_context_acquire(ctx);
+    }
+
+    aio_notify_accept(ctx);
+
+    /* if we have any readable fds, dispatch event */
+    if (ret > 0) {
+        for (i = 0; i < npfd; i++) {
+            nodes[i]->pfd.revents = pollfds[i].revents;
+        }
+    }
+
+    npfd = 0;
+    ctx->walking_handlers--;
+
+    /* Run dispatch even if there were no readable fds to run timers */
+    if (aio_dispatch(ctx)) {
+        progress = true;
+    }
+
+    aio_context_release(ctx);
+
+    return progress;
+}
+
+void aio_context_setup(AioContext *ctx, Error **errp)
+{
+#ifdef CONFIG_EPOLL
+    assert(!ctx->epollfd);
+    ctx->epollfd = epoll_create1(EPOLL_CLOEXEC);
+    if (ctx->epollfd == -1) {
+        ctx->epoll_available = false;
+    } else {
+        ctx->epoll_available = true;
+    }
+#endif
+}

aio-win32.c

@@ -15,13 +15,10 @@
  * GNU GPL, version 2 or (at your option) any later version.
  */
 
-#include "qemu/osdep.h"
 #include "qemu-common.h"
 #include "block/block.h"
 #include "qemu/queue.h"
 #include "qemu/sockets.h"
-#include "qapi/error.h"
-#include "qemu/rcu_queue.h"
 
 struct AioHandler {
     EventNotifier *e;
@@ -40,13 +37,11 @@ void aio_set_fd_handler(AioContext *ctx,
                         bool is_external,
                         IOHandler *io_read,
                         IOHandler *io_write,
-                        AioPollFn *io_poll,
                         void *opaque)
 {
     /* fd is a SOCKET in our case */
     AioHandler *node;
 
-    qemu_lockcnt_lock(&ctx->list_lock);
     QLIST_FOREACH(node, &ctx->aio_handlers, node) {
         if (node->pfd.fd == fd && !node->deleted) {
             break;
@@ -56,14 +51,14 @@ void aio_set_fd_handler(AioContext *ctx,
     /* Are we deleting the fd handler? */
     if (!io_read && !io_write) {
         if (node) {
-            /* If aio_poll is in progress, just mark the node as deleted */
-            if (qemu_lockcnt_count(&ctx->list_lock)) {
+            /* 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 list_lock.
+                 * releasing the walking_handlers lock.
                  */
                 QLIST_REMOVE(node, node);
                 g_free(node);
@@ -76,7 +71,7 @@ void aio_set_fd_handler(AioContext *ctx,
             /* Alloc and insert if it's not already there */
             node = g_new0(AioHandler, 1);
             node->pfd.fd = fd;
-            QLIST_INSERT_HEAD_RCU(&ctx->aio_handlers, node, node);
+            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
         }
 
         node->pfd.events = 0;
@@ -101,26 +96,16 @@ void aio_set_fd_handler(AioContext *ctx,
                        FD_CONNECT | FD_WRITE | FD_OOB);
     }
 
-    qemu_lockcnt_unlock(&ctx->list_lock);
     aio_notify(ctx);
 }
 
-void aio_set_fd_poll(AioContext *ctx, int fd,
-                     IOHandler *io_poll_begin,
-                     IOHandler *io_poll_end)
-{
-    /* Not implemented */
-}
-
 void aio_set_event_notifier(AioContext *ctx,
                             EventNotifier *e,
                             bool is_external,
-                            EventNotifierHandler *io_notify,
-                            AioPollFn *io_poll)
+                            EventNotifierHandler *io_notify)
 {
     AioHandler *node;
 
-    qemu_lockcnt_lock(&ctx->list_lock);
     QLIST_FOREACH(node, &ctx->aio_handlers, node) {
         if (node->e == e && !node->deleted) {
             break;
@@ -132,14 +117,14 @@ void aio_set_event_notifier(AioContext *ctx,
         if (node) {
             g_source_remove_poll(&ctx->source, &node->pfd);
 
-            /* aio_poll is in progress, just mark the node as deleted */
-            if (qemu_lockcnt_count(&ctx->list_lock)) {
+            /* 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 list_lock.
+                 * releasing the walking_handlers lock.
                  */
                 QLIST_REMOVE(node, node);
                 g_free(node);
@@ -153,7 +138,7 @@ void aio_set_event_notifier(AioContext *ctx,
             node->pfd.fd = (uintptr_t)event_notifier_get_handle(e);
             node->pfd.events = G_IO_IN;
             node->is_external = is_external;
-            QLIST_INSERT_HEAD_RCU(&ctx->aio_handlers, node, node);
+            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
 
             g_source_add_poll(&ctx->source, &node->pfd);
         }
@@ -161,18 +146,9 @@ void aio_set_event_notifier(AioContext *ctx,
         node->io_notify = io_notify;
     }
 
-    qemu_lockcnt_unlock(&ctx->list_lock);
     aio_notify(ctx);
 }
 
-void aio_set_event_notifier_poll(AioContext *ctx,
-                                 EventNotifier *notifier,
-                                 EventNotifierHandler *io_poll_begin,
-                                 EventNotifierHandler *io_poll_end)
-{
-    /* Not implemented */
-}
-
 bool aio_prepare(AioContext *ctx)
 {
     static struct timeval tv0;
@@ -180,16 +156,10 @@ bool aio_prepare(AioContext *ctx)
     bool have_select_revents = false;
     fd_set rfds, wfds;
 
-    /*
-     * We have to walk very carefully in case aio_set_fd_handler is
-     * called while we're walking.
-     */
-    qemu_lockcnt_inc(&ctx->list_lock);
-
     /* fill fd sets */
     FD_ZERO(&rfds);
     FD_ZERO(&wfds);
-    QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
+    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
         if (node->io_read) {
             FD_SET ((SOCKET)node->pfd.fd, &rfds);
         }
@@ -199,7 +169,7 @@ bool aio_prepare(AioContext *ctx)
     }
 
     if (select(0, &rfds, &wfds, NULL, &tv0) > 0) {
-        QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
+        QLIST_FOREACH(node, &ctx->aio_handlers, node) {
             node->pfd.revents = 0;
             if (FD_ISSET(node->pfd.fd, &rfds)) {
                 node->pfd.revents |= G_IO_IN;
@@ -213,53 +183,45 @@ bool aio_prepare(AioContext *ctx)
         }
     }
 
-    qemu_lockcnt_dec(&ctx->list_lock);
     return have_select_revents;
 }
 
 bool aio_pending(AioContext *ctx)
 {
     AioHandler *node;
-    bool result = false;
 
-    /*
-     * We have to walk very carefully in case aio_set_fd_handler is
-     * called while we're walking.
-     */
-    qemu_lockcnt_inc(&ctx->list_lock);
-    QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
+    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
         if (node->pfd.revents && node->io_notify) {
-            result = true;
-            break;
+            return true;
         }
 
         if ((node->pfd.revents & G_IO_IN) && node->io_read) {
-            result = true;
-            break;
+            return true;
         }
         if ((node->pfd.revents & G_IO_OUT) && node->io_write) {
-            result = true;
-            break;
+            return true;
         }
     }
 
-    qemu_lockcnt_dec(&ctx->list_lock);
-    return result;
+    return false;
 }
 
 static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event)
 {
     AioHandler *node;
     bool progress = false;
-    AioHandler *tmp;
 
     /*
      * We have to walk very carefully in case aio_set_fd_handler is
      * called while we're walking.
      */
-    QLIST_FOREACH_SAFE_RCU(node, &ctx->aio_handlers, node, tmp) {
+    node = QLIST_FIRST(&ctx->aio_handlers);
+    while (node) {
+        AioHandler *tmp;
         int revents = node->pfd.revents;
 
+        ctx->walking_handlers++;
+
         if (!node->deleted &&
             (revents || event_notifier_get_handle(node->e) == event) &&
             node->io_notify) {
@@ -294,25 +256,28 @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event)
             }
         }
 
-        if (node->deleted) {
-            if (qemu_lockcnt_dec_if_lock(&ctx->list_lock)) {
-                QLIST_REMOVE(node, node);
-                g_free(node);
-                qemu_lockcnt_inc_and_unlock(&ctx->list_lock);
-            }
+        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;
 }
 
-void aio_dispatch(AioContext *ctx)
+bool aio_dispatch(AioContext *ctx)
 {
-    qemu_lockcnt_inc(&ctx->list_lock);
-    aio_bh_poll(ctx);
-    aio_dispatch_handlers(ctx, INVALID_HANDLE_VALUE);
-    qemu_lockcnt_dec(&ctx->list_lock);
-    timerlistgroup_run_timers(&ctx->tlg);
+    bool progress;
+
+    progress = aio_bh_poll(ctx);
+    progress |= aio_dispatch_handlers(ctx, INVALID_HANDLE_VALUE);
+    progress |= timerlistgroup_run_timers(&ctx->tlg);
+    return progress;
 }
 
 bool aio_poll(AioContext *ctx, bool blocking)
@@ -323,6 +288,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
     int count;
     int timeout;
 
+    aio_context_acquire(ctx);
     progress = false;
 
     /* aio_notify can avoid the expensive event_notifier_set if
@@ -336,18 +302,20 @@ bool aio_poll(AioContext *ctx, bool blocking)
         atomic_add(&ctx->notify_me, 2);
     }
 
-    qemu_lockcnt_inc(&ctx->list_lock);
     have_select_revents = aio_prepare(ctx);
 
+    ctx->walking_handlers++;
+
     /* fill fd sets */
     count = 0;
-    QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
+    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
         if (!node->deleted && node->io_notify
             && aio_node_check(ctx, node->is_external)) {
             events[count++] = event_notifier_get_handle(node->e);
         }
     }
 
+    ctx->walking_handlers--;
     first = true;
 
     /* ctx->notifier is always registered.  */
@@ -363,11 +331,17 @@ bool aio_poll(AioContext *ctx, bool blocking)
 
         timeout = blocking && !have_select_revents
             ? qemu_timeout_ns_to_ms(aio_compute_timeout(ctx)) : 0;
+        if (timeout) {
+            aio_context_release(ctx);
+        }
         ret = WaitForMultipleObjects(count, events, FALSE, timeout);
         if (blocking) {
             assert(first);
             atomic_sub(&ctx->notify_me, 2);
         }
+        if (timeout) {
+            aio_context_acquire(ctx);
+        }
 
         if (first) {
             aio_notify_accept(ctx);
@@ -390,18 +364,12 @@ bool aio_poll(AioContext *ctx, bool blocking)
         progress |= aio_dispatch_handlers(ctx, event);
     } while (count > 0);
 
-    qemu_lockcnt_dec(&ctx->list_lock);
-
     progress |= timerlistgroup_run_timers(&ctx->tlg);
+
+    aio_context_release(ctx);
     return progress;
 }
 
-void aio_context_setup(AioContext *ctx)
+void aio_context_setup(AioContext *ctx, Error **errp)
 {
 }
-
-void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
-                                 int64_t grow, int64_t shrink, Error **errp)
-{
-    error_setg(errp, "AioContext polling is not implemented on Windows");
-}

arch_init.c

@@ -21,18 +21,16 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
-#include "qemu-common.h"
-#include "cpu.h"
+#include <stdint.h>
 #include "sysemu/sysemu.h"
 #include "sysemu/arch_init.h"
 #include "hw/pci/pci.h"
-#include "hw/audio/soundhw.h"
+#include "hw/audio/audio.h"
+#include "hw/smbios/smbios.h"
 #include "qemu/config-file.h"
 #include "qemu/error-report.h"
 #include "qmp-commands.h"
 #include "hw/acpi/acpi.h"
-#include "qemu/help_option.h"
 
 #ifdef TARGET_SPARC
 int graphic_width = 1024;
@@ -63,8 +61,6 @@ int graphic_depth = 32;
 #define QEMU_ARCH QEMU_ARCH_MIPS
 #elif defined(TARGET_MOXIE)
 #define QEMU_ARCH QEMU_ARCH_MOXIE
-#elif defined(TARGET_NIOS2)
-#define QEMU_ARCH QEMU_ARCH_NIOS2
 #elif defined(TARGET_OPENRISC)
 #define QEMU_ARCH QEMU_ARCH_OPENRISC
 #elif defined(TARGET_PPC)
@@ -85,6 +81,205 @@ int graphic_depth = 32;
 
 const uint32_t arch_type = QEMU_ARCH;
 
+static struct defconfig_file {
+    const char *filename;
+    /* Indicates it is an user config file (disabled by -no-user-config) */
+    bool userconfig;
+} default_config_files[] = {
+    { CONFIG_QEMU_CONFDIR "/qemu.conf",                   true },
+    { NULL }, /* end of list */
+};
+
+int qemu_read_default_config_files(bool userconfig)
+{
+    int ret;
+    struct defconfig_file *f;
+
+    for (f = default_config_files; f->filename; f++) {
+        if (!userconfig && f->userconfig) {
+            continue;
+        }
+        ret = qemu_read_config_file(f->filename);
+        if (ret < 0 && ret != -ENOENT) {
+            return ret;
+        }
+    }
+
+    return 0;
+}
+
+struct soundhw {
+    const char *name;
+    const char *descr;
+    int enabled;
+    int isa;
+    union {
+        int (*init_isa) (ISABus *bus);
+        int (*init_pci) (PCIBus *bus);
+    } init;
+};
+
+static struct soundhw soundhw[9];
+static int soundhw_count;
+
+void isa_register_soundhw(const char *name, const char *descr,
+                          int (*init_isa)(ISABus *bus))
+{
+    assert(soundhw_count < ARRAY_SIZE(soundhw) - 1);
+    soundhw[soundhw_count].name = name;
+    soundhw[soundhw_count].descr = descr;
+    soundhw[soundhw_count].isa = 1;
+    soundhw[soundhw_count].init.init_isa = init_isa;
+    soundhw_count++;
+}
+
+void pci_register_soundhw(const char *name, const char *descr,
+                          int (*init_pci)(PCIBus *bus))
+{
+    assert(soundhw_count < ARRAY_SIZE(soundhw) - 1);
+    soundhw[soundhw_count].name = name;
+    soundhw[soundhw_count].descr = descr;
+    soundhw[soundhw_count].isa = 0;
+    soundhw[soundhw_count].init.init_pci = init_pci;
+    soundhw_count++;
+}
+
+void select_soundhw(const char *optarg)
+{
+    struct soundhw *c;
+
+    if (is_help_option(optarg)) {
+    show_valid_cards:
+
+        if (soundhw_count) {
+             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");
+        }
+        exit(!is_help_option(optarg));
+    }
+    else {
+        size_t l;
+        const char *p;
+        char *e;
+        int bad_card = 0;
+
+        if (!strcmp(optarg, "all")) {
+            for (c = soundhw; c->name; ++c) {
+                c->enabled = 1;
+            }
+            return;
+        }
+
+        p = optarg;
+        while (*p) {
+            e = strchr(p, ',');
+            l = !e ? strlen(p) : (size_t) (e - p);
+
+            for (c = soundhw; c->name; ++c) {
+                if (!strncmp(c->name, p, l) && !c->name[l]) {
+                    c->enabled = 1;
+                    break;
+                }
+            }
+
+            if (!c->name) {
+                if (l > 80) {
+                    error_report("Unknown sound card name (too big to show)");
+                }
+                else {
+                    error_report("Unknown sound card name `%.*s'",
+                                 (int) l, p);
+                }
+                bad_card = 1;
+            }
+            p += l + (e != NULL);
+        }
+
+        if (bad_card) {
+            goto show_valid_cards;
+        }
+    }
+}
+
+void audio_init(void)
+{
+    struct soundhw *c;
+    ISABus *isa_bus = (ISABus *) object_resolve_path_type("", TYPE_ISA_BUS, NULL);
+    PCIBus *pci_bus = (PCIBus *) object_resolve_path_type("", TYPE_PCI_BUS, NULL);
+
+    for (c = soundhw; c->name; ++c) {
+        if (c->enabled) {
+            if (c->isa) {
+                if (!isa_bus) {
+                    error_report("ISA bus not available for %s", c->name);
+                    exit(1);
+                }
+                c->init.init_isa(isa_bus);
+            } else {
+                if (!pci_bus) {
+                    error_report("PCI bus not available for %s", c->name);
+                    exit(1);
+                }
+                c->init.init_pci(pci_bus);
+            }
+        }
+    }
+}
+
+int qemu_uuid_parse(const char *str, uint8_t *uuid)
+{
+    int ret;
+
+    if (strlen(str) != 36) {
+        return -1;
+    }
+
+    ret = sscanf(str, UUID_FMT, &uuid[0], &uuid[1], &uuid[2], &uuid[3],
+                 &uuid[4], &uuid[5], &uuid[6], &uuid[7], &uuid[8], &uuid[9],
+                 &uuid[10], &uuid[11], &uuid[12], &uuid[13], &uuid[14],
+                 &uuid[15]);
+
+    if (ret != 16) {
+        return -1;
+    }
+    return 0;
+}
+
+void do_acpitable_option(const QemuOpts *opts)
+{
+#ifdef TARGET_I386
+    Error *err = NULL;
+
+    acpi_table_add(opts, &err);
+    if (err) {
+        error_report("Wrong acpi table provided: %s",
+                     error_get_pretty(err));
+        error_free(err);
+        exit(1);
+    }
+#endif
+}
+
+void do_smbios_option(QemuOpts *opts)
+{
+#ifdef TARGET_I386
+    smbios_entry_add(opts);
+#endif
+}
+
+void cpudef_init(void)
+{
+#if defined(cpudef_setup)
+    cpudef_setup(); /* parse cpu definitions in target config file */
+#endif
+}
+
 int kvm_available(void)
 {
 #ifdef CONFIG_KVM

async.c

@@ -1,8 +1,7 @@
 /*
- * Data plane event loop
+ * QEMU System Emulator
  *
  * Copyright (c) 2003-2008 Fabrice Bellard
- * Copyright (c) 2009-2017 QEMU contributors
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this software and associated documentation files (the "Software"), to deal
@@ -23,16 +22,11 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
-#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/aio.h"
 #include "block/thread-pool.h"
 #include "qemu/main-loop.h"
 #include "qemu/atomic.h"
-#include "block/raw-aio.h"
-#include "qemu/coroutine_int.h"
-#include "trace.h"
 
 /***********************************************************/
 /* bottom halves (can be seen as timers which expire ASAP) */
@@ -47,26 +41,6 @@ struct QEMUBH {
     bool deleted;
 };
 
-void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
-{
-    QEMUBH *bh;
-    bh = g_new(QEMUBH, 1);
-    *bh = (QEMUBH){
-        .ctx = ctx,
-        .cb = cb,
-        .opaque = opaque,
-    };
-    qemu_lockcnt_lock(&ctx->list_lock);
-    bh->next = ctx->first_bh;
-    bh->scheduled = 1;
-    bh->deleted = 1;
-    /* Make sure that the members are ready before putting bh into list */
-    smp_wmb();
-    ctx->first_bh = bh;
-    qemu_lockcnt_unlock(&ctx->list_lock);
-    aio_notify(ctx);
-}
-
 QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
 {
     QEMUBH *bh;
@@ -76,12 +50,12 @@ QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
         .cb = cb,
         .opaque = opaque,
     };
-    qemu_lockcnt_lock(&ctx->list_lock);
+    qemu_mutex_lock(&ctx->bh_lock);
     bh->next = ctx->first_bh;
     /* Make sure that the members are ready before putting bh into list */
     smp_wmb();
     ctx->first_bh = bh;
-    qemu_lockcnt_unlock(&ctx->list_lock);
+    qemu_mutex_unlock(&ctx->bh_lock);
     return bh;
 }
 
@@ -90,56 +64,53 @@ void aio_bh_call(QEMUBH *bh)
     bh->cb(bh->opaque);
 }
 
-/* Multiple occurrences of aio_bh_poll cannot be called concurrently.
- * The count in ctx->list_lock is incremented before the call, and is
- * not affected by the call.
- */
+/* Multiple occurrences of aio_bh_poll cannot be called concurrently */
 int aio_bh_poll(AioContext *ctx)
 {
     QEMUBH *bh, **bhp, *next;
     int ret;
-    bool deleted = false;
+
+    ctx->walking_bh++;
 
     ret = 0;
-    for (bh = atomic_rcu_read(&ctx->first_bh); bh; bh = next) {
-        next = atomic_rcu_read(&bh->next);
+    for (bh = ctx->first_bh; bh; bh = next) {
+        /* Make sure that fetching bh happens before accessing its members */
+        smp_read_barrier_depends();
+        next = bh->next;
         /* The atomic_xchg is paired with the one in qemu_bh_schedule.  The
          * implicit memory barrier ensures that the callback sees all writes
          * done by the scheduling thread.  It also ensures that the scheduling
          * thread sees the zero before bh->cb has run, and thus will call
          * aio_notify again if necessary.
          */
-        if (atomic_xchg(&bh->scheduled, 0)) {
-            /* Idle BHs don't count as progress */
-            if (!bh->idle) {
+        if (!bh->deleted && atomic_xchg(&bh->scheduled, 0)) {
+            /* Idle BHs and the notify BH don't count as progress */
+            if (!bh->idle && bh != ctx->notify_dummy_bh) {
                 ret = 1;
             }
             bh->idle = 0;
             aio_bh_call(bh);
         }
-        if (bh->deleted) {
-            deleted = true;
-        }
     }
 
+    ctx->walking_bh--;
+
     /* remove deleted bhs */
-    if (!deleted) {
-        return ret;
-    }
-
-    if (qemu_lockcnt_dec_if_lock(&ctx->list_lock)) {
+    if (!ctx->walking_bh) {
+        qemu_mutex_lock(&ctx->bh_lock);
         bhp = &ctx->first_bh;
         while (*bhp) {
             bh = *bhp;
-            if (bh->deleted && !bh->scheduled) {
+            if (bh->deleted) {
                 *bhp = bh->next;
                 g_free(bh);
             } else {
                 bhp = &bh->next;
             }
         }
-        qemu_lockcnt_inc_and_unlock(&ctx->list_lock);
+        qemu_mutex_unlock(&ctx->bh_lock);
     }
+
     return ret;
 }
 
@@ -193,9 +164,8 @@ aio_compute_timeout(AioContext *ctx)
     int timeout = -1;
     QEMUBH *bh;
 
-    for (bh = atomic_rcu_read(&ctx->first_bh); bh;
-         bh = atomic_rcu_read(&bh->next)) {
-        if (bh->scheduled) {
+    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 */
@@ -243,9 +213,9 @@ aio_ctx_check(GSource *source)
     aio_notify_accept(ctx);
 
     for (bh = ctx->first_bh; bh; bh = bh->next) {
-        if (bh->scheduled) {
+        if (!bh->deleted && bh->scheduled) {
             return true;
-        }
+	}
     }
     return aio_pending(ctx) || (timerlistgroup_deadline_ns(&ctx->tlg) == 0);
 }
@@ -267,21 +237,10 @@ aio_ctx_finalize(GSource     *source)
 {
     AioContext *ctx = (AioContext *) source;
 
+    qemu_bh_delete(ctx->notify_dummy_bh);
     thread_pool_free(ctx->thread_pool);
 
-#ifdef CONFIG_LINUX_AIO
-    if (ctx->linux_aio) {
-        laio_detach_aio_context(ctx->linux_aio, ctx);
-        laio_cleanup(ctx->linux_aio);
-        ctx->linux_aio = NULL;
-    }
-#endif
-
-    assert(QSLIST_EMPTY(&ctx->scheduled_coroutines));
-    qemu_bh_delete(ctx->co_schedule_bh);
-
-    qemu_lockcnt_lock(&ctx->list_lock);
-    assert(!qemu_lockcnt_count(&ctx->list_lock));
+    qemu_mutex_lock(&ctx->bh_lock);
     while (ctx->first_bh) {
         QEMUBH *next = ctx->first_bh->next;
 
@@ -291,12 +250,12 @@ aio_ctx_finalize(GSource     *source)
         g_free(ctx->first_bh);
         ctx->first_bh = next;
     }
-    qemu_lockcnt_unlock(&ctx->list_lock);
+    qemu_mutex_unlock(&ctx->bh_lock);
 
-    aio_set_event_notifier(ctx, &ctx->notifier, false, NULL, NULL);
+    aio_set_event_notifier(ctx, &ctx->notifier, false, NULL);
     event_notifier_cleanup(&ctx->notifier);
-    qemu_rec_mutex_destroy(&ctx->lock);
-    qemu_lockcnt_destroy(&ctx->list_lock);
+    rfifolock_destroy(&ctx->lock);
+    qemu_mutex_destroy(&ctx->bh_lock);
     timerlistgroup_deinit(&ctx->tlg);
 }
 
@@ -321,17 +280,6 @@ ThreadPool *aio_get_thread_pool(AioContext *ctx)
     return ctx->thread_pool;
 }
 
-#ifdef CONFIG_LINUX_AIO
-LinuxAioState *aio_get_linux_aio(AioContext *ctx)
-{
-    if (!ctx->linux_aio) {
-        ctx->linux_aio = laio_init();
-        laio_attach_aio_context(ctx->linux_aio, ctx);
-    }
-    return ctx->linux_aio;
-}
-#endif
-
 void aio_notify(AioContext *ctx)
 {
     /* Write e.g. bh->scheduled before reading ctx->notify_me.  Pairs
@@ -351,83 +299,56 @@ void aio_notify_accept(AioContext *ctx)
     }
 }
 
-static void aio_timerlist_notify(void *opaque, QEMUClockType type)
+static void aio_timerlist_notify(void *opaque)
 {
     aio_notify(opaque);
 }
 
+static void aio_rfifolock_cb(void *opaque)
+{
+    AioContext *ctx = opaque;
+
+    /* Kick owner thread in case they are blocked in aio_poll() */
+    qemu_bh_schedule(ctx->notify_dummy_bh);
+}
+
+static void notify_dummy_bh(void *opaque)
+{
+    /* Do nothing, we were invoked just to force the event loop to iterate */
+}
+
 static void event_notifier_dummy_cb(EventNotifier *e)
 {
 }
 
-/* Returns true if aio_notify() was called (e.g. a BH was scheduled) */
-static bool event_notifier_poll(void *opaque)
-{
-    EventNotifier *e = opaque;
-    AioContext *ctx = container_of(e, AioContext, notifier);
-
-    return atomic_read(&ctx->notified);
-}
-
-static void co_schedule_bh_cb(void *opaque)
-{
-    AioContext *ctx = opaque;
-    QSLIST_HEAD(, Coroutine) straight, reversed;
-
-    QSLIST_MOVE_ATOMIC(&reversed, &ctx->scheduled_coroutines);
-    QSLIST_INIT(&straight);
-
-    while (!QSLIST_EMPTY(&reversed)) {
-        Coroutine *co = QSLIST_FIRST(&reversed);
-        QSLIST_REMOVE_HEAD(&reversed, co_scheduled_next);
-        QSLIST_INSERT_HEAD(&straight, co, co_scheduled_next);
-    }
-
-    while (!QSLIST_EMPTY(&straight)) {
-        Coroutine *co = QSLIST_FIRST(&straight);
-        QSLIST_REMOVE_HEAD(&straight, co_scheduled_next);
-        trace_aio_co_schedule_bh_cb(ctx, co);
-        aio_context_acquire(ctx);
-        qemu_coroutine_enter(co);
-        aio_context_release(ctx);
-    }
-}
-
 AioContext *aio_context_new(Error **errp)
 {
     int ret;
     AioContext *ctx;
+    Error *local_err = NULL;
 
     ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext));
-    aio_context_setup(ctx);
-
+    aio_context_setup(ctx, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        goto fail;
+    }
     ret = event_notifier_init(&ctx->notifier, false);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Failed to initialize event notifier");
         goto fail;
     }
     g_source_set_can_recurse(&ctx->source, true);
-    qemu_lockcnt_init(&ctx->list_lock);
-
-    ctx->co_schedule_bh = aio_bh_new(ctx, co_schedule_bh_cb, ctx);
-    QSLIST_INIT(&ctx->scheduled_coroutines);
-
     aio_set_event_notifier(ctx, &ctx->notifier,
                            false,
                            (EventNotifierHandler *)
-                           event_notifier_dummy_cb,
-                           event_notifier_poll);
-#ifdef CONFIG_LINUX_AIO
-    ctx->linux_aio = NULL;
-#endif
+                           event_notifier_dummy_cb);
     ctx->thread_pool = NULL;
-    qemu_rec_mutex_init(&ctx->lock);
+    qemu_mutex_init(&ctx->bh_lock);
+    rfifolock_init(&ctx->lock, aio_rfifolock_cb, ctx);
     timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);
 
-    ctx->poll_ns = 0;
-    ctx->poll_max_ns = 0;
-    ctx->poll_grow = 0;
-    ctx->poll_shrink = 0;
+    ctx->notify_dummy_bh = aio_bh_new(ctx, notify_dummy_bh, NULL);
 
     return ctx;
 fail:
@@ -435,45 +356,6 @@ fail:
     return NULL;
 }
 
-void aio_co_schedule(AioContext *ctx, Coroutine *co)
-{
-    trace_aio_co_schedule(ctx, co);
-    QSLIST_INSERT_HEAD_ATOMIC(&ctx->scheduled_coroutines,
-                              co, co_scheduled_next);
-    qemu_bh_schedule(ctx->co_schedule_bh);
-}
-
-void aio_co_wake(struct Coroutine *co)
-{
-    AioContext *ctx;
-
-    /* Read coroutine before co->ctx.  Matches smp_wmb in
-     * qemu_coroutine_enter.
-     */
-    smp_read_barrier_depends();
-    ctx = atomic_read(&co->ctx);
-
-    aio_co_enter(ctx, co);
-}
-
-void aio_co_enter(AioContext *ctx, struct Coroutine *co)
-{
-    if (ctx != qemu_get_current_aio_context()) {
-        aio_co_schedule(ctx, co);
-        return;
-    }
-
-    if (qemu_in_coroutine()) {
-        Coroutine *self = qemu_coroutine_self();
-        assert(self != co);
-        QSIMPLEQ_INSERT_TAIL(&self->co_queue_wakeup, co, co_queue_next);
-    } else {
-        aio_context_acquire(ctx);
-        qemu_aio_coroutine_enter(ctx, co);
-        aio_context_release(ctx);
-    }
-}
-
 void aio_context_ref(AioContext *ctx)
 {
     g_source_ref(&ctx->source);
@@ -486,10 +368,10 @@ void aio_context_unref(AioContext *ctx)
 
 void aio_context_acquire(AioContext *ctx)
 {
-    qemu_rec_mutex_lock(&ctx->lock);
+    rfifolock_lock(&ctx->lock);
 }
 
 void aio_context_release(AioContext *ctx)
 {
-    qemu_rec_mutex_unlock(&ctx->lock);
+    rfifolock_unlock(&ctx->lock);
 }

atomic_template.h

@@ -1,215 +0,0 @@
-/*
- * Atomic helper templates
- * Included from tcg-runtime.c and cputlb.c.
- *
- * Copyright (c) 2016 Red Hat, Inc
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this library; if not, see <http://www.gnu.org/licenses/>.
- */
-
-#if DATA_SIZE == 16
-# define SUFFIX     o
-# define DATA_TYPE  Int128
-# define BSWAP      bswap128
-#elif DATA_SIZE == 8
-# define SUFFIX     q
-# define DATA_TYPE  uint64_t
-# define BSWAP      bswap64
-#elif DATA_SIZE == 4
-# define SUFFIX     l
-# define DATA_TYPE  uint32_t
-# define BSWAP      bswap32
-#elif DATA_SIZE == 2
-# define SUFFIX     w
-# define DATA_TYPE  uint16_t
-# define BSWAP      bswap16
-#elif DATA_SIZE == 1
-# define SUFFIX     b
-# define DATA_TYPE  uint8_t
-# define BSWAP
-#else
-# error unsupported data size
-#endif
-
-#if DATA_SIZE >= 4
-# define ABI_TYPE  DATA_TYPE
-#else
-# define ABI_TYPE  uint32_t
-#endif
-
-/* Define host-endian atomic operations.  Note that END is used within
-   the ATOMIC_NAME macro, and redefined below.  */
-#if DATA_SIZE == 1
-# define END
-#elif defined(HOST_WORDS_BIGENDIAN)
-# define END  _be
-#else
-# define END  _le
-#endif
-
-ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
-                              ABI_TYPE cmpv, ABI_TYPE newv EXTRA_ARGS)
-{
-    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    return atomic_cmpxchg__nocheck(haddr, cmpv, newv);
-}
-
-#if DATA_SIZE >= 16
-ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr EXTRA_ARGS)
-{
-    DATA_TYPE val, *haddr = ATOMIC_MMU_LOOKUP;
-    __atomic_load(haddr, &val, __ATOMIC_RELAXED);
-    return val;
-}
-
-void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr,
-                     ABI_TYPE val EXTRA_ARGS)
-{
-    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    __atomic_store(haddr, &val, __ATOMIC_RELAXED);
-}
-#else
-ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr,
-                           ABI_TYPE val EXTRA_ARGS)
-{
-    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    return atomic_xchg__nocheck(haddr, val);
-}
-
-#define GEN_ATOMIC_HELPER(X)                                        \
-ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
-                 ABI_TYPE val EXTRA_ARGS)                           \
-{                                                                   \
-    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;                           \
-    return atomic_##X(haddr, val);                                  \
-}                                                                   \
-
-GEN_ATOMIC_HELPER(fetch_add)
-GEN_ATOMIC_HELPER(fetch_and)
-GEN_ATOMIC_HELPER(fetch_or)
-GEN_ATOMIC_HELPER(fetch_xor)
-GEN_ATOMIC_HELPER(add_fetch)
-GEN_ATOMIC_HELPER(and_fetch)
-GEN_ATOMIC_HELPER(or_fetch)
-GEN_ATOMIC_HELPER(xor_fetch)
-
-#undef GEN_ATOMIC_HELPER
-#endif /* DATA SIZE >= 16 */
-
-#undef END
-
-#if DATA_SIZE > 1
-
-/* Define reverse-host-endian atomic operations.  Note that END is used
-   within the ATOMIC_NAME macro.  */
-#ifdef HOST_WORDS_BIGENDIAN
-# define END  _le
-#else
-# define END  _be
-#endif
-
-ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
-                              ABI_TYPE cmpv, ABI_TYPE newv EXTRA_ARGS)
-{
-    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    return BSWAP(atomic_cmpxchg__nocheck(haddr, BSWAP(cmpv), BSWAP(newv)));
-}
-
-#if DATA_SIZE >= 16
-ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr EXTRA_ARGS)
-{
-    DATA_TYPE val, *haddr = ATOMIC_MMU_LOOKUP;
-    __atomic_load(haddr, &val, __ATOMIC_RELAXED);
-    return BSWAP(val);
-}
-
-void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr,
-                     ABI_TYPE val EXTRA_ARGS)
-{
-    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    val = BSWAP(val);
-    __atomic_store(haddr, &val, __ATOMIC_RELAXED);
-}
-#else
-ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr,
-                           ABI_TYPE val EXTRA_ARGS)
-{
-    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    return BSWAP(atomic_xchg__nocheck(haddr, BSWAP(val)));
-}
-
-#define GEN_ATOMIC_HELPER(X)                                        \
-ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
-                 ABI_TYPE val EXTRA_ARGS)                           \
-{                                                                   \
-    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;                           \
-    return BSWAP(atomic_##X(haddr, BSWAP(val)));                    \
-}
-
-GEN_ATOMIC_HELPER(fetch_and)
-GEN_ATOMIC_HELPER(fetch_or)
-GEN_ATOMIC_HELPER(fetch_xor)
-GEN_ATOMIC_HELPER(and_fetch)
-GEN_ATOMIC_HELPER(or_fetch)
-GEN_ATOMIC_HELPER(xor_fetch)
-
-#undef GEN_ATOMIC_HELPER
-
-/* Note that for addition, we need to use a separate cmpxchg loop instead
-   of bswaps for the reverse-host-endian helpers.  */
-ABI_TYPE ATOMIC_NAME(fetch_add)(CPUArchState *env, target_ulong addr,
-                         ABI_TYPE val EXTRA_ARGS)
-{
-    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    DATA_TYPE ldo, ldn, ret, sto;
-
-    ldo = atomic_read__nocheck(haddr);
-    while (1) {
-        ret = BSWAP(ldo);
-        sto = BSWAP(ret + val);
-        ldn = atomic_cmpxchg__nocheck(haddr, ldo, sto);
-        if (ldn == ldo) {
-            return ret;
-        }
-        ldo = ldn;
-    }
-}
-
-ABI_TYPE ATOMIC_NAME(add_fetch)(CPUArchState *env, target_ulong addr,
-                         ABI_TYPE val EXTRA_ARGS)
-{
-    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    DATA_TYPE ldo, ldn, ret, sto;
-
-    ldo = atomic_read__nocheck(haddr);
-    while (1) {
-        ret = BSWAP(ldo) + val;
-        sto = BSWAP(ret);
-        ldn = atomic_cmpxchg__nocheck(haddr, ldo, sto);
-        if (ldn == ldo) {
-            return ret;
-        }
-        ldo = ldn;
-    }
-}
-#endif /* DATA_SIZE >= 16 */
-
-#undef END
-#endif /* DATA_SIZE > 1 */
-
-#undef BSWAP
-#undef ABI_TYPE
-#undef DATA_TYPE
-#undef SUFFIX
-#undef DATA_SIZE

audio/alsaaudio.c

@@ -21,7 +21,6 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
 #include <alsa/asoundlib.h>
 #include "qemu-common.h"
 #include "qemu/main-loop.h"

audio/audio.c

@@ -21,14 +21,11 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
 #include "hw/hw.h"
 #include "audio.h"
 #include "monitor/monitor.h"
 #include "qemu/timer.h"
 #include "sysemu/sysemu.h"
-#include "qemu/cutils.h"
-#include "sysemu/replay.h"
 
 #define AUDIO_CAP "audio"
 #include "audio_int.h"
@@ -1113,7 +1110,7 @@ static int audio_is_timer_needed (void)
 static void audio_reset_timer (AudioState *s)
 {
     if (audio_is_timer_needed ()) {
-        timer_mod_anticipate_ns(s->ts,
+        timer_mod (s->ts,
             qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + conf.period.ticks);
     }
     else {
@@ -1132,6 +1129,8 @@ static void audio_timer (void *opaque)
  */
 int AUD_write (SWVoiceOut *sw, void *buf, int size)
 {
+    int bytes;
+
     if (!sw) {
         /* XXX: Consider options */
         return size;
@@ -1142,11 +1141,14 @@ int AUD_write (SWVoiceOut *sw, void *buf, int size)
         return 0;
     }
 
-    return sw->hw->pcm_ops->write(sw, buf, size);
+    bytes = sw->hw->pcm_ops->write (sw, buf, size);
+    return bytes;
 }
 
 int AUD_read (SWVoiceIn *sw, void *buf, int size)
 {
+    int bytes;
+
     if (!sw) {
         /* XXX: Consider options */
         return size;
@@ -1157,7 +1159,8 @@ int AUD_read (SWVoiceIn *sw, void *buf, int size)
         return 0;
     }
 
-    return sw->hw->pcm_ops->read(sw, buf, size);
+    bytes = sw->hw->pcm_ops->read (sw, buf, size);
+    return bytes;
 }
 
 int AUD_get_buffer_size_out (SWVoiceOut *sw)
@@ -1388,7 +1391,6 @@ static void audio_run_out (AudioState *s)
 
         prev_rpos = hw->rpos;
         played = hw->pcm_ops->run_out (hw, live);
-        replay_audio_out(&played);
         if (audio_bug (AUDIO_FUNC, hw->rpos >= hw->samples)) {
             dolog ("hw->rpos=%d hw->samples=%d played=%d\n",
                    hw->rpos, hw->samples, played);
@@ -1452,12 +1454,9 @@ static void audio_run_in (AudioState *s)
 
     while ((hw = audio_pcm_hw_find_any_enabled_in (hw))) {
         SWVoiceIn *sw;
-        int captured = 0, min;
+        int captured, min;
 
-        if (replay_mode != REPLAY_MODE_PLAY) {
-            captured = hw->pcm_ops->run_in(hw);
-        }
-        replay_audio_in(&captured, hw->conv_buf, &hw->wpos, hw->samples);
+        captured = hw->pcm_ops->run_in (hw);
 
         min = audio_pcm_hw_find_min_in (hw);
         hw->total_samples_captured += captured - min;
@@ -1744,21 +1743,13 @@ static void audio_vm_change_state_handler (void *opaque, int running,
     audio_reset_timer (s);
 }
 
-static bool is_cleaning_up;
-
-bool audio_is_cleaning_up(void)
-{
-    return is_cleaning_up;
-}
-
-void audio_cleanup(void)
+static void audio_atexit (void)
 {
     AudioState *s = &glob_audio_state;
-    HWVoiceOut *hwo, *hwon;
-    HWVoiceIn *hwi, *hwin;
+    HWVoiceOut *hwo = NULL;
+    HWVoiceIn *hwi = NULL;
 
-    is_cleaning_up = true;
-    QLIST_FOREACH_SAFE(hwo, &glob_audio_state.hw_head_out, entries, hwon) {
+    while ((hwo = audio_pcm_hw_find_any_out (hwo))) {
         SWVoiceCap *sc;
 
         if (hwo->enabled) {
@@ -1774,20 +1765,17 @@ void audio_cleanup(void)
                 cb->ops.destroy (cb->opaque);
             }
         }
-        QLIST_REMOVE(hwo, entries);
     }
 
-    QLIST_FOREACH_SAFE(hwi, &glob_audio_state.hw_head_in, entries, hwin) {
+    while ((hwi = audio_pcm_hw_find_any_in (hwi))) {
         if (hwi->enabled) {
             hwi->pcm_ops->ctl_in (hwi, VOICE_DISABLE);
         }
         hwi->pcm_ops->fini_in (hwi);
-        QLIST_REMOVE(hwi, entries);
     }
 
     if (s->drv) {
         s->drv->fini (s->drv_opaque);
-        s->drv = NULL;
     }
 }
 
@@ -1815,9 +1803,12 @@ static void audio_init (void)
     QLIST_INIT (&s->hw_head_out);
     QLIST_INIT (&s->hw_head_in);
     QLIST_INIT (&s->cap_head);
-    atexit(audio_cleanup);
+    atexit (audio_atexit);
 
     s->ts = timer_new_ns(QEMU_CLOCK_VIRTUAL, audio_timer, s);
+    if (!s->ts) {
+        hw_error("Could not create audio timer\n");
+    }
 
     audio_process_options ("AUDIO", audio_options);
 
@@ -1868,8 +1859,12 @@ static void audio_init (void)
 
     if (!done) {
         done = !audio_driver_init (s, &no_audio_driver);
-        assert(done);
-        dolog("warning: Using timer based audio emulation\n");
+        if (!done) {
+            hw_error("Could not initialize audio subsystem\n");
+        }
+        else {
+            dolog ("warning: Using timer based audio emulation\n");
+        }
     }
 
     if (conf.period.hertz <= 0) {
@@ -1880,7 +1875,8 @@ static void audio_init (void)
         }
         conf.period.ticks = 1;
     } else {
-        conf.period.ticks = NANOSECONDS_PER_SECOND / conf.period.hertz;
+        conf.period.ticks =
+            muldiv64 (1, get_ticks_per_sec (), conf.period.hertz);
     }
 
     e = qemu_add_vm_change_state_handler (audio_vm_change_state_handler, s);
@@ -1982,7 +1978,8 @@ CaptureVoiceOut *AUD_add_capture (
         QLIST_INSERT_HEAD (&s->cap_head, cap, entries);
         QLIST_INSERT_HEAD (&cap->cb_head, cb, entries);
 
-        QLIST_FOREACH(hw, &glob_audio_state.hw_head_out, entries) {
+        hw = NULL;
+        while ((hw = audio_pcm_hw_find_any_out (hw))) {
             audio_attach_capture (hw);
         }
         return cap;
@@ -2028,8 +2025,6 @@ void AUD_del_capture (CaptureVoiceOut *cap, void *cb_opaque)
                     sw = sw1;
                 }
                 QLIST_REMOVE (cap, entries);
-                g_free (cap->hw.mix_buf);
-                g_free (cap->buf);
                 g_free (cap);
             }
             return;

audio/audio.h

@@ -21,10 +21,10 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-
 #ifndef QEMU_AUDIO_H
 #define QEMU_AUDIO_H
 
+#include "config-host.h"
 #include "qemu/queue.h"
 
 typedef void (*audio_callback_fn) (void *opaque, int avail);
@@ -163,12 +163,4 @@ static inline void *advance (void *p, int incr)
 int wav_start_capture (CaptureState *s, const char *path, int freq,
                        int bits, int nchannels);
 
-bool audio_is_cleaning_up(void);
-void audio_cleanup(void);
-
-void audio_sample_to_uint64(void *samples, int pos,
-                            uint64_t *left, uint64_t *right);
-void audio_sample_from_uint64(void *samples, int pos,
-                            uint64_t left, uint64_t right);
-
-#endif /* QEMU_AUDIO_H */
+#endif  /* audio.h */

audio/audio_int.h

@@ -21,7 +21,6 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-
 #ifndef QEMU_AUDIO_INT_H
 #define QEMU_AUDIO_INT_H
 
@@ -258,4 +257,4 @@ static inline int audio_ring_dist (int dst, int src, int len)
 #define AUDIO_FUNC __FILE__ ":" AUDIO_STRINGIFY (__LINE__)
 #endif
 
-#endif /* QEMU_AUDIO_INT_H */
+#endif /* audio_int.h */

audio/audio_pt_int.c

@@ -1,4 +1,3 @@
-#include "qemu/osdep.h"
 #include "qemu-common.h"
 #include "audio.h"
 

audio/audio_pt_int.h

@@ -19,4 +19,4 @@ int audio_pt_wait (struct audio_pt *, const char *);
 int audio_pt_unlock_and_signal (struct audio_pt *, const char *);
 int audio_pt_join (struct audio_pt *, void **, const char *);
 
-#endif /* QEMU_AUDIO_PT_INT_H */
+#endif /* audio_pt_int.h */

audio/audio_win_int.c

@@ -1,6 +1,5 @@
 /* public domain */
 
-#include "qemu/osdep.h"
 #include "qemu-common.h"
 
 #define AUDIO_CAP "win-int"

audio/coreaudio.c

@@ -22,8 +22,8 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
 #include <CoreAudio/CoreAudio.h>
+#include <string.h>             /* strerror */
 #include <pthread.h>            /* pthread_X */
 
 #include "qemu-common.h"
@@ -32,9 +32,7 @@
 #define AUDIO_CAP "coreaudio"
 #include "audio_int.h"
 
-#ifndef MAC_OS_X_VERSION_10_6
-#define MAC_OS_X_VERSION_10_6 1060
-#endif
+static int isAtexit;
 
 typedef struct {
     int buffer_frames;
@@ -47,233 +45,11 @@ typedef struct coreaudioVoiceOut {
     AudioDeviceID outputDeviceID;
     UInt32 audioDevicePropertyBufferFrameSize;
     AudioStreamBasicDescription outputStreamBasicDescription;
-    AudioDeviceIOProcID ioprocid;
     int live;
     int decr;
     int rpos;
 } coreaudioVoiceOut;
 
-#if MAC_OS_X_VERSION_MAX_ALLOWED >= MAC_OS_X_VERSION_10_6
-/* The APIs used here only become available from 10.6 */
-
-static OSStatus coreaudio_get_voice(AudioDeviceID *id)
-{
-    UInt32 size = sizeof(*id);
-    AudioObjectPropertyAddress addr = {
-        kAudioHardwarePropertyDefaultOutputDevice,
-        kAudioObjectPropertyScopeGlobal,
-        kAudioObjectPropertyElementMaster
-    };
-
-    return AudioObjectGetPropertyData(kAudioObjectSystemObject,
-                                      &addr,
-                                      0,
-                                      NULL,
-                                      &size,
-                                      id);
-}
-
-static OSStatus coreaudio_get_framesizerange(AudioDeviceID id,
-                                             AudioValueRange *framerange)
-{
-    UInt32 size = sizeof(*framerange);
-    AudioObjectPropertyAddress addr = {
-        kAudioDevicePropertyBufferFrameSizeRange,
-        kAudioDevicePropertyScopeOutput,
-        kAudioObjectPropertyElementMaster
-    };
-
-    return AudioObjectGetPropertyData(id,
-                                      &addr,
-                                      0,
-                                      NULL,
-                                      &size,
-                                      framerange);
-}
-
-static OSStatus coreaudio_get_framesize(AudioDeviceID id, UInt32 *framesize)
-{
-    UInt32 size = sizeof(*framesize);
-    AudioObjectPropertyAddress addr = {
-        kAudioDevicePropertyBufferFrameSize,
-        kAudioDevicePropertyScopeOutput,
-        kAudioObjectPropertyElementMaster
-    };
-
-    return AudioObjectGetPropertyData(id,
-                                      &addr,
-                                      0,
-                                      NULL,
-                                      &size,
-                                      framesize);
-}
-
-static OSStatus coreaudio_set_framesize(AudioDeviceID id, UInt32 *framesize)
-{
-    UInt32 size = sizeof(*framesize);
-    AudioObjectPropertyAddress addr = {
-        kAudioDevicePropertyBufferFrameSize,
-        kAudioDevicePropertyScopeOutput,
-        kAudioObjectPropertyElementMaster
-    };
-
-    return AudioObjectSetPropertyData(id,
-                                      &addr,
-                                      0,
-                                      NULL,
-                                      size,
-                                      framesize);
-}
-
-static OSStatus coreaudio_get_streamformat(AudioDeviceID id,
-                                           AudioStreamBasicDescription *d)
-{
-    UInt32 size = sizeof(*d);
-    AudioObjectPropertyAddress addr = {
-        kAudioDevicePropertyStreamFormat,
-        kAudioDevicePropertyScopeOutput,
-        kAudioObjectPropertyElementMaster
-    };
-
-    return AudioObjectGetPropertyData(id,
-                                      &addr,
-                                      0,
-                                      NULL,
-                                      &size,
-                                      d);
-}
-
-static OSStatus coreaudio_set_streamformat(AudioDeviceID id,
-                                           AudioStreamBasicDescription *d)
-{
-    UInt32 size = sizeof(*d);
-    AudioObjectPropertyAddress addr = {
-        kAudioDevicePropertyStreamFormat,
-        kAudioDevicePropertyScopeOutput,
-        kAudioObjectPropertyElementMaster
-    };
-
-    return AudioObjectSetPropertyData(id,
-                                      &addr,
-                                      0,
-                                      NULL,
-                                      size,
-                                      d);
-}
-
-static OSStatus coreaudio_get_isrunning(AudioDeviceID id, UInt32 *result)
-{
-    UInt32 size = sizeof(*result);
-    AudioObjectPropertyAddress addr = {
-        kAudioDevicePropertyDeviceIsRunning,
-        kAudioDevicePropertyScopeOutput,
-        kAudioObjectPropertyElementMaster
-    };
-
-    return AudioObjectGetPropertyData(id,
-                                      &addr,
-                                      0,
-                                      NULL,
-                                      &size,
-                                      result);
-}
-#else
-/* Legacy versions of functions using deprecated APIs */
-
-static OSStatus coreaudio_get_voice(AudioDeviceID *id)
-{
-    UInt32 size = sizeof(*id);
-
-    return AudioHardwareGetProperty(
-        kAudioHardwarePropertyDefaultOutputDevice,
-        &size,
-        id);
-}
-
-static OSStatus coreaudio_get_framesizerange(AudioDeviceID id,
-                                             AudioValueRange *framerange)
-{
-    UInt32 size = sizeof(*framerange);
-
-    return AudioDeviceGetProperty(
-        id,
-        0,
-        0,
-        kAudioDevicePropertyBufferFrameSizeRange,
-        &size,
-        framerange);
-}
-
-static OSStatus coreaudio_get_framesize(AudioDeviceID id, UInt32 *framesize)
-{
-    UInt32 size = sizeof(*framesize);
-
-    return AudioDeviceGetProperty(
-        id,
-        0,
-        false,
-        kAudioDevicePropertyBufferFrameSize,
-        &size,
-        framesize);
-}
-
-static OSStatus coreaudio_set_framesize(AudioDeviceID id, UInt32 *framesize)
-{
-    UInt32 size = sizeof(*framesize);
-
-    return AudioDeviceSetProperty(
-        id,
-        NULL,
-        0,
-        false,
-        kAudioDevicePropertyBufferFrameSize,
-        size,
-        framesize);
-}
-
-static OSStatus coreaudio_get_streamformat(AudioDeviceID id,
-                                           AudioStreamBasicDescription *d)
-{
-    UInt32 size = sizeof(*d);
-
-    return AudioDeviceGetProperty(
-        id,
-        0,
-        false,
-        kAudioDevicePropertyStreamFormat,
-        &size,
-        d);
-}
-
-static OSStatus coreaudio_set_streamformat(AudioDeviceID id,
-                                           AudioStreamBasicDescription *d)
-{
-    UInt32 size = sizeof(*d);
-
-    return AudioDeviceSetProperty(
-        id,
-        0,
-        0,
-        0,
-        kAudioDevicePropertyStreamFormat,
-        size,
-        d);
-}
-
-static OSStatus coreaudio_get_isrunning(AudioDeviceID id, UInt32 *result)
-{
-    UInt32 size = sizeof(*result);
-
-    return AudioDeviceGetProperty(
-        id,
-        0,
-        0,
-        kAudioDevicePropertyDeviceIsRunning,
-        &size,
-        result);
-}
-#endif
-
 static void coreaudio_logstatus (OSStatus status)
 {
     const char *str = "BUG";
@@ -368,7 +144,10 @@ static inline UInt32 isPlaying (AudioDeviceID outputDeviceID)
 {
     OSStatus status;
     UInt32 result = 0;
-    status = coreaudio_get_isrunning(outputDeviceID, &result);
+    UInt32 propertySize = sizeof(outputDeviceID);
+    status = AudioDeviceGetProperty(
+        outputDeviceID, 0, 0,
+        kAudioDevicePropertyDeviceIsRunning, &propertySize, &result);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr(status,
                          "Could not determine whether Device is playing\n");
@@ -376,6 +155,11 @@ static inline UInt32 isPlaying (AudioDeviceID outputDeviceID)
     return result;
 }
 
+static void coreaudio_atexit (void)
+{
+    isAtexit = 1;
+}
+
 static int coreaudio_lock (coreaudioVoiceOut *core, const char *fn_name)
 {
     int err;
@@ -504,6 +288,7 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
 {
     OSStatus status;
     coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw;
+    UInt32 propertySize;
     int err;
     const char *typ = "playback";
     AudioValueRange frameRange;
@@ -518,7 +303,12 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
 
     audio_pcm_init_info (&hw->info, as);
 
-    status = coreaudio_get_voice(&core->outputDeviceID);
+    /* open default output device */
+    propertySize = sizeof(core->outputDeviceID);
+    status = AudioHardwareGetProperty(
+        kAudioHardwarePropertyDefaultOutputDevice,
+        &propertySize,
+        &core->outputDeviceID);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ,
                            "Could not get default output Device\n");
@@ -530,8 +320,14 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
     }
 
     /* get minimum and maximum buffer frame sizes */
-    status = coreaudio_get_framesizerange(core->outputDeviceID,
-                                          &frameRange);
+    propertySize = sizeof(frameRange);
+    status = AudioDeviceGetProperty(
+        core->outputDeviceID,
+        0,
+        0,
+        kAudioDevicePropertyBufferFrameSizeRange,
+        &propertySize,
+        &frameRange);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ,
                            "Could not get device buffer frame range\n");
@@ -551,8 +347,15 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
     }
 
     /* set Buffer Frame Size */
-    status = coreaudio_set_framesize(core->outputDeviceID,
-                                     &core->audioDevicePropertyBufferFrameSize);
+    propertySize = sizeof(core->audioDevicePropertyBufferFrameSize);
+    status = AudioDeviceSetProperty(
+        core->outputDeviceID,
+        NULL,
+        0,
+        false,
+        kAudioDevicePropertyBufferFrameSize,
+        propertySize,
+        &core->audioDevicePropertyBufferFrameSize);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ,
                            "Could not set device buffer frame size %" PRIu32 "\n",
@@ -561,8 +364,14 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
     }
 
     /* get Buffer Frame Size */
-    status = coreaudio_get_framesize(core->outputDeviceID,
-                                     &core->audioDevicePropertyBufferFrameSize);
+    propertySize = sizeof(core->audioDevicePropertyBufferFrameSize);
+    status = AudioDeviceGetProperty(
+        core->outputDeviceID,
+        0,
+        false,
+        kAudioDevicePropertyBufferFrameSize,
+        &propertySize,
+        &core->audioDevicePropertyBufferFrameSize);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ,
                            "Could not get device buffer frame size\n");
@@ -571,8 +380,14 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
     hw->samples = conf->nbuffers * core->audioDevicePropertyBufferFrameSize;
 
     /* get StreamFormat */
-    status = coreaudio_get_streamformat(core->outputDeviceID,
-                                        &core->outputStreamBasicDescription);
+    propertySize = sizeof(core->outputStreamBasicDescription);
+    status = AudioDeviceGetProperty(
+        core->outputDeviceID,
+        0,
+        false,
+        kAudioDevicePropertyStreamFormat,
+        &propertySize,
+        &core->outputStreamBasicDescription);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ,
                            "Could not get Device Stream properties\n");
@@ -582,8 +397,15 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
 
     /* set Samplerate */
     core->outputStreamBasicDescription.mSampleRate = (Float64) as->freq;
-    status = coreaudio_set_streamformat(core->outputDeviceID,
-                                        &core->outputStreamBasicDescription);
+    propertySize = sizeof(core->outputStreamBasicDescription);
+    status = AudioDeviceSetProperty(
+        core->outputDeviceID,
+        0,
+        0,
+        0,
+        kAudioDevicePropertyStreamFormat,
+        propertySize,
+        &core->outputStreamBasicDescription);
     if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ, "Could not set samplerate %d\n",
                            as->freq);
@@ -592,12 +414,8 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
     }
 
     /* set Callback */
-    core->ioprocid = NULL;
-    status = AudioDeviceCreateIOProcID(core->outputDeviceID,
-                                       audioDeviceIOProc,
-                                       hw,
-                                       &core->ioprocid);
-    if (status != kAudioHardwareNoError || core->ioprocid == NULL) {
+    status = AudioDeviceAddIOProc(core->outputDeviceID, audioDeviceIOProc, hw);
+    if (status != kAudioHardwareNoError) {
         coreaudio_logerr2 (status, typ, "Could not set IOProc\n");
         core->outputDeviceID = kAudioDeviceUnknown;
         return -1;
@@ -605,10 +423,10 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
 
     /* start Playback */
     if (!isPlaying(core->outputDeviceID)) {
-        status = AudioDeviceStart(core->outputDeviceID, core->ioprocid);
+        status = AudioDeviceStart(core->outputDeviceID, audioDeviceIOProc);
         if (status != kAudioHardwareNoError) {
             coreaudio_logerr2 (status, typ, "Could not start playback\n");
-            AudioDeviceDestroyIOProcID(core->outputDeviceID, core->ioprocid);
+            AudioDeviceRemoveIOProc(core->outputDeviceID, audioDeviceIOProc);
             core->outputDeviceID = kAudioDeviceUnknown;
             return -1;
         }
@@ -623,18 +441,18 @@ static void coreaudio_fini_out (HWVoiceOut *hw)
     int err;
     coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw;
 
-    if (!audio_is_cleaning_up()) {
+    if (!isAtexit) {
         /* stop playback */
         if (isPlaying(core->outputDeviceID)) {
-            status = AudioDeviceStop(core->outputDeviceID, core->ioprocid);
+            status = AudioDeviceStop(core->outputDeviceID, audioDeviceIOProc);
             if (status != kAudioHardwareNoError) {
                 coreaudio_logerr (status, "Could not stop playback\n");
             }
         }
 
         /* remove callback */
-        status = AudioDeviceDestroyIOProcID(core->outputDeviceID,
-                                            core->ioprocid);
+        status = AudioDeviceRemoveIOProc(core->outputDeviceID,
+                                         audioDeviceIOProc);
         if (status != kAudioHardwareNoError) {
             coreaudio_logerr (status, "Could not remove IOProc\n");
         }
@@ -657,7 +475,7 @@ static int coreaudio_ctl_out (HWVoiceOut *hw, int cmd, ...)
     case VOICE_ENABLE:
         /* start playback */
         if (!isPlaying(core->outputDeviceID)) {
-            status = AudioDeviceStart(core->outputDeviceID, core->ioprocid);
+            status = AudioDeviceStart(core->outputDeviceID, audioDeviceIOProc);
             if (status != kAudioHardwareNoError) {
                 coreaudio_logerr (status, "Could not resume playback\n");
             }
@@ -666,10 +484,9 @@ static int coreaudio_ctl_out (HWVoiceOut *hw, int cmd, ...)
 
     case VOICE_DISABLE:
         /* stop playback */
-        if (!audio_is_cleaning_up()) {
+        if (!isAtexit) {
             if (isPlaying(core->outputDeviceID)) {
-                status = AudioDeviceStop(core->outputDeviceID,
-                                         core->ioprocid);
+                status = AudioDeviceStop(core->outputDeviceID, audioDeviceIOProc);
                 if (status != kAudioHardwareNoError) {
                     coreaudio_logerr (status, "Could not pause playback\n");
                 }
@@ -690,6 +507,7 @@ static void *coreaudio_audio_init (void)
     CoreaudioConf *conf = g_malloc(sizeof(CoreaudioConf));
     *conf = glob_conf;
 
+    atexit(coreaudio_atexit);
     return conf;
 }
 

audio/dsoundaudio.c

@@ -26,7 +26,6 @@
  * SEAL 1.07 by Carlos 'pel' Hasan was used as documentation
  */
 
-#include "qemu/osdep.h"
 #include "qemu-common.h"
 #include "audio.h"
 

audio/mixeng.c

@@ -22,10 +22,7 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
 #include "qemu-common.h"
-#include "qemu/bswap.h"
-#include "qemu/error-report.h"
 #include "audio.h"
 
 #define AUDIO_CAP "mixeng"
@@ -268,42 +265,11 @@ f_sample *mixeng_clip[2][2][2][3] = {
     }
 };
 
-
-void audio_sample_to_uint64(void *samples, int pos,
-                            uint64_t *left, uint64_t *right)
-{
-    struct st_sample *sample = samples;
-    sample += pos;
-#ifdef FLOAT_MIXENG
-    error_report(
-        "Coreaudio and floating point samples are not supported by replay yet");
-    abort();
-#else
-    *left = sample->l;
-    *right = sample->r;
-#endif
-}
-
-void audio_sample_from_uint64(void *samples, int pos,
-                            uint64_t left, uint64_t right)
-{
-    struct st_sample *sample = samples;
-    sample += pos;
-#ifdef FLOAT_MIXENG
-    error_report(
-        "Coreaudio and floating point samples are not supported by replay yet");
-    abort();
-#else
-    sample->l = left;
-    sample->r = right;
-#endif
-}
-
 /*
  * August 21, 1998
  * Copyright 1998 Fabrice Bellard.
  *
- * [Rewrote completely the code of Lance Norskog And Sundry
+ * [Rewrote completly the code of Lance Norskog And Sundry
  * Contributors with a more efficient algorithm.]
  *
  * This source code is freely redistributable and may be used for

audio/mixeng.h

@@ -21,7 +21,6 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-
 #ifndef QEMU_MIXENG_H
 #define QEMU_MIXENG_H
 
@@ -49,4 +48,4 @@ void st_rate_stop (void *opaque);
 void mixeng_clear (struct st_sample *buf, int len);
 void mixeng_volume (struct st_sample *buf, int len, struct mixeng_volume *vol);
 
-#endif /* QEMU_MIXENG_H */
+#endif  /* mixeng.h */

audio/noaudio.c

@@ -21,9 +21,7 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
 #include "qemu-common.h"
-#include "qemu/host-utils.h"
 #include "audio.h"
 #include "qemu/timer.h"
 
@@ -50,8 +48,8 @@ static int no_run_out (HWVoiceOut *hw, int live)
 
     now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
     ticks = now - no->old_ticks;
-    bytes = muldiv64(ticks, hw->info.bytes_per_second, NANOSECONDS_PER_SECOND);
-    bytes = audio_MIN(bytes, INT_MAX);
+    bytes = muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());
+    bytes = audio_MIN (bytes, INT_MAX);
     samples = bytes >> hw->info.shift;
 
     no->old_ticks = now;
@@ -62,7 +60,7 @@ static int no_run_out (HWVoiceOut *hw, int live)
 
 static int no_write (SWVoiceOut *sw, void *buf, int len)
 {
-    return audio_pcm_sw_write(sw, buf, len);
+    return audio_pcm_sw_write (sw, buf, len);
 }
 
 static int no_init_out(HWVoiceOut *hw, struct audsettings *as, void *drv_opaque)
@@ -107,7 +105,7 @@ static int no_run_in (HWVoiceIn *hw)
         int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
         int64_t ticks = now - no->old_ticks;
         int64_t bytes =
-            muldiv64(ticks, hw->info.bytes_per_second, NANOSECONDS_PER_SECOND);
+            muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());
 
         no->old_ticks = now;
         bytes = audio_MIN (bytes, INT_MAX);

audio/ossaudio.c

@@ -21,7 +21,9 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <sys/types.h>
 #include <sys/ioctl.h>
 #include <sys/soundcard.h>
 #include "qemu-common.h"
@@ -897,7 +899,7 @@ static struct audio_option oss_options[] = {
         .name  = "EXCLUSIVE",
         .tag   = AUD_OPT_BOOL,
         .valp  = &glob_conf.exclusive,
-        .descr = "Open device in exclusive mode (vmix won't work)"
+        .descr = "Open device in exclusive mode (vmix wont work)"
     },
 #ifdef USE_DSP_POLICY
     {

audio/paaudio.c

@@ -1,5 +1,4 @@
 /* public domain */
-#include "qemu/osdep.h"
 #include "qemu-common.h"
 #include "audio.h"
 
@@ -781,22 +780,23 @@ static int qpa_ctl_in (HWVoiceIn *hw, int cmd, ...)
 
             pa_threaded_mainloop_lock (g->mainloop);
 
-            op = pa_context_set_source_output_volume (g->context,
-                pa_stream_get_index (pa->stream),
+            /* FIXME: use the upcoming "set_source_output_{volume,mute}" */
+            op = pa_context_set_source_volume_by_index (g->context,
+                pa_stream_get_device_index (pa->stream),
                 &v, NULL, NULL);
             if (!op) {
                 qpa_logerr (pa_context_errno (g->context),
-                            "set_source_output_volume() failed\n");
+                            "set_source_volume() failed\n");
             } else {
                 pa_operation_unref(op);
             }
 
-            op = pa_context_set_source_output_mute (g->context,
+            op = pa_context_set_source_mute_by_index (g->context,
                 pa_stream_get_index (pa->stream),
                 sw->vol.mute, NULL, NULL);
             if (!op) {
                 qpa_logerr (pa_context_errno (g->context),
-                            "set_source_output_mute() failed\n");
+                            "set_source_mute() failed\n");
             } else {
                 pa_operation_unref (op);
             }

audio/sdlaudio.c

@@ -21,7 +21,6 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
 #include <SDL.h>
 #include <SDL_thread.h>
 #include "qemu-common.h"
@@ -38,14 +37,10 @@
 #define AUDIO_CAP "sdl"
 #include "audio_int.h"
 
-#define USE_SEMAPHORE (SDL_MAJOR_VERSION < 2)
-
 typedef struct SDLVoiceOut {
     HWVoiceOut hw;
     int live;
-#if USE_SEMAPHORE
     int rpos;
-#endif
     int decr;
 } SDLVoiceOut;
 
@@ -57,10 +52,8 @@ static struct {
 
 static struct SDLAudioState {
     int exit;
-#if USE_SEMAPHORE
     SDL_mutex *mutex;
     SDL_sem *sem;
-#endif
     int initialized;
     bool driver_created;
 } glob_sdl;
@@ -79,45 +72,31 @@ static void GCC_FMT_ATTR (1, 2) sdl_logerr (const char *fmt, ...)
 
 static int sdl_lock (SDLAudioState *s, const char *forfn)
 {
-#if USE_SEMAPHORE
     if (SDL_LockMutex (s->mutex)) {
         sdl_logerr ("SDL_LockMutex for %s failed\n", forfn);
         return -1;
     }
-#else
-    SDL_LockAudio();
-#endif
-
     return 0;
 }
 
 static int sdl_unlock (SDLAudioState *s, const char *forfn)
 {
-#if USE_SEMAPHORE
     if (SDL_UnlockMutex (s->mutex)) {
         sdl_logerr ("SDL_UnlockMutex for %s failed\n", forfn);
         return -1;
     }
-#else
-    SDL_UnlockAudio();
-#endif
-
     return 0;
 }
 
 static int sdl_post (SDLAudioState *s, const char *forfn)
 {
-#if USE_SEMAPHORE
     if (SDL_SemPost (s->sem)) {
         sdl_logerr ("SDL_SemPost for %s failed\n", forfn);
         return -1;
     }
-#endif
-
     return 0;
 }
 
-#if USE_SEMAPHORE
 static int sdl_wait (SDLAudioState *s, const char *forfn)
 {
     if (SDL_SemWait (s->sem)) {
@@ -126,7 +105,6 @@ static int sdl_wait (SDLAudioState *s, const char *forfn)
     }
     return 0;
 }
-#endif
 
 static int sdl_unlock_and_post (SDLAudioState *s, const char *forfn)
 {
@@ -267,7 +245,6 @@ static void sdl_callback (void *opaque, Uint8 *buf, int len)
         int to_mix, decr;
 
         /* dolog ("in callback samples=%d\n", samples); */
-#if USE_SEMAPHORE
         sdl_wait (s, "sdl_callback");
         if (s->exit) {
             return;
@@ -286,11 +263,6 @@ static void sdl_callback (void *opaque, Uint8 *buf, int len)
         if (!sdl->live) {
             goto again;
         }
-#else
-        if (s->exit || !sdl->live) {
-            break;
-        }
-#endif
 
         /* dolog ("in callback live=%d\n", live); */
         to_mix = audio_MIN (samples, sdl->live);
@@ -301,11 +273,7 @@ static void sdl_callback (void *opaque, Uint8 *buf, int len)
 
             /* dolog ("in callback to_mix %d, chunk %d\n", to_mix, chunk); */
             hw->clip (buf, src, chunk);
-#if USE_SEMAPHORE
             sdl->rpos = (sdl->rpos + chunk) % hw->samples;
-#else
-            hw->rpos = (hw->rpos + chunk) % hw->samples;
-#endif
             to_mix -= chunk;
             buf += chunk << hw->info.shift;
         }
@@ -313,21 +281,12 @@ static void sdl_callback (void *opaque, Uint8 *buf, int len)
         sdl->live -= decr;
         sdl->decr += decr;
 
-#if USE_SEMAPHORE
     again:
         if (sdl_unlock (s, "sdl_callback")) {
             return;
         }
-#endif
     }
     /* dolog ("done len=%d\n", len); */
-
-#if (SDL_MAJOR_VERSION >= 2)
-    /* SDL2 does not clear the remaining buffer for us, so do it on our own */
-    if (samples) {
-        memset(buf, 0, samples << hw->info.shift);
-    }
-#endif
 }
 
 static int sdl_write_out (SWVoiceOut *sw, void *buf, int len)
@@ -355,12 +314,8 @@ static int sdl_run_out (HWVoiceOut *hw, int live)
     decr = audio_MIN (sdl->decr, live);
     sdl->decr -= decr;
 
-#if USE_SEMAPHORE
     sdl->live = live - decr;
     hw->rpos = sdl->rpos;
-#else
-    sdl->live = live;
-#endif
 
     if (sdl->live > 0) {
         sdl_unlock_and_post (s, "sdl_run_out");
@@ -449,7 +404,6 @@ static void *sdl_audio_init (void)
         return NULL;
     }
 
-#if USE_SEMAPHORE
     s->mutex = SDL_CreateMutex ();
     if (!s->mutex) {
         sdl_logerr ("Failed to create SDL mutex\n");
@@ -464,7 +418,6 @@ static void *sdl_audio_init (void)
         SDL_QuitSubSystem (SDL_INIT_AUDIO);
         return NULL;
     }
-#endif
 
     s->driver_created = true;
     return s;
@@ -474,10 +427,8 @@ static void sdl_audio_fini (void *opaque)
 {
     SDLAudioState *s = opaque;
     sdl_close (s);
-#if USE_SEMAPHORE
     SDL_DestroySemaphore (s->sem);
     SDL_DestroyMutex (s->mutex);
-#endif
     SDL_QuitSubSystem (SDL_INIT_AUDIO);
     s->driver_created = false;
 }

audio/spiceaudio.c

@@ -17,9 +17,7 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "qemu/osdep.h"
 #include "hw/hw.h"
-#include "qemu/host-utils.h"
 #include "qemu/error-report.h"
 #include "qemu/timer.h"
 #include "ui/qemu-spice.h"
@@ -105,11 +103,11 @@ static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)
 
     now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
     ticks = now - rate->start_ticks;
-    bytes = muldiv64(ticks, info->bytes_per_second, NANOSECONDS_PER_SECOND);
+    bytes = muldiv64 (ticks, info->bytes_per_second, get_ticks_per_sec ());
     samples = (bytes - rate->bytes_sent) >> info->shift;
     if (samples < 0 || samples > 65536) {
         error_report("Resetting rate control (%" PRId64 " samples)", samples);
-        rate_start(rate);
+        rate_start (rate);
         samples = 0;
     }
     rate->bytes_sent += samples << info->shift;

audio/trace-events

@@ -1,17 +0,0 @@
-# See docs/tracing.txt for syntax documentation.
-
-# audio/alsaaudio.c
-alsa_revents(int revents) "revents = %d"
-alsa_pollout(int i, int fd) "i = %d fd = %d"
-alsa_set_handler(int events, int index, int fd, int err) "events=%#x index=%d fd=%d err=%d"
-alsa_wrote_zero(int len) "Failed to write %d frames (wrote zero)"
-alsa_read_zero(long len) "Failed to read %ld frames (read zero)"
-alsa_xrun_out(void) "Recovering from playback xrun"
-alsa_xrun_in(void) "Recovering from capture xrun"
-alsa_resume_out(void) "Resuming suspended output stream"
-alsa_resume_in(void) "Resuming suspended input stream"
-alsa_no_frames(int state) "No frames available and ALSA state is %d"
-
-# audio/ossaudio.c
-oss_version(int version) "OSS version = %#x"
-oss_invalid_available_size(int size, int bufsize) "Invalid available size, size=%d bufsize=%d"

audio/wavaudio.c

@@ -21,8 +21,7 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
-#include "qemu/host-utils.h"
+#include "hw/hw.h"
 #include "qemu/timer.h"
 #include "audio.h"
 
@@ -51,7 +50,7 @@ static int wav_run_out (HWVoiceOut *hw, int live)
     int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
     int64_t ticks = now - wav->old_ticks;
     int64_t bytes =
-        muldiv64(ticks, hw->info.bytes_per_second, NANOSECONDS_PER_SECOND);
+        muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());
 
     if (bytes > INT_MAX) {
         samples = INT_MAX >> hw->info.shift;

audio/wavcapture.c

@@ -1,4 +1,3 @@
-#include "qemu/osdep.h"
 #include "hw/hw.h"
 #include "monitor/monitor.h"
 #include "qemu/error-report.h"
@@ -88,7 +87,6 @@ static void wav_capture_destroy (void *opaque)
     WAVState *wav = opaque;
 
     AUD_del_capture (wav->cap, wav);
-    g_free (wav);
 }
 
 static void wav_capture_info (void *opaque)

backends/Makefile.objs

@@ -1,10 +1,11 @@
 common-obj-y += rng.o rng-egd.o
 common-obj-$(CONFIG_POSIX) += rng-random.o
 
+common-obj-y += msmouse.o testdev.o
+common-obj-$(CONFIG_BRLAPI) += baum.o
+baum.o-cflags := $(SDL_CFLAGS)
+
 common-obj-$(CONFIG_TPM) += tpm.o
 
 common-obj-y += hostmem.o hostmem-ram.o
 common-obj-$(CONFIG_LINUX) += hostmem-file.o
-
-common-obj-y += cryptodev.o
-common-obj-y += cryptodev-builtin.o

backends/baum.c

@@ -1,7 +1,7 @@
 /*
  * QEMU Baum Braille Device
  *
- * Copyright (c) 2008, 2010-2011, 2016 Samuel Thibault
+ * Copyright (c) 2008 Samuel Thibault
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this software and associated documentation files (the "Software"), to deal
@@ -21,16 +21,16 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
-#include "qapi/error.h"
 #include "qemu-common.h"
-#include "chardev/char.h"
+#include "sysemu/char.h"
 #include "qemu/timer.h"
 #include "hw/usb.h"
-#include "ui/console.h"
 #include <brlapi.h>
 #include <brlapi_constants.h>
 #include <brlapi_keycodes.h>
+#ifdef CONFIG_SDL
+#include <SDL_syswm.h>
+#endif
 
 #if 0
 #define DPRINTF(fmt, ...) \
@@ -85,12 +85,11 @@
 #define BUF_SIZE 256
 
 typedef struct {
-    Chardev parent;
+    CharDriverState *chr;
 
     brlapi_handle_t *brlapi;
     int brlapi_fd;
     unsigned int x, y;
-    bool deferred_init;
 
     uint8_t in_buf[BUF_SIZE];
     uint8_t in_buf_used;
@@ -98,17 +97,11 @@ typedef struct {
     uint8_t out_buf_used, out_buf_ptr;
 
     QEMUTimer *cellCount_timer;
-} BaumChardev;
-
-#define TYPE_CHARDEV_BRAILLE "chardev-braille"
-#define BAUM_CHARDEV(obj) OBJECT_CHECK(BaumChardev, (obj), TYPE_CHARDEV_BRAILLE)
+} BaumDriverState;
 
 /* Let's assume NABCC by default */
-enum way {
-    DOTS2ASCII,
-    ASCII2DOTS
-};
-static const uint8_t nabcc_translation[2][256] = {
+static const uint8_t nabcc_translation[256] = {
+    [0] = ' ',
 #ifndef BRLAPI_DOTS
 #define BRLAPI_DOTS(d1,d2,d3,d4,d5,d6,d7,d8) \
     ((d1?BRLAPI_DOT1:0)|\
@@ -120,145 +113,111 @@ static const uint8_t nabcc_translation[2][256] = {
      (d7?BRLAPI_DOT7:0)|\
      (d8?BRLAPI_DOT8:0))
 #endif
-#define DO(dots, ascii) \
-    [DOTS2ASCII][dots] = ascii, \
-    [ASCII2DOTS][ascii] = dots
-    DO(0, ' '),
-    DO(BRLAPI_DOTS(1, 0, 0, 0, 0, 0, 0, 0), 'a'),
-    DO(BRLAPI_DOTS(1, 1, 0, 0, 0, 0, 0, 0), 'b'),
-    DO(BRLAPI_DOTS(1, 0, 0, 1, 0, 0, 0, 0), 'c'),
-    DO(BRLAPI_DOTS(1, 0, 0, 1, 1, 0, 0, 0), 'd'),
-    DO(BRLAPI_DOTS(1, 0, 0, 0, 1, 0, 0, 0), 'e'),
-    DO(BRLAPI_DOTS(1, 1, 0, 1, 0, 0, 0, 0), 'f'),
-    DO(BRLAPI_DOTS(1, 1, 0, 1, 1, 0, 0, 0), 'g'),
-    DO(BRLAPI_DOTS(1, 1, 0, 0, 1, 0, 0, 0), 'h'),
-    DO(BRLAPI_DOTS(0, 1, 0, 1, 0, 0, 0, 0), 'i'),
-    DO(BRLAPI_DOTS(0, 1, 0, 1, 1, 0, 0, 0), 'j'),
-    DO(BRLAPI_DOTS(1, 0, 1, 0, 0, 0, 0, 0), 'k'),
-    DO(BRLAPI_DOTS(1, 1, 1, 0, 0, 0, 0, 0), 'l'),
-    DO(BRLAPI_DOTS(1, 0, 1, 1, 0, 0, 0, 0), 'm'),
-    DO(BRLAPI_DOTS(1, 0, 1, 1, 1, 0, 0, 0), 'n'),
-    DO(BRLAPI_DOTS(1, 0, 1, 0, 1, 0, 0, 0), 'o'),
-    DO(BRLAPI_DOTS(1, 1, 1, 1, 0, 0, 0, 0), 'p'),
-    DO(BRLAPI_DOTS(1, 1, 1, 1, 1, 0, 0, 0), 'q'),
-    DO(BRLAPI_DOTS(1, 1, 1, 0, 1, 0, 0, 0), 'r'),
-    DO(BRLAPI_DOTS(0, 1, 1, 1, 0, 0, 0, 0), 's'),
-    DO(BRLAPI_DOTS(0, 1, 1, 1, 1, 0, 0, 0), 't'),
-    DO(BRLAPI_DOTS(1, 0, 1, 0, 0, 1, 0, 0), 'u'),
-    DO(BRLAPI_DOTS(1, 1, 1, 0, 0, 1, 0, 0), 'v'),
-    DO(BRLAPI_DOTS(0, 1, 0, 1, 1, 1, 0, 0), 'w'),
-    DO(BRLAPI_DOTS(1, 0, 1, 1, 0, 1, 0, 0), 'x'),
-    DO(BRLAPI_DOTS(1, 0, 1, 1, 1, 1, 0, 0), 'y'),
-    DO(BRLAPI_DOTS(1, 0, 1, 0, 1, 1, 0, 0), 'z'),
+    [BRLAPI_DOTS(1,0,0,0,0,0,0,0)] = 'a',
+    [BRLAPI_DOTS(1,1,0,0,0,0,0,0)] = 'b',
+    [BRLAPI_DOTS(1,0,0,1,0,0,0,0)] = 'c',
+    [BRLAPI_DOTS(1,0,0,1,1,0,0,0)] = 'd',
+    [BRLAPI_DOTS(1,0,0,0,1,0,0,0)] = 'e',
+    [BRLAPI_DOTS(1,1,0,1,0,0,0,0)] = 'f',
+    [BRLAPI_DOTS(1,1,0,1,1,0,0,0)] = 'g',
+    [BRLAPI_DOTS(1,1,0,0,1,0,0,0)] = 'h',
+    [BRLAPI_DOTS(0,1,0,1,0,0,0,0)] = 'i',
+    [BRLAPI_DOTS(0,1,0,1,1,0,0,0)] = 'j',
+    [BRLAPI_DOTS(1,0,1,0,0,0,0,0)] = 'k',
+    [BRLAPI_DOTS(1,1,1,0,0,0,0,0)] = 'l',
+    [BRLAPI_DOTS(1,0,1,1,0,0,0,0)] = 'm',
+    [BRLAPI_DOTS(1,0,1,1,1,0,0,0)] = 'n',
+    [BRLAPI_DOTS(1,0,1,0,1,0,0,0)] = 'o',
+    [BRLAPI_DOTS(1,1,1,1,0,0,0,0)] = 'p',
+    [BRLAPI_DOTS(1,1,1,1,1,0,0,0)] = 'q',
+    [BRLAPI_DOTS(1,1,1,0,1,0,0,0)] = 'r',
+    [BRLAPI_DOTS(0,1,1,1,0,0,0,0)] = 's',
+    [BRLAPI_DOTS(0,1,1,1,1,0,0,0)] = 't',
+    [BRLAPI_DOTS(1,0,1,0,0,1,0,0)] = 'u',
+    [BRLAPI_DOTS(1,1,1,0,0,1,0,0)] = 'v',
+    [BRLAPI_DOTS(0,1,0,1,1,1,0,0)] = 'w',
+    [BRLAPI_DOTS(1,0,1,1,0,1,0,0)] = 'x',
+    [BRLAPI_DOTS(1,0,1,1,1,1,0,0)] = 'y',
+    [BRLAPI_DOTS(1,0,1,0,1,1,0,0)] = 'z',
 
-    DO(BRLAPI_DOTS(1, 0, 0, 0, 0, 0, 1, 0), 'A'),
-    DO(BRLAPI_DOTS(1, 1, 0, 0, 0, 0, 1, 0), 'B'),
-    DO(BRLAPI_DOTS(1, 0, 0, 1, 0, 0, 1, 0), 'C'),
-    DO(BRLAPI_DOTS(1, 0, 0, 1, 1, 0, 1, 0), 'D'),
-    DO(BRLAPI_DOTS(1, 0, 0, 0, 1, 0, 1, 0), 'E'),
-    DO(BRLAPI_DOTS(1, 1, 0, 1, 0, 0, 1, 0), 'F'),
-    DO(BRLAPI_DOTS(1, 1, 0, 1, 1, 0, 1, 0), 'G'),
-    DO(BRLAPI_DOTS(1, 1, 0, 0, 1, 0, 1, 0), 'H'),
-    DO(BRLAPI_DOTS(0, 1, 0, 1, 0, 0, 1, 0), 'I'),
-    DO(BRLAPI_DOTS(0, 1, 0, 1, 1, 0, 1, 0), 'J'),
-    DO(BRLAPI_DOTS(1, 0, 1, 0, 0, 0, 1, 0), 'K'),
-    DO(BRLAPI_DOTS(1, 1, 1, 0, 0, 0, 1, 0), 'L'),
-    DO(BRLAPI_DOTS(1, 0, 1, 1, 0, 0, 1, 0), 'M'),
-    DO(BRLAPI_DOTS(1, 0, 1, 1, 1, 0, 1, 0), 'N'),
-    DO(BRLAPI_DOTS(1, 0, 1, 0, 1, 0, 1, 0), 'O'),
-    DO(BRLAPI_DOTS(1, 1, 1, 1, 0, 0, 1, 0), 'P'),
-    DO(BRLAPI_DOTS(1, 1, 1, 1, 1, 0, 1, 0), 'Q'),
-    DO(BRLAPI_DOTS(1, 1, 1, 0, 1, 0, 1, 0), 'R'),
-    DO(BRLAPI_DOTS(0, 1, 1, 1, 0, 0, 1, 0), 'S'),
-    DO(BRLAPI_DOTS(0, 1, 1, 1, 1, 0, 1, 0), 'T'),
-    DO(BRLAPI_DOTS(1, 0, 1, 0, 0, 1, 1, 0), 'U'),
-    DO(BRLAPI_DOTS(1, 1, 1, 0, 0, 1, 1, 0), 'V'),
-    DO(BRLAPI_DOTS(0, 1, 0, 1, 1, 1, 1, 0), 'W'),
-    DO(BRLAPI_DOTS(1, 0, 1, 1, 0, 1, 1, 0), 'X'),
-    DO(BRLAPI_DOTS(1, 0, 1, 1, 1, 1, 1, 0), 'Y'),
-    DO(BRLAPI_DOTS(1, 0, 1, 0, 1, 1, 1, 0), 'Z'),
+    [BRLAPI_DOTS(1,0,0,0,0,0,1,0)] = 'A',
+    [BRLAPI_DOTS(1,1,0,0,0,0,1,0)] = 'B',
+    [BRLAPI_DOTS(1,0,0,1,0,0,1,0)] = 'C',
+    [BRLAPI_DOTS(1,0,0,1,1,0,1,0)] = 'D',
+    [BRLAPI_DOTS(1,0,0,0,1,0,1,0)] = 'E',
+    [BRLAPI_DOTS(1,1,0,1,0,0,1,0)] = 'F',
+    [BRLAPI_DOTS(1,1,0,1,1,0,1,0)] = 'G',
+    [BRLAPI_DOTS(1,1,0,0,1,0,1,0)] = 'H',
+    [BRLAPI_DOTS(0,1,0,1,0,0,1,0)] = 'I',
+    [BRLAPI_DOTS(0,1,0,1,1,0,1,0)] = 'J',
+    [BRLAPI_DOTS(1,0,1,0,0,0,1,0)] = 'K',
+    [BRLAPI_DOTS(1,1,1,0,0,0,1,0)] = 'L',
+    [BRLAPI_DOTS(1,0,1,1,0,0,1,0)] = 'M',
+    [BRLAPI_DOTS(1,0,1,1,1,0,1,0)] = 'N',
+    [BRLAPI_DOTS(1,0,1,0,1,0,1,0)] = 'O',
+    [BRLAPI_DOTS(1,1,1,1,0,0,1,0)] = 'P',
+    [BRLAPI_DOTS(1,1,1,1,1,0,1,0)] = 'Q',
+    [BRLAPI_DOTS(1,1,1,0,1,0,1,0)] = 'R',
+    [BRLAPI_DOTS(0,1,1,1,0,0,1,0)] = 'S',
+    [BRLAPI_DOTS(0,1,1,1,1,0,1,0)] = 'T',
+    [BRLAPI_DOTS(1,0,1,0,0,1,1,0)] = 'U',
+    [BRLAPI_DOTS(1,1,1,0,0,1,1,0)] = 'V',
+    [BRLAPI_DOTS(0,1,0,1,1,1,1,0)] = 'W',
+    [BRLAPI_DOTS(1,0,1,1,0,1,1,0)] = 'X',
+    [BRLAPI_DOTS(1,0,1,1,1,1,1,0)] = 'Y',
+    [BRLAPI_DOTS(1,0,1,0,1,1,1,0)] = 'Z',
 
-    DO(BRLAPI_DOTS(0, 0, 1, 0, 1, 1, 0, 0), '0'),
-    DO(BRLAPI_DOTS(0, 1, 0, 0, 0, 0, 0, 0), '1'),
-    DO(BRLAPI_DOTS(0, 1, 1, 0, 0, 0, 0, 0), '2'),
-    DO(BRLAPI_DOTS(0, 1, 0, 0, 1, 0, 0, 0), '3'),
-    DO(BRLAPI_DOTS(0, 1, 0, 0, 1, 1, 0, 0), '4'),
-    DO(BRLAPI_DOTS(0, 1, 0, 0, 0, 1, 0, 0), '5'),
-    DO(BRLAPI_DOTS(0, 1, 1, 0, 1, 0, 0, 0), '6'),
-    DO(BRLAPI_DOTS(0, 1, 1, 0, 1, 1, 0, 0), '7'),
-    DO(BRLAPI_DOTS(0, 1, 1, 0, 0, 1, 0, 0), '8'),
-    DO(BRLAPI_DOTS(0, 0, 1, 0, 1, 0, 0, 0), '9'),
+    [BRLAPI_DOTS(0,0,1,0,1,1,0,0)] = '0',
+    [BRLAPI_DOTS(0,1,0,0,0,0,0,0)] = '1',
+    [BRLAPI_DOTS(0,1,1,0,0,0,0,0)] = '2',
+    [BRLAPI_DOTS(0,1,0,0,1,0,0,0)] = '3',
+    [BRLAPI_DOTS(0,1,0,0,1,1,0,0)] = '4',
+    [BRLAPI_DOTS(0,1,0,0,0,1,0,0)] = '5',
+    [BRLAPI_DOTS(0,1,1,0,1,0,0,0)] = '6',
+    [BRLAPI_DOTS(0,1,1,0,1,1,0,0)] = '7',
+    [BRLAPI_DOTS(0,1,1,0,0,1,0,0)] = '8',
+    [BRLAPI_DOTS(0,0,1,0,1,0,0,0)] = '9',
 
-    DO(BRLAPI_DOTS(0, 0, 0, 1, 0, 1, 0, 0), '.'),
-    DO(BRLAPI_DOTS(0, 0, 1, 1, 0, 1, 0, 0), '+'),
-    DO(BRLAPI_DOTS(0, 0, 1, 0, 0, 1, 0, 0), '-'),
-    DO(BRLAPI_DOTS(1, 0, 0, 0, 0, 1, 0, 0), '*'),
-    DO(BRLAPI_DOTS(0, 0, 1, 1, 0, 0, 0, 0), '/'),
-    DO(BRLAPI_DOTS(1, 1, 1, 0, 1, 1, 0, 0), '('),
-    DO(BRLAPI_DOTS(0, 1, 1, 1, 1, 1, 0, 0), ')'),
+    [BRLAPI_DOTS(0,0,0,1,0,1,0,0)] = '.',
+    [BRLAPI_DOTS(0,0,1,1,0,1,0,0)] = '+',
+    [BRLAPI_DOTS(0,0,1,0,0,1,0,0)] = '-',
+    [BRLAPI_DOTS(1,0,0,0,0,1,0,0)] = '*',
+    [BRLAPI_DOTS(0,0,1,1,0,0,0,0)] = '/',
+    [BRLAPI_DOTS(1,1,1,0,1,1,0,0)] = '(',
+    [BRLAPI_DOTS(0,1,1,1,1,1,0,0)] = ')',
 
-    DO(BRLAPI_DOTS(1, 1, 1, 1, 0, 1, 0, 0), '&'),
-    DO(BRLAPI_DOTS(0, 0, 1, 1, 1, 1, 0, 0), '#'),
+    [BRLAPI_DOTS(1,1,1,1,0,1,0,0)] = '&',
+    [BRLAPI_DOTS(0,0,1,1,1,1,0,0)] = '#',
 
-    DO(BRLAPI_DOTS(0, 0, 0, 0, 0, 1, 0, 0), ','),
-    DO(BRLAPI_DOTS(0, 0, 0, 0, 1, 1, 0, 0), ';'),
-    DO(BRLAPI_DOTS(1, 0, 0, 0, 1, 1, 0, 0), ':'),
-    DO(BRLAPI_DOTS(0, 1, 1, 1, 0, 1, 0, 0), '!'),
-    DO(BRLAPI_DOTS(1, 0, 0, 1, 1, 1, 0, 0), '?'),
-    DO(BRLAPI_DOTS(0, 0, 0, 0, 1, 0, 0, 0), '"'),
-    DO(BRLAPI_DOTS(0, 0, 1, 0, 0, 0, 0, 0), '\''),
-    DO(BRLAPI_DOTS(0, 0, 0, 1, 0, 0, 0, 0), '`'),
-    DO(BRLAPI_DOTS(0, 0, 0, 1, 1, 0, 1, 0), '^'),
-    DO(BRLAPI_DOTS(0, 0, 0, 1, 1, 0, 0, 0), '~'),
-    DO(BRLAPI_DOTS(0, 1, 0, 1, 0, 1, 1, 0), '['),
-    DO(BRLAPI_DOTS(1, 1, 0, 1, 1, 1, 1, 0), ']'),
-    DO(BRLAPI_DOTS(0, 1, 0, 1, 0, 1, 0, 0), '{'),
-    DO(BRLAPI_DOTS(1, 1, 0, 1, 1, 1, 0, 0), '}'),
-    DO(BRLAPI_DOTS(1, 1, 1, 1, 1, 1, 0, 0), '='),
-    DO(BRLAPI_DOTS(1, 1, 0, 0, 0, 1, 0, 0), '<'),
-    DO(BRLAPI_DOTS(0, 0, 1, 1, 1, 0, 0, 0), '>'),
-    DO(BRLAPI_DOTS(1, 1, 0, 1, 0, 1, 0, 0), '$'),
-    DO(BRLAPI_DOTS(1, 0, 0, 1, 0, 1, 0, 0), '%'),
-    DO(BRLAPI_DOTS(0, 0, 0, 1, 0, 0, 1, 0), '@'),
-    DO(BRLAPI_DOTS(1, 1, 0, 0, 1, 1, 0, 0), '|'),
-    DO(BRLAPI_DOTS(1, 1, 0, 0, 1, 1, 1, 0), '\\'),
-    DO(BRLAPI_DOTS(0, 0, 0, 1, 1, 1, 0, 0), '_'),
+    [BRLAPI_DOTS(0,0,0,0,0,1,0,0)] = ',',
+    [BRLAPI_DOTS(0,0,0,0,1,1,0,0)] = ';',
+    [BRLAPI_DOTS(1,0,0,0,1,1,0,0)] = ':',
+    [BRLAPI_DOTS(0,1,1,1,0,1,0,0)] = '!',
+    [BRLAPI_DOTS(1,0,0,1,1,1,0,0)] = '?',
+    [BRLAPI_DOTS(0,0,0,0,1,0,0,0)] = '"',
+    [BRLAPI_DOTS(0,0,1,0,0,0,0,0)] ='\'',
+    [BRLAPI_DOTS(0,0,0,1,0,0,0,0)] = '`',
+    [BRLAPI_DOTS(0,0,0,1,1,0,1,0)] = '^',
+    [BRLAPI_DOTS(0,0,0,1,1,0,0,0)] = '~',
+    [BRLAPI_DOTS(0,1,0,1,0,1,1,0)] = '[',
+    [BRLAPI_DOTS(1,1,0,1,1,1,1,0)] = ']',
+    [BRLAPI_DOTS(0,1,0,1,0,1,0,0)] = '{',
+    [BRLAPI_DOTS(1,1,0,1,1,1,0,0)] = '}',
+    [BRLAPI_DOTS(1,1,1,1,1,1,0,0)] = '=',
+    [BRLAPI_DOTS(1,1,0,0,0,1,0,0)] = '<',
+    [BRLAPI_DOTS(0,0,1,1,1,0,0,0)] = '>',
+    [BRLAPI_DOTS(1,1,0,1,0,1,0,0)] = '$',
+    [BRLAPI_DOTS(1,0,0,1,0,1,0,0)] = '%',
+    [BRLAPI_DOTS(0,0,0,1,0,0,1,0)] = '@',
+    [BRLAPI_DOTS(1,1,0,0,1,1,0,0)] = '|',
+    [BRLAPI_DOTS(1,1,0,0,1,1,1,0)] ='\\',
+    [BRLAPI_DOTS(0,0,0,1,1,1,0,0)] = '_',
 };
 
-/* The guest OS has started discussing with us, finish initializing BrlAPI */
-static int baum_deferred_init(BaumChardev *baum)
-{
-    int tty = BRLAPI_TTY_DEFAULT;
-    QemuConsole *con;
-
-    if (baum->deferred_init) {
-        return 1;
-    }
-
-    if (brlapi__getDisplaySize(baum->brlapi, &baum->x, &baum->y) == -1) {
-        brlapi_perror("baum: brlapi__getDisplaySize");
-        return 0;
-    }
-
-    con = qemu_console_lookup_by_index(0);
-    if (con && qemu_console_is_graphic(con)) {
-        tty = qemu_console_get_window_id(con);
-        if (tty == -1)
-            tty = BRLAPI_TTY_DEFAULT;
-    }
-
-    if (brlapi__enterTtyMode(baum->brlapi, tty, NULL) == -1) {
-        brlapi_perror("baum: brlapi__enterTtyMode");
-        return 0;
-    }
-    baum->deferred_init = 1;
-    return 1;
-}
-
 /* The serial port can receive more of our data */
-static void baum_chr_accept_input(struct Chardev *chr)
+static void baum_accept_input(struct CharDriverState *chr)
 {
-    BaumChardev *baum = BAUM_CHARDEV(chr);
+    BaumDriverState *baum = chr->opaque;
     int room, first;
 
     if (!baum->out_buf_used)
@@ -282,25 +241,24 @@ static void baum_chr_accept_input(struct Chardev *chr)
 }
 
 /* We want to send a packet */
-static void baum_write_packet(BaumChardev *baum, const uint8_t *buf, int len)
+static void baum_write_packet(BaumDriverState *baum, const uint8_t *buf, int len)
 {
-    Chardev *chr = CHARDEV(baum);
     uint8_t io_buf[1 + 2 * len], *cur = io_buf;
     int room;
     *cur++ = ESC;
     while (len--)
         if ((*cur++ = *buf++) == ESC)
             *cur++ = ESC;
-    room = qemu_chr_be_can_write(chr);
+    room = qemu_chr_be_can_write(baum->chr);
     len = cur - io_buf;
     if (len <= room) {
         /* Fits */
-        qemu_chr_be_write(chr, io_buf, len);
+        qemu_chr_be_write(baum->chr, io_buf, len);
     } else {
         int first;
         uint8_t out;
         /* Can't fit all, send what can be, and store the rest. */
-        qemu_chr_be_write(chr, io_buf, room);
+        qemu_chr_be_write(baum->chr, io_buf, room);
         len -= room;
         cur = io_buf + room;
         if (len > BUF_SIZE - baum->out_buf_used) {
@@ -325,14 +283,14 @@ static void baum_write_packet(BaumChardev *baum, const uint8_t *buf, int len)
 /* Called when the other end seems to have a wrong idea of our display size */
 static void baum_cellCount_timer_cb(void *opaque)
 {
-    BaumChardev *baum = BAUM_CHARDEV(opaque);
+    BaumDriverState *baum = opaque;
     uint8_t cell_count[] = { BAUM_RSP_CellCount, baum->x * baum->y };
     DPRINTF("Timeout waiting for DisplayData, sending cell count\n");
     baum_write_packet(baum, cell_count, sizeof(cell_count));
 }
 
 /* Try to interpret a whole incoming packet */
-static int baum_eat_packet(BaumChardev *baum, const uint8_t *buf, int len)
+static int baum_eat_packet(BaumDriverState *baum, const uint8_t *buf, int len)
 {
     const uint8_t *cur = buf;
     uint8_t req = 0;
@@ -377,7 +335,7 @@ static int baum_eat_packet(BaumChardev *baum, const uint8_t *buf, int len)
 
         /* Allow 100ms to complete the DisplayData packet */
         timer_mod(baum->cellCount_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
-                       NANOSECONDS_PER_SECOND / 10);
+                       get_ticks_per_sec() / 10);
         for (i = 0; i < baum->x * baum->y ; i++) {
             EAT(c);
             cells[i] = c;
@@ -386,10 +344,8 @@ static int baum_eat_packet(BaumChardev *baum, const uint8_t *buf, int len)
                 cursor = i + 1;
                 c &= ~(BRLAPI_DOT7|BRLAPI_DOT8);
             }
-            c = nabcc_translation[DOTS2ASCII][c];
-            if (!c) {
+            if (!(c = nabcc_translation[c]))
                 c = '?';
-            }
             text[i] = c;
         }
         timer_del(baum->cellCount_timer);
@@ -473,17 +429,15 @@ static int baum_eat_packet(BaumChardev *baum, const uint8_t *buf, int len)
 }
 
 /* The other end is writing some data.  Store it and try to interpret */
-static int baum_chr_write(Chardev *chr, const uint8_t *buf, int len)
+static int baum_write(CharDriverState *chr, const uint8_t *buf, int len)
 {
-    BaumChardev *baum = BAUM_CHARDEV(chr);
+    BaumDriverState *baum = chr->opaque;
     int tocopy, cur, eaten, orig_len = len;
 
     if (!len)
         return 0;
     if (!baum->brlapi)
         return len;
-    if (!baum_deferred_init(baum))
-        return len;
 
     while (len) {
         /* Complete our buffer as much as possible */
@@ -514,31 +468,20 @@ static int baum_chr_write(Chardev *chr, const uint8_t *buf, int len)
 }
 
 /* Send the key code to the other end */
-static void baum_send_key(BaumChardev *baum, uint8_t type, uint8_t value)
-{
+static void baum_send_key(BaumDriverState *baum, uint8_t type, uint8_t value) {
     uint8_t packet[] = { type, value };
     DPRINTF("writing key %x %x\n", type, value);
     baum_write_packet(baum, packet, sizeof(packet));
 }
 
-static void baum_send_key2(BaumChardev *baum, uint8_t type, uint8_t value,
-                           uint8_t value2)
-{
-    uint8_t packet[] = { type, value, value2 };
-    DPRINTF("writing key %x %x\n", type, value);
-    baum_write_packet(baum, packet, sizeof(packet));
-}
-
 /* We got some data on the BrlAPI socket */
 static void baum_chr_read(void *opaque)
 {
-    BaumChardev *baum = BAUM_CHARDEV(opaque);
+    BaumDriverState *baum = opaque;
     brlapi_keyCode_t code;
     int ret;
     if (!baum->brlapi)
         return;
-    if (!baum_deferred_init(baum))
-        return;
     while ((ret = brlapi__readKey(baum->brlapi, 0, &code)) == 1) {
         DPRINTF("got key %"BRLAPI_PRIxKEYCODE"\n", code);
         /* Emulate */
@@ -595,17 +538,7 @@ static void baum_chr_read(void *opaque)
             }
             break;
         case BRLAPI_KEY_TYPE_SYM:
-            {
-                brlapi_keyCode_t keysym = code & BRLAPI_KEY_CODE_MASK;
-                if (keysym < 0x100) {
-                    uint8_t dots = nabcc_translation[ASCII2DOTS][keysym];
-                    if (dots) {
-                        baum_send_key2(baum, BAUM_RSP_EntryKeys, 0, dots);
-                        baum_send_key2(baum, BAUM_RSP_EntryKeys, 0, 0);
-                    }
-                }
-                break;
-            }
+            break;
         }
     }
     if (ret == -1 && (brlapi_errno != BRLAPI_ERROR_LIBCERR || errno != EINTR)) {
@@ -616,24 +549,40 @@ static void baum_chr_read(void *opaque)
     }
 }
 
-static void char_braille_finalize(Object *obj)
+static void baum_close(struct CharDriverState *chr)
 {
-    BaumChardev *baum = BAUM_CHARDEV(obj);
+    BaumDriverState *baum = chr->opaque;
 
     timer_free(baum->cellCount_timer);
     if (baum->brlapi) {
         brlapi__closeConnection(baum->brlapi);
         g_free(baum->brlapi);
     }
+    g_free(baum);
 }
 
-static void baum_chr_open(Chardev *chr,
-                          ChardevBackend *backend,
-                          bool *be_opened,
-                          Error **errp)
+static CharDriverState *chr_baum_init(const char *id,
+                                      ChardevBackend *backend,
+                                      ChardevReturn *ret,
+                                      Error **errp)
 {
-    BaumChardev *baum = BAUM_CHARDEV(chr);
+    BaumDriverState *baum;
+    CharDriverState *chr;
     brlapi_handle_t *handle;
+#if defined(CONFIG_SDL)
+#if SDL_COMPILEDVERSION < SDL_VERSIONNUM(2, 0, 0)
+    SDL_SysWMinfo info;
+#endif
+#endif
+    int tty;
+
+    baum = g_malloc0(sizeof(BaumDriverState));
+    baum->chr = chr = qemu_chr_alloc();
+
+    chr->opaque = baum;
+    chr->chr_write = baum_write;
+    chr->chr_accept_input = baum_accept_input;
+    chr->chr_close = baum_close;
 
     handle = g_malloc0(brlapi_getHandleSize());
     baum->brlapi = handle;
@@ -642,36 +591,52 @@ static void baum_chr_open(Chardev *chr,
     if (baum->brlapi_fd == -1) {
         error_setg(errp, "brlapi__openConnection: %s",
                    brlapi_strerror(brlapi_error_location()));
-        g_free(handle);
-        return;
+        goto fail_handle;
     }
-    baum->deferred_init = 0;
 
     baum->cellCount_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, baum_cellCount_timer_cb, baum);
 
+    if (brlapi__getDisplaySize(handle, &baum->x, &baum->y) == -1) {
+        error_setg(errp, "brlapi__getDisplaySize: %s",
+                   brlapi_strerror(brlapi_error_location()));
+        goto fail;
+    }
+
+#if defined(CONFIG_SDL)
+#if SDL_COMPILEDVERSION < SDL_VERSIONNUM(2, 0, 0)
+    memset(&info, 0, sizeof(info));
+    SDL_VERSION(&info.version);
+    if (SDL_GetWMInfo(&info))
+        tty = info.info.x11.wmwindow;
+    else
+#endif
+#endif
+        tty = BRLAPI_TTY_DEFAULT;
+
+    if (brlapi__enterTtyMode(handle, tty, NULL) == -1) {
+        error_setg(errp, "brlapi__enterTtyMode: %s",
+                   brlapi_strerror(brlapi_error_location()));
+        goto fail;
+    }
+
     qemu_set_fd_handler(baum->brlapi_fd, baum_chr_read, NULL, baum);
+
+    return chr;
+
+fail:
+    timer_free(baum->cellCount_timer);
+    brlapi__closeConnection(handle);
+fail_handle:
+    g_free(handle);
+    g_free(chr);
+    g_free(baum);
+    return NULL;
 }
 
-static void char_braille_class_init(ObjectClass *oc, void *data)
-{
-    ChardevClass *cc = CHARDEV_CLASS(oc);
-
-    cc->open = baum_chr_open;
-    cc->chr_write = baum_chr_write;
-    cc->chr_accept_input = baum_chr_accept_input;
-}
-
-static const TypeInfo char_braille_type_info = {
-    .name = TYPE_CHARDEV_BRAILLE,
-    .parent = TYPE_CHARDEV,
-    .instance_size = sizeof(BaumChardev),
-    .instance_finalize = char_braille_finalize,
-    .class_init = char_braille_class_init,
-};
-
 static void register_types(void)
 {
-    type_register_static(&char_braille_type_info);
+    register_char_driver("braille", CHARDEV_BACKEND_KIND_BRAILLE, NULL,
+                         chr_baum_init);
 }
 
 type_init(register_types);

backends/cryptodev-builtin.c

@@ -1,400 +0,0 @@
-/*
- * QEMU Cryptodev backend for QEMU cipher APIs
- *
- * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD.
- *
- * Authors:
- *    Gonglei <arei.gonglei@huawei.com>
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this library; if not, see <http://www.gnu.org/licenses/>.
- *
- */
-
-#include "qemu/osdep.h"
-#include "sysemu/cryptodev.h"
-#include "hw/boards.h"
-#include "qapi/error.h"
-#include "standard-headers/linux/virtio_crypto.h"
-#include "crypto/cipher.h"
-
-
-/**
- * @TYPE_CRYPTODEV_BACKEND_BUILTIN:
- * name of backend that uses QEMU cipher API
- */
-#define TYPE_CRYPTODEV_BACKEND_BUILTIN "cryptodev-backend-builtin"
-
-#define CRYPTODEV_BACKEND_BUILTIN(obj) \
-    OBJECT_CHECK(CryptoDevBackendBuiltin, \
-                 (obj), TYPE_CRYPTODEV_BACKEND_BUILTIN)
-
-typedef struct CryptoDevBackendBuiltin
-                         CryptoDevBackendBuiltin;
-
-typedef struct CryptoDevBackendBuiltinSession {
-    QCryptoCipher *cipher;
-    uint8_t direction; /* encryption or decryption */
-    uint8_t type; /* cipher? hash? aead? */
-    QTAILQ_ENTRY(CryptoDevBackendBuiltinSession) next;
-} CryptoDevBackendBuiltinSession;
-
-/* Max number of symmetric sessions */
-#define MAX_NUM_SESSIONS 256
-
-#define CRYPTODEV_BUITLIN_MAX_AUTH_KEY_LEN    512
-#define CRYPTODEV_BUITLIN_MAX_CIPHER_KEY_LEN  64
-
-struct CryptoDevBackendBuiltin {
-    CryptoDevBackend parent_obj;
-
-    CryptoDevBackendBuiltinSession *sessions[MAX_NUM_SESSIONS];
-};
-
-static void cryptodev_builtin_init(
-             CryptoDevBackend *backend, Error **errp)
-{
-    /* Only support one queue */
-    int queues = backend->conf.peers.queues;
-    CryptoDevBackendClient *cc;
-
-    if (queues != 1) {
-        error_setg(errp,
-                  "Only support one queue in cryptdov-builtin backend");
-        return;
-    }
-
-    cc = cryptodev_backend_new_client(
-              "cryptodev-builtin", NULL);
-    cc->info_str = g_strdup_printf("cryptodev-builtin0");
-    cc->queue_index = 0;
-    backend->conf.peers.ccs[0] = cc;
-
-    backend->conf.crypto_services =
-                         1u << VIRTIO_CRYPTO_SERVICE_CIPHER |
-                         1u << VIRTIO_CRYPTO_SERVICE_HASH |
-                         1u << VIRTIO_CRYPTO_SERVICE_MAC;
-    backend->conf.cipher_algo_l = 1u << VIRTIO_CRYPTO_CIPHER_AES_CBC;
-    backend->conf.hash_algo = 1u << VIRTIO_CRYPTO_HASH_SHA1;
-    /*
-     * Set the Maximum length of crypto request.
-     * Why this value? Just avoid to overflow when
-     * memory allocation for each crypto request.
-     */
-    backend->conf.max_size = LONG_MAX - sizeof(CryptoDevBackendSymOpInfo);
-    backend->conf.max_cipher_key_len = CRYPTODEV_BUITLIN_MAX_CIPHER_KEY_LEN;
-    backend->conf.max_auth_key_len = CRYPTODEV_BUITLIN_MAX_AUTH_KEY_LEN;
-
-    cryptodev_backend_set_ready(backend, true);
-}
-
-static int
-cryptodev_builtin_get_unused_session_index(
-                 CryptoDevBackendBuiltin *builtin)
-{
-    size_t i;
-
-    for (i = 0; i < MAX_NUM_SESSIONS; i++) {
-        if (builtin->sessions[i] == NULL) {
-            return i;
-        }
-    }
-
-    return -1;
-}
-
-#define AES_KEYSIZE_128 16
-#define AES_KEYSIZE_192 24
-#define AES_KEYSIZE_256 32
-#define AES_KEYSIZE_128_XTS AES_KEYSIZE_256
-#define AES_KEYSIZE_256_XTS 64
-
-static int
-cryptodev_builtin_get_aes_algo(uint32_t key_len, int mode, Error **errp)
-{
-    int algo;
-
-    if (key_len == AES_KEYSIZE_128) {
-        algo = QCRYPTO_CIPHER_ALG_AES_128;
-    } else if (key_len == AES_KEYSIZE_192) {
-        algo = QCRYPTO_CIPHER_ALG_AES_192;
-    } else if (key_len == AES_KEYSIZE_256) { /* equals AES_KEYSIZE_128_XTS */
-        if (mode == QCRYPTO_CIPHER_MODE_XTS) {
-            algo = QCRYPTO_CIPHER_ALG_AES_128;
-        } else {
-            algo = QCRYPTO_CIPHER_ALG_AES_256;
-        }
-    } else if (key_len == AES_KEYSIZE_256_XTS) {
-        if (mode == QCRYPTO_CIPHER_MODE_XTS) {
-            algo = QCRYPTO_CIPHER_ALG_AES_256;
-        } else {
-            goto err;
-        }
-    } else {
-        goto err;
-    }
-
-    return algo;
-
-err:
-   error_setg(errp, "Unsupported key length :%u", key_len);
-   return -1;
-}
-
-static int cryptodev_builtin_create_cipher_session(
-                    CryptoDevBackendBuiltin *builtin,
-                    CryptoDevBackendSymSessionInfo *sess_info,
-                    Error **errp)
-{
-    int algo;
-    int mode;
-    QCryptoCipher *cipher;
-    int index;
-    CryptoDevBackendBuiltinSession *sess;
-
-    if (sess_info->op_type != VIRTIO_CRYPTO_SYM_OP_CIPHER) {
-        error_setg(errp, "Unsupported optype :%u", sess_info->op_type);
-        return -1;
-    }
-
-    index = cryptodev_builtin_get_unused_session_index(builtin);
-    if (index < 0) {
-        error_setg(errp, "Total number of sessions created exceeds %u",
-                  MAX_NUM_SESSIONS);
-        return -1;
-    }
-
-    switch (sess_info->cipher_alg) {
-    case VIRTIO_CRYPTO_CIPHER_AES_ECB:
-        mode = QCRYPTO_CIPHER_MODE_ECB;
-        algo = cryptodev_builtin_get_aes_algo(sess_info->key_len,
-                                                    mode, errp);
-        if (algo < 0)  {
-            return -1;
-        }
-        break;
-    case VIRTIO_CRYPTO_CIPHER_AES_CBC:
-        mode = QCRYPTO_CIPHER_MODE_CBC;
-        algo = cryptodev_builtin_get_aes_algo(sess_info->key_len,
-                                                    mode, errp);
-        if (algo < 0)  {
-            return -1;
-        }
-        break;
-    case VIRTIO_CRYPTO_CIPHER_AES_CTR:
-        mode = QCRYPTO_CIPHER_MODE_CTR;
-        algo = cryptodev_builtin_get_aes_algo(sess_info->key_len,
-                                                    mode, errp);
-        if (algo < 0)  {
-            return -1;
-        }
-        break;
-    case VIRTIO_CRYPTO_CIPHER_AES_XTS:
-        mode = QCRYPTO_CIPHER_MODE_XTS;
-        algo = cryptodev_builtin_get_aes_algo(sess_info->key_len,
-                                                    mode, errp);
-        if (algo < 0)  {
-            return -1;
-        }
-        break;
-    case VIRTIO_CRYPTO_CIPHER_3DES_ECB:
-        mode = QCRYPTO_CIPHER_MODE_ECB;
-        algo = QCRYPTO_CIPHER_ALG_3DES;
-        break;
-    case VIRTIO_CRYPTO_CIPHER_3DES_CBC:
-        mode = QCRYPTO_CIPHER_MODE_CBC;
-        algo = QCRYPTO_CIPHER_ALG_3DES;
-        break;
-    case VIRTIO_CRYPTO_CIPHER_3DES_CTR:
-        mode = QCRYPTO_CIPHER_MODE_CTR;
-        algo = QCRYPTO_CIPHER_ALG_3DES;
-        break;
-    default:
-        error_setg(errp, "Unsupported cipher alg :%u",
-                   sess_info->cipher_alg);
-        return -1;
-    }
-
-    cipher = qcrypto_cipher_new(algo, mode,
-                               sess_info->cipher_key,
-                               sess_info->key_len,
-                               errp);
-    if (!cipher) {
-        return -1;
-    }
-
-    sess = g_new0(CryptoDevBackendBuiltinSession, 1);
-    sess->cipher = cipher;
-    sess->direction = sess_info->direction;
-    sess->type = sess_info->op_type;
-
-    builtin->sessions[index] = sess;
-
-    return index;
-}
-
-static int64_t cryptodev_builtin_sym_create_session(
-           CryptoDevBackend *backend,
-           CryptoDevBackendSymSessionInfo *sess_info,
-           uint32_t queue_index, Error **errp)
-{
-    CryptoDevBackendBuiltin *builtin =
-                      CRYPTODEV_BACKEND_BUILTIN(backend);
-    int64_t session_id = -1;
-    int ret;
-
-    switch (sess_info->op_code) {
-    case VIRTIO_CRYPTO_CIPHER_CREATE_SESSION:
-        ret = cryptodev_builtin_create_cipher_session(
-                           builtin, sess_info, errp);
-        if (ret < 0) {
-            return ret;
-        } else {
-            session_id = ret;
-        }
-        break;
-    case VIRTIO_CRYPTO_HASH_CREATE_SESSION:
-    case VIRTIO_CRYPTO_MAC_CREATE_SESSION:
-    default:
-        error_setg(errp, "Unsupported opcode :%" PRIu32 "",
-                   sess_info->op_code);
-        return -1;
-    }
-
-    return session_id;
-}
-
-static int cryptodev_builtin_sym_close_session(
-           CryptoDevBackend *backend,
-           uint64_t session_id,
-           uint32_t queue_index, Error **errp)
-{
-    CryptoDevBackendBuiltin *builtin =
-                      CRYPTODEV_BACKEND_BUILTIN(backend);
-
-    if (session_id >= MAX_NUM_SESSIONS ||
-              builtin->sessions[session_id] == NULL) {
-        error_setg(errp, "Cannot find a valid session id: %" PRIu64 "",
-                      session_id);
-        return -1;
-    }
-
-    qcrypto_cipher_free(builtin->sessions[session_id]->cipher);
-    g_free(builtin->sessions[session_id]);
-    builtin->sessions[session_id] = NULL;
-    return 0;
-}
-
-static int cryptodev_builtin_sym_operation(
-                 CryptoDevBackend *backend,
-                 CryptoDevBackendSymOpInfo *op_info,
-                 uint32_t queue_index, Error **errp)
-{
-    CryptoDevBackendBuiltin *builtin =
-                      CRYPTODEV_BACKEND_BUILTIN(backend);
-    CryptoDevBackendBuiltinSession *sess;
-    int ret;
-
-    if (op_info->session_id >= MAX_NUM_SESSIONS ||
-              builtin->sessions[op_info->session_id] == NULL) {
-        error_setg(errp, "Cannot find a valid session id: %" PRIu64 "",
-                   op_info->session_id);
-        return -VIRTIO_CRYPTO_INVSESS;
-    }
-
-    if (op_info->op_type == VIRTIO_CRYPTO_SYM_OP_ALGORITHM_CHAINING) {
-        error_setg(errp,
-               "Algorithm chain is unsupported for cryptdoev-builtin");
-        return -VIRTIO_CRYPTO_NOTSUPP;
-    }
-
-    sess = builtin->sessions[op_info->session_id];
-
-    if (op_info->iv_len > 0) {
-        ret = qcrypto_cipher_setiv(sess->cipher, op_info->iv,
-                                   op_info->iv_len, errp);
-        if (ret < 0) {
-            return -VIRTIO_CRYPTO_ERR;
-        }
-    }
-
-    if (sess->direction == VIRTIO_CRYPTO_OP_ENCRYPT) {
-        ret = qcrypto_cipher_encrypt(sess->cipher, op_info->src,
-                                     op_info->dst, op_info->src_len, errp);
-        if (ret < 0) {
-            return -VIRTIO_CRYPTO_ERR;
-        }
-    } else {
-        ret = qcrypto_cipher_decrypt(sess->cipher, op_info->src,
-                                     op_info->dst, op_info->src_len, errp);
-        if (ret < 0) {
-            return -VIRTIO_CRYPTO_ERR;
-        }
-    }
-    return VIRTIO_CRYPTO_OK;
-}
-
-static void cryptodev_builtin_cleanup(
-             CryptoDevBackend *backend,
-             Error **errp)
-{
-    CryptoDevBackendBuiltin *builtin =
-                      CRYPTODEV_BACKEND_BUILTIN(backend);
-    size_t i;
-    int queues = backend->conf.peers.queues;
-    CryptoDevBackendClient *cc;
-
-    for (i = 0; i < MAX_NUM_SESSIONS; i++) {
-        if (builtin->sessions[i] != NULL) {
-            cryptodev_builtin_sym_close_session(
-                    backend, i, 0, errp);
-        }
-    }
-
-    for (i = 0; i < queues; i++) {
-        cc = backend->conf.peers.ccs[i];
-        if (cc) {
-            cryptodev_backend_free_client(cc);
-            backend->conf.peers.ccs[i] = NULL;
-        }
-    }
-
-    cryptodev_backend_set_ready(backend, false);
-}
-
-static void
-cryptodev_builtin_class_init(ObjectClass *oc, void *data)
-{
-    CryptoDevBackendClass *bc = CRYPTODEV_BACKEND_CLASS(oc);
-
-    bc->init = cryptodev_builtin_init;
-    bc->cleanup = cryptodev_builtin_cleanup;
-    bc->create_session = cryptodev_builtin_sym_create_session;
-    bc->close_session = cryptodev_builtin_sym_close_session;
-    bc->do_sym_op = cryptodev_builtin_sym_operation;
-}
-
-static const TypeInfo cryptodev_builtin_info = {
-    .name = TYPE_CRYPTODEV_BACKEND_BUILTIN,
-    .parent = TYPE_CRYPTODEV_BACKEND,
-    .class_init = cryptodev_builtin_class_init,
-    .instance_size = sizeof(CryptoDevBackendBuiltin),
-};
-
-static void
-cryptodev_builtin_register_types(void)
-{
-    type_register_static(&cryptodev_builtin_info);
-}
-
-type_init(cryptodev_builtin_register_types);

backends/cryptodev.c

@@ -1,271 +0,0 @@
-/*
- * QEMU Crypto Device Implementation
- *
- * Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD.
- *
- * Authors:
- *    Gonglei <arei.gonglei@huawei.com>
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this library; if not, see <http://www.gnu.org/licenses/>.
- *
- */
-
-#include "qemu/osdep.h"
-#include "sysemu/cryptodev.h"
-#include "hw/boards.h"
-#include "qapi/error.h"
-#include "qapi/visitor.h"
-#include "qapi-types.h"
-#include "qapi-visit.h"
-#include "qemu/config-file.h"
-#include "qom/object_interfaces.h"
-#include "hw/virtio/virtio-crypto.h"
-
-
-static QTAILQ_HEAD(, CryptoDevBackendClient) crypto_clients;
-
-
-CryptoDevBackendClient *
-cryptodev_backend_new_client(const char *model,
-                                    const char *name)
-{
-    CryptoDevBackendClient *cc;
-
-    cc = g_malloc0(sizeof(CryptoDevBackendClient));
-    cc->model = g_strdup(model);
-    if (name) {
-        cc->name = g_strdup(name);
-    }
-
-    QTAILQ_INSERT_TAIL(&crypto_clients, cc, next);
-
-    return cc;
-}
-
-void cryptodev_backend_free_client(
-                  CryptoDevBackendClient *cc)
-{
-    QTAILQ_REMOVE(&crypto_clients, cc, next);
-    g_free(cc->name);
-    g_free(cc->model);
-    g_free(cc->info_str);
-    g_free(cc);
-}
-
-void cryptodev_backend_cleanup(
-             CryptoDevBackend *backend,
-             Error **errp)
-{
-    CryptoDevBackendClass *bc =
-                  CRYPTODEV_BACKEND_GET_CLASS(backend);
-
-    if (bc->cleanup) {
-        bc->cleanup(backend, errp);
-    }
-}
-
-int64_t cryptodev_backend_sym_create_session(
-           CryptoDevBackend *backend,
-           CryptoDevBackendSymSessionInfo *sess_info,
-           uint32_t queue_index, Error **errp)
-{
-    CryptoDevBackendClass *bc =
-                      CRYPTODEV_BACKEND_GET_CLASS(backend);
-
-    if (bc->create_session) {
-        return bc->create_session(backend, sess_info, queue_index, errp);
-    }
-
-    return -1;
-}
-
-int cryptodev_backend_sym_close_session(
-           CryptoDevBackend *backend,
-           uint64_t session_id,
-           uint32_t queue_index, Error **errp)
-{
-    CryptoDevBackendClass *bc =
-                      CRYPTODEV_BACKEND_GET_CLASS(backend);
-
-    if (bc->close_session) {
-        return bc->close_session(backend, session_id, queue_index, errp);
-    }
-
-    return -1;
-}
-
-static int cryptodev_backend_sym_operation(
-                 CryptoDevBackend *backend,
-                 CryptoDevBackendSymOpInfo *op_info,
-                 uint32_t queue_index, Error **errp)
-{
-    CryptoDevBackendClass *bc =
-                      CRYPTODEV_BACKEND_GET_CLASS(backend);
-
-    if (bc->do_sym_op) {
-        return bc->do_sym_op(backend, op_info, queue_index, errp);
-    }
-
-    return -VIRTIO_CRYPTO_ERR;
-}
-
-int cryptodev_backend_crypto_operation(
-                 CryptoDevBackend *backend,
-                 void *opaque,
-                 uint32_t queue_index, Error **errp)
-{
-    VirtIOCryptoReq *req = opaque;
-
-    if (req->flags == CRYPTODEV_BACKEND_ALG_SYM) {
-        CryptoDevBackendSymOpInfo *op_info;
-        op_info = req->u.sym_op_info;
-
-        return cryptodev_backend_sym_operation(backend,
-                         op_info, queue_index, errp);
-    } else {
-        error_setg(errp, "Unsupported cryptodev alg type: %" PRIu32 "",
-                   req->flags);
-       return -VIRTIO_CRYPTO_NOTSUPP;
-    }
-
-    return -VIRTIO_CRYPTO_ERR;
-}
-
-static void
-cryptodev_backend_get_queues(Object *obj, Visitor *v, const char *name,
-                             void *opaque, Error **errp)
-{
-    CryptoDevBackend *backend = CRYPTODEV_BACKEND(obj);
-    uint32_t value = backend->conf.peers.queues;
-
-    visit_type_uint32(v, name, &value, errp);
-}
-
-static void
-cryptodev_backend_set_queues(Object *obj, Visitor *v, const char *name,
-                             void *opaque, Error **errp)
-{
-    CryptoDevBackend *backend = CRYPTODEV_BACKEND(obj);
-    Error *local_err = NULL;
-    uint32_t value;
-
-    visit_type_uint32(v, name, &value, &local_err);
-    if (local_err) {
-        goto out;
-    }
-    if (!value) {
-        error_setg(&local_err, "Property '%s.%s' doesn't take value '%"
-                   PRIu32 "'", object_get_typename(obj), name, value);
-        goto out;
-    }
-    backend->conf.peers.queues = value;
-out:
-    error_propagate(errp, local_err);
-}
-
-static void
-cryptodev_backend_complete(UserCreatable *uc, Error **errp)
-{
-    CryptoDevBackend *backend = CRYPTODEV_BACKEND(uc);
-    CryptoDevBackendClass *bc = CRYPTODEV_BACKEND_GET_CLASS(uc);
-    Error *local_err = NULL;
-
-    if (bc->init) {
-        bc->init(backend, &local_err);
-        if (local_err) {
-            goto out;
-        }
-    }
-
-    return;
-
-out:
-    error_propagate(errp, local_err);
-}
-
-void cryptodev_backend_set_used(CryptoDevBackend *backend, bool used)
-{
-    backend->is_used = used;
-}
-
-bool cryptodev_backend_is_used(CryptoDevBackend *backend)
-{
-    return backend->is_used;
-}
-
-void cryptodev_backend_set_ready(CryptoDevBackend *backend, bool ready)
-{
-    backend->ready = ready;
-}
-
-bool cryptodev_backend_is_ready(CryptoDevBackend *backend)
-{
-    return backend->ready;
-}
-
-static bool
-cryptodev_backend_can_be_deleted(UserCreatable *uc, Error **errp)
-{
-    return !cryptodev_backend_is_used(CRYPTODEV_BACKEND(uc));
-}
-
-static void cryptodev_backend_instance_init(Object *obj)
-{
-    object_property_add(obj, "queues", "uint32",
-                          cryptodev_backend_get_queues,
-                          cryptodev_backend_set_queues,
-                          NULL, NULL, NULL);
-    /* Initialize devices' queues property to 1 */
-    object_property_set_int(obj, 1, "queues", NULL);
-}
-
-static void cryptodev_backend_finalize(Object *obj)
-{
-    CryptoDevBackend *backend = CRYPTODEV_BACKEND(obj);
-
-    cryptodev_backend_cleanup(backend, NULL);
-}
-
-static void
-cryptodev_backend_class_init(ObjectClass *oc, void *data)
-{
-    UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
-
-    ucc->complete = cryptodev_backend_complete;
-    ucc->can_be_deleted = cryptodev_backend_can_be_deleted;
-
-    QTAILQ_INIT(&crypto_clients);
-}
-
-static const TypeInfo cryptodev_backend_info = {
-    .name = TYPE_CRYPTODEV_BACKEND,
-    .parent = TYPE_OBJECT,
-    .instance_size = sizeof(CryptoDevBackend),
-    .instance_init = cryptodev_backend_instance_init,
-    .instance_finalize = cryptodev_backend_finalize,
-    .class_size = sizeof(CryptoDevBackendClass),
-    .class_init = cryptodev_backend_class_init,
-    .interfaces = (InterfaceInfo[]) {
-        { TYPE_USER_CREATABLE },
-        { }
-    }
-};
-
-static void
-cryptodev_backend_register_types(void)
-{
-    type_register_static(&cryptodev_backend_info);
-}
-
-type_init(cryptodev_backend_register_types);

backends/hostmem-file.c

@@ -9,8 +9,6 @@
  * 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/osdep.h"
-#include "qapi/error.h"
 #include "qemu-common.h"
 #include "sysemu/hostmem.h"
 #include "sysemu/sysemu.h"
@@ -51,19 +49,24 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
 #ifndef CONFIG_LINUX
     error_setg(errp, "-mem-path not supported on this host");
 #else
-    if (!host_memory_backend_mr_inited(backend)) {
-        gchar *path;
+    if (!memory_region_size(&backend->mr)) {
         backend->force_prealloc = mem_prealloc;
-        path = object_get_canonical_path(OBJECT(backend));
         memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
-                                 path,
+                                 object_get_canonical_path(OBJECT(backend)),
                                  backend->size, fb->share,
                                  fb->mem_path, errp);
-        g_free(path);
     }
 #endif
 }
 
+static void
+file_backend_class_init(ObjectClass *oc, void *data)
+{
+    HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
+
+    bc->alloc = file_backend_memory_alloc;
+}
+
 static char *get_mem_path(Object *o, Error **errp)
 {
     HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
@@ -76,7 +79,7 @@ static void set_mem_path(Object *o, const char *str, Error **errp)
     HostMemoryBackend *backend = MEMORY_BACKEND(o);
     HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
 
-    if (host_memory_backend_mr_inited(backend)) {
+    if (memory_region_size(&backend->mr)) {
         error_setg(errp, "cannot change property value");
         return;
     }
@@ -96,7 +99,7 @@ static void file_memory_backend_set_share(Object *o, bool value, Error **errp)
     HostMemoryBackend *backend = MEMORY_BACKEND(o);
     HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
 
-    if (host_memory_backend_mr_inited(backend)) {
+    if (memory_region_size(&backend->mr)) {
         error_setg(errp, "cannot change property value");
         return;
     }
@@ -104,32 +107,20 @@ static void file_memory_backend_set_share(Object *o, bool value, Error **errp)
 }
 
 static void
-file_backend_class_init(ObjectClass *oc, void *data)
+file_backend_instance_init(Object *o)
 {
-    HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
-
-    bc->alloc = file_backend_memory_alloc;
-
-    object_class_property_add_bool(oc, "share",
-        file_memory_backend_get_share, file_memory_backend_set_share,
-        &error_abort);
-    object_class_property_add_str(oc, "mem-path",
-        get_mem_path, set_mem_path,
-        &error_abort);
-}
-
-static void file_backend_instance_finalize(Object *o)
-{
-    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
-
-    g_free(fb->mem_path);
+    object_property_add_bool(o, "share",
+                        file_memory_backend_get_share,
+                        file_memory_backend_set_share, NULL);
+    object_property_add_str(o, "mem-path", get_mem_path,
+                            set_mem_path, NULL);
 }
 
 static const TypeInfo file_backend_info = {
     .name = TYPE_MEMORY_BACKEND_FILE,
     .parent = TYPE_MEMORY_BACKEND,
     .class_init = file_backend_class_init,
-    .instance_finalize = file_backend_instance_finalize,
+    .instance_init = file_backend_instance_init,
     .instance_size = sizeof(HostMemoryBackendFile),
 };
 

backends/hostmem-ram.c

@@ -9,9 +9,7 @@
  * 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/osdep.h"
 #include "sysemu/hostmem.h"
-#include "qapi/error.h"
 #include "qom/object_interfaces.h"
 
 #define TYPE_MEMORY_BACKEND_RAM "memory-backend-ram"

backends/hostmem.c

@@ -9,10 +9,8 @@
  * 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/osdep.h"
 #include "sysemu/hostmem.h"
 #include "hw/boards.h"
-#include "qapi/error.h"
 #include "qapi/visitor.h"
 #include "qapi-types.h"
 #include "qapi-visit.h"
@@ -28,29 +26,29 @@ QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_INTERLEAVE != MPOL_INTERLEAVE);
 #endif
 
 static void
-host_memory_backend_get_size(Object *obj, Visitor *v, const char *name,
-                             void *opaque, Error **errp)
+host_memory_backend_get_size(Object *obj, Visitor *v, void *opaque,
+                             const char *name, Error **errp)
 {
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
     uint64_t value = backend->size;
 
-    visit_type_size(v, name, &value, errp);
+    visit_type_size(v, &value, name, errp);
 }
 
 static void
-host_memory_backend_set_size(Object *obj, Visitor *v, const char *name,
-                             void *opaque, Error **errp)
+host_memory_backend_set_size(Object *obj, Visitor *v, void *opaque,
+                             const char *name, Error **errp)
 {
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
     Error *local_err = NULL;
     uint64_t value;
 
-    if (host_memory_backend_mr_inited(backend)) {
+    if (memory_region_size(&backend->mr)) {
         error_setg(&local_err, "cannot change property value");
         goto out;
     }
 
-    visit_type_size(v, name, &value, &local_err);
+    visit_type_size(v, &value, name, &local_err);
     if (local_err) {
         goto out;
     }
@@ -65,8 +63,8 @@ out:
 }
 
 static void
-host_memory_backend_get_host_nodes(Object *obj, Visitor *v, const char *name,
-                                   void *opaque, Error **errp)
+host_memory_backend_get_host_nodes(Object *obj, Visitor *v, void *opaque,
+                                   const char *name, Error **errp)
 {
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
     uint16List *host_nodes = NULL;
@@ -93,18 +91,18 @@ host_memory_backend_get_host_nodes(Object *obj, Visitor *v, const char *name,
         node = &(*node)->next;
     } while (true);
 
-    visit_type_uint16List(v, name, &host_nodes, errp);
+    visit_type_uint16List(v, &host_nodes, name, errp);
 }
 
 static void
-host_memory_backend_set_host_nodes(Object *obj, Visitor *v, const char *name,
-                                   void *opaque, Error **errp)
+host_memory_backend_set_host_nodes(Object *obj, Visitor *v, void *opaque,
+                                   const char *name, Error **errp)
 {
 #ifdef CONFIG_NUMA
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
     uint16List *l = NULL;
 
-    visit_type_uint16List(v, name, &l, errp);
+    visit_type_uint16List(v, &l, name, errp);
 
     while (l) {
         bitmap_set(backend->host_nodes, l->value, 1);
@@ -146,7 +144,7 @@ static void host_memory_backend_set_merge(Object *obj, bool value, Error **errp)
 {
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
 
-    if (!host_memory_backend_mr_inited(backend)) {
+    if (!memory_region_size(&backend->mr)) {
         backend->merge = value;
         return;
     }
@@ -172,7 +170,7 @@ static void host_memory_backend_set_dump(Object *obj, bool value, Error **errp)
 {
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
 
-    if (!host_memory_backend_mr_inited(backend)) {
+    if (!memory_region_size(&backend->mr)) {
         backend->dump = value;
         return;
     }
@@ -197,7 +195,6 @@ static bool host_memory_backend_get_prealloc(Object *obj, Error **errp)
 static void host_memory_backend_set_prealloc(Object *obj, bool value,
                                              Error **errp)
 {
-    Error *local_err = NULL;
     HostMemoryBackend *backend = MEMORY_BACKEND(obj);
 
     if (backend->force_prealloc) {
@@ -208,7 +205,7 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value,
         }
     }
 
-    if (!host_memory_backend_mr_inited(backend)) {
+    if (!memory_region_size(&backend->mr)) {
         backend->prealloc = value;
         return;
     }
@@ -218,11 +215,7 @@ static void host_memory_backend_set_prealloc(Object *obj, bool value,
         void *ptr = memory_region_get_ram_ptr(&backend->mr);
         uint64_t sz = memory_region_size(&backend->mr);
 
-        os_mem_prealloc(fd, ptr, sz, smp_cpus, &local_err);
-        if (local_err) {
-            error_propagate(errp, local_err);
-            return;
-        }
+        os_mem_prealloc(fd, ptr, sz);
         backend->prealloc = true;
     }
 }
@@ -235,31 +228,32 @@ static void host_memory_backend_init(Object *obj)
     backend->merge = machine_mem_merge(machine);
     backend->dump = machine_dump_guest_core(machine);
     backend->prealloc = mem_prealloc;
-}
 
-bool host_memory_backend_mr_inited(HostMemoryBackend *backend)
-{
-    /*
-     * NOTE: We forbid zero-length memory backend, so here zero means
-     * "we haven't inited the backend memory region yet".
-     */
-    return memory_region_size(&backend->mr) != 0;
+    object_property_add_bool(obj, "merge",
+                        host_memory_backend_get_merge,
+                        host_memory_backend_set_merge, NULL);
+    object_property_add_bool(obj, "dump",
+                        host_memory_backend_get_dump,
+                        host_memory_backend_set_dump, NULL);
+    object_property_add_bool(obj, "prealloc",
+                        host_memory_backend_get_prealloc,
+                        host_memory_backend_set_prealloc, NULL);
+    object_property_add(obj, "size", "int",
+                        host_memory_backend_get_size,
+                        host_memory_backend_set_size, NULL, NULL, NULL);
+    object_property_add(obj, "host-nodes", "int",
+                        host_memory_backend_get_host_nodes,
+                        host_memory_backend_set_host_nodes, NULL, NULL, NULL);
+    object_property_add_enum(obj, "policy", "HostMemPolicy",
+                             HostMemPolicy_lookup,
+                             host_memory_backend_get_policy,
+                             host_memory_backend_set_policy, NULL);
 }
 
 MemoryRegion *
 host_memory_backend_get_memory(HostMemoryBackend *backend, Error **errp)
 {
-    return host_memory_backend_mr_inited(backend) ? &backend->mr : NULL;
-}
-
-void host_memory_backend_set_mapped(HostMemoryBackend *backend, bool mapped)
-{
-    backend->is_mapped = mapped;
-}
-
-bool host_memory_backend_is_mapped(HostMemoryBackend *backend)
-{
-    return backend->is_mapped;
+    return memory_region_size(&backend->mr) ? &backend->mr : NULL;
 }
 
 static void
@@ -274,7 +268,8 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
     if (bc->alloc) {
         bc->alloc(backend, &local_err);
         if (local_err) {
-            goto out;
+            error_propagate(errp, local_err);
+            return;
         }
 
         ptr = memory_region_get_ram_ptr(&backend->mr);
@@ -330,45 +325,24 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
          * specified NUMA policy in place.
          */
         if (backend->prealloc) {
-            os_mem_prealloc(memory_region_get_fd(&backend->mr), ptr, sz,
-                            smp_cpus, &local_err);
-            if (local_err) {
-                goto out;
-            }
+            os_mem_prealloc(memory_region_get_fd(&backend->mr), ptr, sz);
         }
     }
-out:
-    error_propagate(errp, local_err);
 }
 
 static bool
 host_memory_backend_can_be_deleted(UserCreatable *uc, Error **errp)
 {
-    if (host_memory_backend_is_mapped(MEMORY_BACKEND(uc))) {
+    MemoryRegion *mr;
+
+    mr = host_memory_backend_get_memory(MEMORY_BACKEND(uc), errp);
+    if (memory_region_is_mapped(mr)) {
         return false;
     } else {
         return true;
     }
 }
 
-static char *get_id(Object *o, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(o);
-
-    return g_strdup(backend->id);
-}
-
-static void set_id(Object *o, const char *str, Error **errp)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(o);
-
-    if (backend->id) {
-        error_setg(errp, "cannot change property value");
-        return;
-    }
-    backend->id = g_strdup(str);
-}
-
 static void
 host_memory_backend_class_init(ObjectClass *oc, void *data)
 {
@@ -376,35 +350,6 @@ host_memory_backend_class_init(ObjectClass *oc, void *data)
 
     ucc->complete = host_memory_backend_memory_complete;
     ucc->can_be_deleted = host_memory_backend_can_be_deleted;
-
-    object_class_property_add_bool(oc, "merge",
-        host_memory_backend_get_merge,
-        host_memory_backend_set_merge, &error_abort);
-    object_class_property_add_bool(oc, "dump",
-        host_memory_backend_get_dump,
-        host_memory_backend_set_dump, &error_abort);
-    object_class_property_add_bool(oc, "prealloc",
-        host_memory_backend_get_prealloc,
-        host_memory_backend_set_prealloc, &error_abort);
-    object_class_property_add(oc, "size", "int",
-        host_memory_backend_get_size,
-        host_memory_backend_set_size,
-        NULL, NULL, &error_abort);
-    object_class_property_add(oc, "host-nodes", "int",
-        host_memory_backend_get_host_nodes,
-        host_memory_backend_set_host_nodes,
-        NULL, NULL, &error_abort);
-    object_class_property_add_enum(oc, "policy", "HostMemPolicy",
-        HostMemPolicy_lookup,
-        host_memory_backend_get_policy,
-        host_memory_backend_set_policy, &error_abort);
-    object_class_property_add_str(oc, "id", get_id, set_id, &error_abort);
-}
-
-static void host_memory_backend_finalize(Object *o)
-{
-    HostMemoryBackend *backend = MEMORY_BACKEND(o);
-    g_free(backend->id);
 }
 
 static const TypeInfo host_memory_backend_info = {
@@ -415,7 +360,6 @@ static const TypeInfo host_memory_backend_info = {
     .class_init = host_memory_backend_class_init,
     .instance_size = sizeof(HostMemoryBackend),
     .instance_init = host_memory_backend_init,
-    .instance_finalize = host_memory_backend_finalize,
     .interfaces = (InterfaceInfo[]) {
         { TYPE_USER_CREATABLE },
         { }

backends/msmouse.c

@@ -0,0 +1,89 @@
+/*
+ * QEMU Microsoft serial mouse emulation
+ *
+ * Copyright (c) 2008 Lubomir Rintel
+ *
+ * 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 <stdlib.h>
+#include "qemu-common.h"
+#include "sysemu/char.h"
+#include "ui/console.h"
+
+#define MSMOUSE_LO6(n) ((n) & 0x3f)
+#define MSMOUSE_HI2(n) (((n) & 0xc0) >> 6)
+
+static void msmouse_event(void *opaque,
+                          int dx, int dy, int dz, int buttons_state)
+{
+    CharDriverState *chr = (CharDriverState *)opaque;
+
+    unsigned char bytes[4] = { 0x40, 0x00, 0x00, 0x00 };
+
+    /* Movement deltas */
+    bytes[0] |= (MSMOUSE_HI2(dy) << 2) | MSMOUSE_HI2(dx);
+    bytes[1] |= MSMOUSE_LO6(dx);
+    bytes[2] |= MSMOUSE_LO6(dy);
+
+    /* Buttons */
+    bytes[0] |= (buttons_state & 0x01 ? 0x20 : 0x00);
+    bytes[0] |= (buttons_state & 0x02 ? 0x10 : 0x00);
+    bytes[3] |= (buttons_state & 0x04 ? 0x20 : 0x00);
+
+    /* We always send the packet of, so that we do not have to keep track
+       of previous state of the middle button. This can potentially confuse
+       some very old drivers for two button mice though. */
+    qemu_chr_be_write(chr, bytes, 4);
+}
+
+static int msmouse_chr_write (struct CharDriverState *s, const uint8_t *buf, int len)
+{
+    /* Ignore writes to mouse port */
+    return len;
+}
+
+static void msmouse_chr_close (struct CharDriverState *chr)
+{
+    g_free (chr);
+}
+
+static CharDriverState *qemu_chr_open_msmouse(const char *id,
+                                              ChardevBackend *backend,
+                                              ChardevReturn *ret,
+                                              Error **errp)
+{
+    CharDriverState *chr;
+
+    chr = qemu_chr_alloc();
+    chr->chr_write = msmouse_chr_write;
+    chr->chr_close = msmouse_chr_close;
+    chr->explicit_be_open = true;
+
+    qemu_add_mouse_event_handler(msmouse_event, chr, 0, "QEMU Microsoft Mouse");
+
+    return chr;
+}
+
+static void register_types(void)
+{
+    register_char_driver("msmouse", CHARDEV_BACKEND_KIND_MSMOUSE, NULL,
+                         qemu_chr_open_msmouse);
+}
+
+type_init(register_types);

backends/rng-egd.c

@@ -10,11 +10,10 @@
  * See the COPYING file in the top-level directory.
  */
 
-#include "qemu/osdep.h"
 #include "sysemu/rng.h"
-#include "chardev/char-fe.h"
-#include "qapi/error.h"
+#include "sysemu/char.h"
 #include "qapi/qmp/qerror.h"
+#include "hw/qdev.h" /* just for DEFINE_PROP_CHR */
 
 #define TYPE_RNG_EGD "rng-egd"
 #define RNG_EGD(obj) OBJECT_CHECK(RngEgd, (obj), TYPE_RNG_EGD)
@@ -23,14 +22,35 @@ typedef struct RngEgd
 {
     RngBackend parent;
 
-    CharBackend chr;
+    CharDriverState *chr;
     char *chr_name;
+
+    GSList *requests;
 } RngEgd;
 
-static void rng_egd_request_entropy(RngBackend *b, RngRequest *req)
+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);
-    size_t size = req->size;
+    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];
@@ -40,21 +60,28 @@ static void rng_egd_request_entropy(RngBackend *b, RngRequest *req)
         header[0] = 0x02;
         header[1] = len;
 
-        /* XXX this blocks entire thread. Rewrite to use
-         * qemu_chr_fe_write and background I/O callbacks */
-        qemu_chr_fe_write_all(&s->chr, header, sizeof(header));
+        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);
-    RngRequest *req;
+    GSList *i;
     int size = 0;
 
-    QSIMPLEQ_FOREACH(req, &s->parent.requests, next) {
+    for (i = s->requests; i; i = i->next) {
+        RngRequest *req = i->data;
         size += req->size - req->offset;
     }
 
@@ -66,8 +93,8 @@ static void rng_egd_chr_read(void *opaque, const uint8_t *buf, int size)
     RngEgd *s = RNG_EGD(opaque);
     size_t buf_offset = 0;
 
-    while (size > 0 && !QSIMPLEQ_EMPTY(&s->parent.requests)) {
-        RngRequest *req = QSIMPLEQ_FIRST(&s->parent.requests);
+    while (size > 0 && s->requests) {
+        RngRequest *req = s->requests->data;
         int len = MIN(size, req->size - req->offset);
 
         memcpy(req->data + req->offset, buf + buf_offset, len);
@@ -76,17 +103,41 @@ static void rng_egd_chr_read(void *opaque, const uint8_t *buf, int size)
         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_backend_finalize_request(&s->parent, req);
+            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);
-    Chardev *chr;
 
     if (s->chr_name == NULL) {
         error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
@@ -94,19 +145,21 @@ static void rng_egd_opened(RngBackend *b, Error **errp)
         return;
     }
 
-    chr = qemu_chr_find(s->chr_name);
-    if (chr == NULL) {
+    s->chr = qemu_chr_find(s->chr_name);
+    if (s->chr == NULL) {
         error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
                   "Device '%s' not found", s->chr_name);
         return;
     }
-    if (!qemu_chr_fe_init(&s->chr, chr, errp)) {
+
+    if (qemu_chr_fe_claim(s->chr) != 0) {
+        error_setg(errp, QERR_DEVICE_IN_USE, s->chr_name);
         return;
     }
 
     /* FIXME we should resubmit pending requests when the CDS reconnects. */
-    qemu_chr_fe_set_handlers(&s->chr, rng_egd_chr_can_read,
-                             rng_egd_chr_read, NULL, s, NULL, true);
+    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)
@@ -125,10 +178,9 @@ static void rng_egd_set_chardev(Object *obj, const char *value, Error **errp)
 static char *rng_egd_get_chardev(Object *obj, Error **errp)
 {
     RngEgd *s = RNG_EGD(obj);
-    Chardev *chr = qemu_chr_fe_get_driver(&s->chr);
 
-    if (chr && chr->label) {
-        return g_strdup(chr->label);
+    if (s->chr && s->chr->label) {
+        return g_strdup(s->chr->label);
     }
 
     return NULL;
@@ -145,8 +197,14 @@ static void rng_egd_finalize(Object *obj)
 {
     RngEgd *s = RNG_EGD(obj);
 
-    qemu_chr_fe_deinit(&s->chr, false);
+    if (s->chr) {
+        qemu_chr_add_handlers(s->chr, NULL, NULL, NULL, NULL);
+        qemu_chr_fe_release(s->chr);
+    }
+
     g_free(s->chr_name);
+
+    rng_egd_free_requests(s);
 }
 
 static void rng_egd_class_init(ObjectClass *klass, void *data)
@@ -154,6 +212,7 @@ 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;
 }
 

backends/rng-random.c

@@ -10,19 +10,21 @@
  * See the COPYING file in the top-level directory.
  */
 
-#include "qemu/osdep.h"
 #include "sysemu/rng-random.h"
 #include "sysemu/rng.h"
-#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/main-loop.h"
 
-struct RngRandom
+struct RndRandom
 {
     RngBackend parent;
 
     int fd;
     char *filename;
+
+    EntropyReceiveFunc *receive_func;
+    void *opaque;
+    size_t size;
 };
 
 /**
@@ -34,41 +36,42 @@ struct RngRandom
 
 static void entropy_available(void *opaque)
 {
-    RngRandom *s = RNG_RANDOM(opaque);
+    RndRandom *s = RNG_RANDOM(opaque);
+    uint8_t buffer[s->size];
+    ssize_t len;
 
-    while (!QSIMPLEQ_EMPTY(&s->parent.requests)) {
-        RngRequest *req = QSIMPLEQ_FIRST(&s->parent.requests);
-        ssize_t len;
-
-        len = read(s->fd, req->data, req->size);
-        if (len < 0 && errno == EAGAIN) {
-            return;
-        }
-        g_assert(len != -1);
-
-        req->receive_entropy(req->opaque, req->data, len);
-
-        rng_backend_finalize_request(&s->parent, req);
+    len = read(s->fd, buffer, s->size);
+    if (len < 0 && errno == EAGAIN) {
+        return;
     }
+    g_assert(len != -1);
+
+    s->receive_func(s->opaque, buffer, len);
+    s->receive_func = NULL;
 
-    /* We've drained all requests, the fd handler can be reset. */
     qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
 }
 
-static void rng_random_request_entropy(RngBackend *b, RngRequest *req)
+static void rng_random_request_entropy(RngBackend *b, size_t size,
+                                        EntropyReceiveFunc *receive_entropy,
+                                        void *opaque)
 {
-    RngRandom *s = RNG_RANDOM(b);
+    RndRandom *s = RNG_RANDOM(b);
 
-    if (QSIMPLEQ_EMPTY(&s->parent.requests)) {
-        /* If there are no pending requests yet, we need to
-         * install our fd handler. */
-        qemu_set_fd_handler(s->fd, entropy_available, NULL, s);
+    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)
 {
-    RngRandom *s = RNG_RANDOM(b);
+    RndRandom *s = RNG_RANDOM(b);
 
     if (s->filename == NULL) {
         error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
@@ -83,7 +86,7 @@ static void rng_random_opened(RngBackend *b, Error **errp)
 
 static char *rng_random_get_filename(Object *obj, Error **errp)
 {
-    RngRandom *s = RNG_RANDOM(obj);
+    RndRandom *s = RNG_RANDOM(obj);
 
     return g_strdup(s->filename);
 }
@@ -92,7 +95,7 @@ static void rng_random_set_filename(Object *obj, const char *filename,
                                  Error **errp)
 {
     RngBackend *b = RNG_BACKEND(obj);
-    RngRandom *s = RNG_RANDOM(obj);
+    RndRandom *s = RNG_RANDOM(obj);
 
     if (b->opened) {
         error_setg(errp, QERR_PERMISSION_DENIED);
@@ -105,7 +108,7 @@ static void rng_random_set_filename(Object *obj, const char *filename,
 
 static void rng_random_init(Object *obj)
 {
-    RngRandom *s = RNG_RANDOM(obj);
+    RndRandom *s = RNG_RANDOM(obj);
 
     object_property_add_str(obj, "filename",
                             rng_random_get_filename,
@@ -118,7 +121,7 @@ static void rng_random_init(Object *obj)
 
 static void rng_random_finalize(Object *obj)
 {
-    RngRandom *s = RNG_RANDOM(obj);
+    RndRandom *s = RNG_RANDOM(obj);
 
     if (s->fd != -1) {
         qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
@@ -139,7 +142,7 @@ static void rng_random_class_init(ObjectClass *klass, void *data)
 static const TypeInfo rng_random_info = {
     .name = TYPE_RNG_RANDOM,
     .parent = TYPE_RNG_BACKEND,
-    .instance_size = sizeof(RngRandom),
+    .instance_size = sizeof(RndRandom),
     .class_init = rng_random_class_init,
     .instance_init = rng_random_init,
     .instance_finalize = rng_random_finalize,

backends/rng.c

@@ -10,9 +10,7 @@
  * See the COPYING file in the top-level directory.
  */
 
-#include "qemu/osdep.h"
 #include "sysemu/rng.h"
-#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qom/object_interfaces.h"
 
@@ -21,20 +19,18 @@ void rng_backend_request_entropy(RngBackend *s, size_t size,
                                  void *opaque)
 {
     RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
-    RngRequest *req;
 
     if (k->request_entropy) {
-        req = g_malloc(sizeof(*req));
+        k->request_entropy(s, size, receive_entropy, opaque);
+    }
+}
 
-        req->offset = 0;
-        req->size = size;
-        req->receive_entropy = receive_entropy;
-        req->opaque = opaque;
-        req->data = g_malloc(req->size);
+void rng_backend_cancel_requests(RngBackend *s)
+{
+    RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
 
-        k->request_entropy(s, req);
-
-        QSIMPLEQ_INSERT_TAIL(&s->requests, req, next);
+    if (k->cancel_requests) {
+        k->cancel_requests(s);
     }
 }
 
@@ -76,48 +72,14 @@ static void rng_backend_prop_set_opened(Object *obj, bool value, Error **errp)
     s->opened = true;
 }
 
-static void rng_backend_free_request(RngRequest *req)
-{
-    g_free(req->data);
-    g_free(req);
-}
-
-static void rng_backend_free_requests(RngBackend *s)
-{
-    RngRequest *req, *next;
-
-    QSIMPLEQ_FOREACH_SAFE(req, &s->requests, next, next) {
-        rng_backend_free_request(req);
-    }
-
-    QSIMPLEQ_INIT(&s->requests);
-}
-
-void rng_backend_finalize_request(RngBackend *s, RngRequest *req)
-{
-    QSIMPLEQ_REMOVE(&s->requests, req, RngRequest, next);
-    rng_backend_free_request(req);
-}
-
 static void rng_backend_init(Object *obj)
 {
-    RngBackend *s = RNG_BACKEND(obj);
-
-    QSIMPLEQ_INIT(&s->requests);
-
     object_property_add_bool(obj, "opened",
                              rng_backend_prop_get_opened,
                              rng_backend_prop_set_opened,
                              NULL);
 }
 
-static void rng_backend_finalize(Object *obj)
-{
-    RngBackend *s = RNG_BACKEND(obj);
-
-    rng_backend_free_requests(s);
-}
-
 static void rng_backend_class_init(ObjectClass *oc, void *data)
 {
     UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
@@ -130,7 +92,6 @@ static const TypeInfo rng_backend_info = {
     .parent = TYPE_OBJECT,
     .instance_size = sizeof(RngBackend),
     .instance_init = rng_backend_init,
-    .instance_finalize = rng_backend_finalize,
     .class_size = sizeof(RngBackendClass),
     .class_init = rng_backend_class_init,
     .abstract = true,

backends/testdev.c

@@ -23,25 +23,19 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
 #include "qemu-common.h"
-#include "chardev/char.h"
+#include "sysemu/char.h"
 
 #define BUF_SIZE 32
 
 typedef struct {
-    Chardev parent;
-
+    CharDriverState *chr;
     uint8_t in_buf[32];
     int in_buf_used;
-} TestdevChardev;
-
-#define TYPE_CHARDEV_TESTDEV "chardev-testdev"
-#define TESTDEV_CHARDEV(obj)                                    \
-    OBJECT_CHECK(TestdevChardev, (obj), TYPE_CHARDEV_TESTDEV)
+} TestdevCharState;
 
 /* Try to interpret a whole incoming packet */
-static int testdev_eat_packet(TestdevChardev *testdev)
+static int testdev_eat_packet(TestdevCharState *testdev)
 {
     const uint8_t *cur = testdev->in_buf;
     int len = testdev->in_buf_used;
@@ -82,9 +76,9 @@ static int testdev_eat_packet(TestdevChardev *testdev)
 }
 
 /* The other end is writing some data.  Store it and try to interpret */
-static int testdev_chr_write(Chardev *chr, const uint8_t *buf, int len)
+static int testdev_write(CharDriverState *chr, const uint8_t *buf, int len)
 {
-    TestdevChardev *testdev = TESTDEV_CHARDEV(chr);
+    TestdevCharState *testdev = chr->opaque;
     int tocopy, eaten, orig_len = len;
 
     while (len) {
@@ -107,23 +101,35 @@ static int testdev_chr_write(Chardev *chr, const uint8_t *buf, int len)
     return orig_len;
 }
 
-static void char_testdev_class_init(ObjectClass *oc, void *data)
+static void testdev_close(struct CharDriverState *chr)
 {
-    ChardevClass *cc = CHARDEV_CLASS(oc);
+    TestdevCharState *testdev = chr->opaque;
 
-    cc->chr_write = testdev_chr_write;
+    g_free(testdev);
 }
 
-static const TypeInfo char_testdev_type_info = {
-    .name = TYPE_CHARDEV_TESTDEV,
-    .parent = TYPE_CHARDEV,
-    .instance_size = sizeof(TestdevChardev),
-    .class_init = char_testdev_class_init,
-};
+static CharDriverState *chr_testdev_init(const char *id,
+                                         ChardevBackend *backend,
+                                         ChardevReturn *ret,
+                                         Error **errp)
+{
+    TestdevCharState *testdev;
+    CharDriverState *chr;
+
+    testdev = g_new0(TestdevCharState, 1);
+    testdev->chr = chr = g_new0(CharDriverState, 1);
+
+    chr->opaque = testdev;
+    chr->chr_write = testdev_write;
+    chr->chr_close = testdev_close;
+
+    return chr;
+}
 
 static void register_types(void)
 {
-    type_register_static(&char_testdev_type_info);
+    register_char_driver("testdev", CHARDEV_BACKEND_KIND_TESTDEV, NULL,
+                         chr_testdev_init);
 }
 
 type_init(register_types);

backends/tpm.c

@@ -12,9 +12,7 @@
  * Based on backends/rng.c by Anthony Liguori
  */
 
-#include "qemu/osdep.h"
 #include "sysemu/tpm_backend.h"
-#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "sysemu/tpm.h"
 #include "qemu/thread.h"

balloon.c

@@ -24,12 +24,11 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
 #include "qemu-common.h"
 #include "exec/cpu-common.h"
 #include "sysemu/kvm.h"
 #include "sysemu/balloon.h"
-#include "trace-root.h"
+#include "trace.h"
 #include "qmp-commands.h"
 #include "qapi/qmp/qerror.h"
 #include "qapi/qmp/qjson.h"

block/Makefile.objs

@@ -1,36 +1,34 @@
-block-obj-y += raw-format.o qcow.o vdi.o vmdk.o cloop.o bochs.o vpc.o vvfat.o dmg.o
+block-obj-y += raw_bsd.o qcow.o vdi.o vmdk.o cloop.o bochs.o vpc.o vvfat.o
 block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
 block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-obj-y += qed-check.o
-block-obj-y += vhdx.o vhdx-endian.o vhdx-log.o
+block-obj-$(CONFIG_VHDX) += vhdx.o vhdx-endian.o vhdx-log.o
 block-obj-y += quorum.o
-block-obj-y += parallels.o blkdebug.o blkverify.o blkreplay.o
+block-obj-y += parallels.o blkdebug.o blkverify.o
 block-obj-y += block-backend.o snapshot.o qapi.o
-block-obj-$(CONFIG_WIN32) += file-win32.o win32-aio.o
-block-obj-$(CONFIG_POSIX) += file-posix.o
+block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
+block-obj-$(CONFIG_POSIX) += raw-posix.o
 block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
-block-obj-y += null.o mirror.o commit.o io.o
+block-obj-y += null.o mirror.o io.o
 block-obj-y += throttle-groups.o
 
 block-obj-y += nbd.o nbd-client.o sheepdog.o
 block-obj-$(CONFIG_LIBISCSI) += iscsi.o
-block-obj-$(if $(CONFIG_LIBISCSI),y,n) += iscsi-opts.o
 block-obj-$(CONFIG_LIBNFS) += nfs.o
 block-obj-$(CONFIG_CURL) += curl.o
 block-obj-$(CONFIG_RBD) += rbd.o
 block-obj-$(CONFIG_GLUSTERFS) += gluster.o
-block-obj-$(CONFIG_VXHS) += vxhs.o
+block-obj-$(CONFIG_ARCHIPELAGO) += archipelago.o
 block-obj-$(CONFIG_LIBSSH2) += ssh.o
-block-obj-y += accounting.o dirty-bitmap.o
+block-obj-y += dictzip.o
+block-obj-y += tar.o
+block-obj-y += accounting.o
 block-obj-y += write-threshold.o
-block-obj-y += backup.o
-block-obj-$(CONFIG_REPLICATION) += replication.o
-
-block-obj-y += crypto.o
 
 common-obj-y += stream.o
+common-obj-y += commit.o
+common-obj-y += backup.o
 
-nfs.o-libs         := $(LIBNFS_LIBS)
 iscsi.o-cflags     := $(LIBISCSI_CFLAGS)
 iscsi.o-libs       := $(LIBISCSI_LIBS)
 curl.o-cflags      := $(CURL_CFLAGS)
@@ -39,10 +37,10 @@ rbd.o-cflags       := $(RBD_CFLAGS)
 rbd.o-libs         := $(RBD_LIBS)
 gluster.o-cflags   := $(GLUSTERFS_CFLAGS)
 gluster.o-libs     := $(GLUSTERFS_LIBS)
-vxhs.o-libs        := $(VXHS_LIBS)
 ssh.o-cflags       := $(LIBSSH2_CFLAGS)
 ssh.o-libs         := $(LIBSSH2_LIBS)
-block-obj-$(if $(CONFIG_BZIP2),m,n) += dmg-bz2.o
-dmg-bz2.o-libs     := $(BZIP2_LIBS)
+archipelago.o-libs := $(ARCHIPELAGO_LIBS)
+block-obj-m        += dmg.o
+dmg.o-libs         := $(BZIP2_LIBS)
 qcow.o-libs        := -lz
 linux-aio.o-libs   := -laio

block/accounting.c

@@ -23,7 +23,6 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
 #include "block/accounting.h"
 #include "block/block_int.h"
 #include "qemu/timer.h"
@@ -32,19 +31,15 @@
 static QEMUClockType clock_type = QEMU_CLOCK_REALTIME;
 static const int qtest_latency_ns = NANOSECONDS_PER_SECOND / 1000;
 
-void block_acct_init(BlockAcctStats *stats)
-{
-    qemu_mutex_init(&stats->lock);
-    if (qtest_enabled()) {
-        clock_type = QEMU_CLOCK_VIRTUAL;
-    }
-}
-
-void block_acct_setup(BlockAcctStats *stats, bool account_invalid,
-                      bool account_failed)
+void block_acct_init(BlockAcctStats *stats, bool account_invalid,
+                     bool account_failed)
 {
     stats->account_invalid = account_invalid;
     stats->account_failed = account_failed;
+
+    if (qtest_enabled()) {
+        clock_type = QEMU_CLOCK_VIRTUAL;
+    }
 }
 
 void block_acct_cleanup(BlockAcctStats *stats)
@@ -53,7 +48,6 @@ void block_acct_cleanup(BlockAcctStats *stats)
     QSLIST_FOREACH_SAFE(s, &stats->intervals, entries, next) {
         g_free(s);
     }
-    qemu_mutex_destroy(&stats->lock);
 }
 
 void block_acct_add_interval(BlockAcctStats *stats, unsigned interval_length)
@@ -63,15 +57,12 @@ void block_acct_add_interval(BlockAcctStats *stats, unsigned interval_length)
 
     s = g_new0(BlockAcctTimedStats, 1);
     s->interval_length = interval_length;
-    s->stats = stats;
-    qemu_mutex_lock(&stats->lock);
     QSLIST_INSERT_HEAD(&stats->intervals, s, entries);
 
     for (i = 0; i < BLOCK_MAX_IOTYPE; i++) {
         timed_average_init(&s->latency[i], clock_type,
                            (uint64_t) interval_length * NANOSECONDS_PER_SECOND);
     }
-    qemu_mutex_unlock(&stats->lock);
 }
 
 BlockAcctTimedStats *block_acct_interval_next(BlockAcctStats *stats,
@@ -94,8 +85,7 @@ void block_acct_start(BlockAcctStats *stats, BlockAcctCookie *cookie,
     cookie->type = type;
 }
 
-static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,
-                                 bool failed)
+void block_acct_done(BlockAcctStats *stats, BlockAcctCookie *cookie)
 {
     BlockAcctTimedStats *s;
     int64_t time_ns = qemu_clock_get_ns(clock_type);
@@ -107,16 +97,31 @@ static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,
 
     assert(cookie->type < BLOCK_MAX_IOTYPE);
 
-    qemu_mutex_lock(&stats->lock);
+    stats->nr_bytes[cookie->type] += cookie->bytes;
+    stats->nr_ops[cookie->type]++;
+    stats->total_time_ns[cookie->type] += latency_ns;
+    stats->last_access_time_ns = time_ns;
 
-    if (failed) {
-        stats->failed_ops[cookie->type]++;
-    } else {
-        stats->nr_bytes[cookie->type] += cookie->bytes;
-        stats->nr_ops[cookie->type]++;
+    QSLIST_FOREACH(s, &stats->intervals, entries) {
+        timed_average_account(&s->latency[cookie->type], latency_ns);
     }
+}
+
+void block_acct_failed(BlockAcctStats *stats, BlockAcctCookie *cookie)
+{
+    assert(cookie->type < BLOCK_MAX_IOTYPE);
+
+    stats->failed_ops[cookie->type]++;
+
+    if (stats->account_failed) {
+        BlockAcctTimedStats *s;
+        int64_t time_ns = qemu_clock_get_ns(clock_type);
+        int64_t latency_ns = time_ns - cookie->start_time_ns;
+
+        if (qtest_enabled()) {
+            latency_ns = qtest_latency_ns;
+        }
 
-    if (!failed || stats->account_failed) {
         stats->total_time_ns[cookie->type] += latency_ns;
         stats->last_access_time_ns = time_ns;
 
@@ -124,45 +129,29 @@ static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,
             timed_average_account(&s->latency[cookie->type], latency_ns);
         }
     }
-
-    qemu_mutex_unlock(&stats->lock);
-}
-
-void block_acct_done(BlockAcctStats *stats, BlockAcctCookie *cookie)
-{
-    block_account_one_io(stats, cookie, false);
-}
-
-void block_acct_failed(BlockAcctStats *stats, BlockAcctCookie *cookie)
-{
-    block_account_one_io(stats, cookie, true);
 }
 
 void block_acct_invalid(BlockAcctStats *stats, enum BlockAcctType type)
 {
     assert(type < BLOCK_MAX_IOTYPE);
 
-    /* block_account_one_io() updates total_time_ns[], but this one does
-     * not.  The reason is that invalid requests are accounted during their
-     * submission, therefore there's no actual I/O involved.
-     */
-    qemu_mutex_lock(&stats->lock);
+    /* block_acct_done() and block_acct_failed() update
+     * total_time_ns[], but this one does not. The reason is that
+     * invalid requests are accounted during their submission,
+     * therefore there's no actual I/O involved. */
+
     stats->invalid_ops[type]++;
 
     if (stats->account_invalid) {
         stats->last_access_time_ns = qemu_clock_get_ns(clock_type);
     }
-    qemu_mutex_unlock(&stats->lock);
 }
 
 void block_acct_merge_done(BlockAcctStats *stats, enum BlockAcctType type,
                       int num_requests)
 {
     assert(type < BLOCK_MAX_IOTYPE);
-
-    qemu_mutex_lock(&stats->lock);
     stats->merged[type] += num_requests;
-    qemu_mutex_unlock(&stats->lock);
 }
 
 int64_t block_acct_idle_time_ns(BlockAcctStats *stats)
@@ -177,9 +166,7 @@ double block_acct_queue_depth(BlockAcctTimedStats *stats,
 
     assert(type < BLOCK_MAX_IOTYPE);
 
-    qemu_mutex_lock(&stats->stats->lock);
     sum = timed_average_sum(&stats->latency[type], &elapsed);
-    qemu_mutex_unlock(&stats->stats->lock);
 
     return (double) sum / elapsed;
 }

block/backup.c

@@ -11,27 +11,34 @@
  *
  */
 
-#include "qemu/osdep.h"
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
 
 #include "trace.h"
 #include "block/block.h"
 #include "block/block_int.h"
-#include "block/blockjob_int.h"
-#include "block/block_backup.h"
-#include "qapi/error.h"
+#include "block/blockjob.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
-#include "qemu/cutils.h"
 #include "sysemu/block-backend.h"
-#include "qemu/bitmap.h"
-#include "qemu/error-report.h"
 
-#define BACKUP_CLUSTER_SIZE_DEFAULT (1 << 16)
+#define BACKUP_CLUSTER_BITS 16
+#define BACKUP_CLUSTER_SIZE (1 << BACKUP_CLUSTER_BITS)
+#define BACKUP_SECTORS_PER_CLUSTER (BACKUP_CLUSTER_SIZE / BDRV_SECTOR_SIZE)
+
 #define SLICE_TIME 100000000ULL /* ns */
 
+typedef struct CowRequest {
+    int64_t start;
+    int64_t end;
+    QLIST_ENTRY(CowRequest) list;
+    CoQueue wait_queue; /* coroutines blocked on this request */
+} CowRequest;
+
 typedef struct BackupBlockJob {
     BlockJob common;
-    BlockBackend *target;
+    BlockDriverState *target;
     /* bitmap for sync=incremental */
     BdrvDirtyBitmap *sync_bitmap;
     MirrorSyncMode sync_mode;
@@ -40,19 +47,10 @@ typedef struct BackupBlockJob {
     BlockdevOnError on_target_error;
     CoRwlock flush_rwlock;
     uint64_t sectors_read;
-    unsigned long *done_bitmap;
-    int64_t cluster_size;
-    bool compress;
-    NotifierWithReturn before_write;
+    HBitmap *bitmap;
     QLIST_HEAD(, CowRequest) inflight_reqs;
 } BackupBlockJob;
 
-/* Size of a cluster in sectors, instead of bytes. */
-static inline int64_t cluster_size_sectors(BackupBlockJob *job)
-{
-  return job->cluster_size / BDRV_SECTOR_SIZE;
-}
-
 /* See if in-flight requests overlap and wait for them to complete */
 static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job,
                                                        int64_t start,
@@ -65,7 +63,7 @@ static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job,
         retry = false;
         QLIST_FOREACH(req, &job->inflight_reqs, list) {
             if (end > req->start && start < req->end) {
-                qemu_co_queue_wait(&req->wait_queue, NULL);
+                qemu_co_queue_wait(&req->wait_queue);
                 retry = true;
                 break;
             }
@@ -90,25 +88,24 @@ static void cow_request_end(CowRequest *req)
     qemu_co_queue_restart_all(&req->wait_queue);
 }
 
-static int coroutine_fn backup_do_cow(BackupBlockJob *job,
+static int coroutine_fn backup_do_cow(BlockDriverState *bs,
                                       int64_t sector_num, int nb_sectors,
                                       bool *error_is_read,
                                       bool is_write_notifier)
 {
-    BlockBackend *blk = job->common.blk;
+    BackupBlockJob *job = (BackupBlockJob *)bs->job;
     CowRequest cow_request;
     struct iovec iov;
     QEMUIOVector bounce_qiov;
     void *bounce_buffer = NULL;
     int ret = 0;
-    int64_t sectors_per_cluster = cluster_size_sectors(job);
     int64_t start, end;
     int n;
 
     qemu_co_rwlock_rdlock(&job->flush_rwlock);
 
-    start = sector_num / sectors_per_cluster;
-    end = DIV_ROUND_UP(sector_num + nb_sectors, sectors_per_cluster);
+    start = sector_num / BACKUP_SECTORS_PER_CLUSTER;
+    end = DIV_ROUND_UP(sector_num + nb_sectors, BACKUP_SECTORS_PER_CLUSTER);
 
     trace_backup_do_cow_enter(job, start, sector_num, nb_sectors);
 
@@ -116,27 +113,32 @@ static int coroutine_fn backup_do_cow(BackupBlockJob *job,
     cow_request_begin(&cow_request, job, start, end);
 
     for (; start < end; start++) {
-        if (test_bit(start, job->done_bitmap)) {
+        if (hbitmap_get(job->bitmap, start)) {
             trace_backup_do_cow_skip(job, start);
             continue; /* already copied */
         }
 
         trace_backup_do_cow_process(job, start);
 
-        n = MIN(sectors_per_cluster,
+        n = MIN(BACKUP_SECTORS_PER_CLUSTER,
                 job->common.len / BDRV_SECTOR_SIZE -
-                start * sectors_per_cluster);
+                start * BACKUP_SECTORS_PER_CLUSTER);
 
         if (!bounce_buffer) {
-            bounce_buffer = blk_blockalign(blk, job->cluster_size);
+            bounce_buffer = qemu_blockalign(bs, BACKUP_CLUSTER_SIZE);
         }
         iov.iov_base = bounce_buffer;
         iov.iov_len = n * BDRV_SECTOR_SIZE;
         qemu_iovec_init_external(&bounce_qiov, &iov, 1);
 
-        ret = blk_co_preadv(blk, start * job->cluster_size,
-                            bounce_qiov.size, &bounce_qiov,
-                            is_write_notifier ? BDRV_REQ_NO_SERIALISING : 0);
+        if (is_write_notifier) {
+            ret = bdrv_co_readv_no_serialising(bs,
+                                           start * BACKUP_SECTORS_PER_CLUSTER,
+                                           n, &bounce_qiov);
+        } else {
+            ret = bdrv_co_readv(bs, start * BACKUP_SECTORS_PER_CLUSTER, n,
+                                &bounce_qiov);
+        }
         if (ret < 0) {
             trace_backup_do_cow_read_fail(job, start, ret);
             if (error_is_read) {
@@ -146,12 +148,13 @@ static int coroutine_fn backup_do_cow(BackupBlockJob *job,
         }
 
         if (buffer_is_zero(iov.iov_base, iov.iov_len)) {
-            ret = blk_co_pwrite_zeroes(job->target, start * job->cluster_size,
-                                       bounce_qiov.size, BDRV_REQ_MAY_UNMAP);
+            ret = bdrv_co_write_zeroes(job->target,
+                                       start * BACKUP_SECTORS_PER_CLUSTER,
+                                       n, BDRV_REQ_MAY_UNMAP);
         } else {
-            ret = blk_co_pwritev(job->target, start * job->cluster_size,
-                                 bounce_qiov.size, &bounce_qiov,
-                                 job->compress ? BDRV_REQ_WRITE_COMPRESSED : 0);
+            ret = bdrv_co_writev(job->target,
+                                 start * BACKUP_SECTORS_PER_CLUSTER, n,
+                                 &bounce_qiov);
         }
         if (ret < 0) {
             trace_backup_do_cow_write_fail(job, start, ret);
@@ -161,7 +164,7 @@ static int coroutine_fn backup_do_cow(BackupBlockJob *job,
             goto out;
         }
 
-        set_bit(start, job->done_bitmap);
+        hbitmap_set(job->bitmap, start, 1);
 
         /* Publish progress, guest I/O counts as progress too.  Note that the
          * offset field is an opaque progress value, it is not a disk offset.
@@ -188,16 +191,14 @@ static int coroutine_fn backup_before_write_notify(
         NotifierWithReturn *notifier,
         void *opaque)
 {
-    BackupBlockJob *job = container_of(notifier, BackupBlockJob, before_write);
     BdrvTrackedRequest *req = opaque;
     int64_t sector_num = req->offset >> BDRV_SECTOR_BITS;
     int nb_sectors = req->bytes >> BDRV_SECTOR_BITS;
 
-    assert(req->bs == blk_bs(job->common.blk));
     assert((req->offset & (BDRV_SECTOR_SIZE - 1)) == 0);
     assert((req->bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
 
-    return backup_do_cow(job, sector_num, nb_sectors, NULL, true);
+    return backup_do_cow(req->bs, sector_num, nb_sectors, NULL, true);
 }
 
 static void backup_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -211,10 +212,19 @@ static void backup_set_speed(BlockJob *job, int64_t speed, Error **errp)
     ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
 }
 
+static void backup_iostatus_reset(BlockJob *job)
+{
+    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
+
+    if (s->target->blk) {
+        blk_iostatus_reset(s->target->blk);
+    }
+}
+
 static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
 {
     BdrvDirtyBitmap *bm;
-    BlockDriverState *bs = blk_bs(job->common.blk);
+    BlockDriverState *bs = job->common.bs;
 
     if (ret < 0 || block_job_is_cancelled(&job->common)) {
         /* Merge the successor back into the parent, delete nothing. */
@@ -243,96 +253,24 @@ static void backup_abort(BlockJob *job)
     }
 }
 
-static void backup_clean(BlockJob *job)
-{
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
-    assert(s->target);
-    blk_unref(s->target);
-    s->target = NULL;
-}
-
-static void backup_attached_aio_context(BlockJob *job, AioContext *aio_context)
-{
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
-
-    blk_set_aio_context(s->target, aio_context);
-}
-
-void backup_do_checkpoint(BlockJob *job, Error **errp)
-{
-    BackupBlockJob *backup_job = container_of(job, BackupBlockJob, common);
-    int64_t len;
-
-    assert(job->driver->job_type == BLOCK_JOB_TYPE_BACKUP);
-
-    if (backup_job->sync_mode != MIRROR_SYNC_MODE_NONE) {
-        error_setg(errp, "The backup job only supports block checkpoint in"
-                   " sync=none mode");
-        return;
-    }
-
-    len = DIV_ROUND_UP(backup_job->common.len, backup_job->cluster_size);
-    bitmap_zero(backup_job->done_bitmap, len);
-}
-
-void backup_wait_for_overlapping_requests(BlockJob *job, int64_t sector_num,
-                                          int nb_sectors)
-{
-    BackupBlockJob *backup_job = container_of(job, BackupBlockJob, common);
-    int64_t sectors_per_cluster = cluster_size_sectors(backup_job);
-    int64_t start, end;
-
-    assert(job->driver->job_type == BLOCK_JOB_TYPE_BACKUP);
-
-    start = sector_num / sectors_per_cluster;
-    end = DIV_ROUND_UP(sector_num + nb_sectors, sectors_per_cluster);
-    wait_for_overlapping_requests(backup_job, start, end);
-}
-
-void backup_cow_request_begin(CowRequest *req, BlockJob *job,
-                              int64_t sector_num,
-                              int nb_sectors)
-{
-    BackupBlockJob *backup_job = container_of(job, BackupBlockJob, common);
-    int64_t sectors_per_cluster = cluster_size_sectors(backup_job);
-    int64_t start, end;
-
-    assert(job->driver->job_type == BLOCK_JOB_TYPE_BACKUP);
-
-    start = sector_num / sectors_per_cluster;
-    end = DIV_ROUND_UP(sector_num + nb_sectors, sectors_per_cluster);
-    cow_request_begin(req, backup_job, start, end);
-}
-
-void backup_cow_request_end(CowRequest *req)
-{
-    cow_request_end(req);
-}
-
-static void backup_drain(BlockJob *job)
-{
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
-
-    /* Need to keep a reference in case blk_drain triggers execution
-     * of backup_complete...
-     */
-    if (s->target) {
-        BlockBackend *target = s->target;
-        blk_ref(target);
-        blk_drain(target);
-        blk_unref(target);
-    }
-}
+static const BlockJobDriver backup_job_driver = {
+    .instance_size  = sizeof(BackupBlockJob),
+    .job_type       = BLOCK_JOB_TYPE_BACKUP,
+    .set_speed      = backup_set_speed,
+    .iostatus_reset = backup_iostatus_reset,
+    .commit         = backup_commit,
+    .abort          = backup_abort,
+};
 
 static BlockErrorAction backup_error_action(BackupBlockJob *job,
                                             bool read, int error)
 {
     if (read) {
-        return block_job_error_action(&job->common, job->on_source_error,
-                                      true, error);
+        return block_job_error_action(&job->common, job->common.bs,
+                                      job->on_source_error, true, error);
     } else {
-        return block_job_error_action(&job->common, job->on_target_error,
-                                      false, error);
+        return block_job_error_action(&job->common, job->target,
+                                      job->on_target_error, false, error);
     }
 }
 
@@ -342,8 +280,11 @@ typedef struct {
 
 static void backup_complete(BlockJob *job, void *opaque)
 {
+    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
     BackupCompleteData *data = opaque;
 
+    bdrv_unref(s->target);
+
     block_job_completed(job, data->ret);
     g_free(data);
 }
@@ -383,56 +324,54 @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
     int64_t cluster;
     int64_t end;
     int64_t last_cluster = -1;
-    int64_t sectors_per_cluster = cluster_size_sectors(job);
-    BdrvDirtyBitmapIter *dbi;
+    BlockDriverState *bs = job->common.bs;
+    HBitmapIter hbi;
 
     granularity = bdrv_dirty_bitmap_granularity(job->sync_bitmap);
-    clusters_per_iter = MAX((granularity / job->cluster_size), 1);
-    dbi = bdrv_dirty_iter_new(job->sync_bitmap, 0);
+    clusters_per_iter = MAX((granularity / BACKUP_CLUSTER_SIZE), 1);
+    bdrv_dirty_iter_init(job->sync_bitmap, &hbi);
 
     /* Find the next dirty sector(s) */
-    while ((sector = bdrv_dirty_iter_next(dbi)) != -1) {
-        cluster = sector / sectors_per_cluster;
+    while ((sector = hbitmap_iter_next(&hbi)) != -1) {
+        cluster = sector / BACKUP_SECTORS_PER_CLUSTER;
 
         /* Fake progress updates for any clusters we skipped */
         if (cluster != last_cluster + 1) {
             job->common.offset += ((cluster - last_cluster - 1) *
-                                   job->cluster_size);
+                                   BACKUP_CLUSTER_SIZE);
         }
 
         for (end = cluster + clusters_per_iter; cluster < end; cluster++) {
             do {
                 if (yield_and_check(job)) {
-                    goto out;
+                    return ret;
                 }
-                ret = backup_do_cow(job, cluster * sectors_per_cluster,
-                                    sectors_per_cluster, &error_is_read,
+                ret = backup_do_cow(bs, cluster * BACKUP_SECTORS_PER_CLUSTER,
+                                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read,
                                     false);
                 if ((ret < 0) &&
                     backup_error_action(job, error_is_read, -ret) ==
                     BLOCK_ERROR_ACTION_REPORT) {
-                    goto out;
+                    return ret;
                 }
             } while (ret < 0);
         }
 
         /* If the bitmap granularity is smaller than the backup granularity,
          * we need to advance the iterator pointer to the next cluster. */
-        if (granularity < job->cluster_size) {
-            bdrv_set_dirty_iter(dbi, cluster * sectors_per_cluster);
+        if (granularity < BACKUP_CLUSTER_SIZE) {
+            bdrv_set_dirty_iter(&hbi, cluster * BACKUP_SECTORS_PER_CLUSTER);
         }
 
         last_cluster = cluster - 1;
     }
 
     /* Play some final catchup with the progress meter */
-    end = DIV_ROUND_UP(job->common.len, job->cluster_size);
+    end = DIV_ROUND_UP(job->common.len, BACKUP_CLUSTER_SIZE);
     if (last_cluster + 1 < end) {
-        job->common.offset += ((end - last_cluster - 1) * job->cluster_size);
+        job->common.offset += ((end - last_cluster - 1) * BACKUP_CLUSTER_SIZE);
     }
 
-out:
-    bdrv_dirty_iter_free(dbi);
     return ret;
 }
 
@@ -440,27 +379,38 @@ static void coroutine_fn backup_run(void *opaque)
 {
     BackupBlockJob *job = opaque;
     BackupCompleteData *data;
-    BlockDriverState *bs = blk_bs(job->common.blk);
+    BlockDriverState *bs = job->common.bs;
+    BlockDriverState *target = job->target;
+    BlockdevOnError on_target_error = job->on_target_error;
+    NotifierWithReturn before_write = {
+        .notify = backup_before_write_notify,
+    };
     int64_t start, end;
-    int64_t sectors_per_cluster = cluster_size_sectors(job);
     int ret = 0;
 
     QLIST_INIT(&job->inflight_reqs);
     qemu_co_rwlock_init(&job->flush_rwlock);
 
     start = 0;
-    end = DIV_ROUND_UP(job->common.len, job->cluster_size);
+    end = DIV_ROUND_UP(job->common.len, BACKUP_CLUSTER_SIZE);
 
-    job->done_bitmap = bitmap_new(end);
+    job->bitmap = hbitmap_alloc(end, 0);
 
-    job->before_write.notify = backup_before_write_notify;
-    bdrv_add_before_write_notifier(bs, &job->before_write);
+    bdrv_set_enable_write_cache(target, true);
+    if (target->blk) {
+        blk_set_on_error(target->blk, on_target_error, on_target_error);
+        blk_iostatus_enable(target->blk);
+    }
+
+    bdrv_add_before_write_notifier(bs, &before_write);
 
     if (job->sync_mode == MIRROR_SYNC_MODE_NONE) {
         while (!block_job_is_cancelled(&job->common)) {
             /* Yield until the job is cancelled.  We just let our before_write
              * notify callback service CoW requests. */
-            block_job_yield(&job->common);
+            job->common.busy = false;
+            qemu_coroutine_yield();
+            job->common.busy = true;
         }
     } else if (job->sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
         ret = backup_run_incremental(job);
@@ -468,19 +418,18 @@ static void coroutine_fn backup_run(void *opaque)
         /* Both FULL and TOP SYNC_MODE's require copying.. */
         for (; start < end; start++) {
             bool error_is_read;
-            int alloced = 0;
-
             if (yield_and_check(job)) {
                 break;
             }
 
             if (job->sync_mode == MIRROR_SYNC_MODE_TOP) {
                 int i, n;
+                int alloced = 0;
 
                 /* Check to see if these blocks are already in the
                  * backing file. */
 
-                for (i = 0; i < sectors_per_cluster;) {
+                for (i = 0; i < BACKUP_SECTORS_PER_CLUSTER;) {
                     /* bdrv_is_allocated() only returns true/false based
                      * on the first set of sectors it comes across that
                      * are are all in the same state.
@@ -489,11 +438,11 @@ static void coroutine_fn backup_run(void *opaque)
                      * needed but at some point that is always the case. */
                     alloced =
                         bdrv_is_allocated(bs,
-                                start * sectors_per_cluster + i,
-                                sectors_per_cluster - i, &n);
+                                start * BACKUP_SECTORS_PER_CLUSTER + i,
+                                BACKUP_SECTORS_PER_CLUSTER - i, &n);
                     i += n;
 
-                    if (alloced || n == 0) {
+                    if (alloced == 1 || n == 0) {
                         break;
                     }
                 }
@@ -505,13 +454,8 @@ static void coroutine_fn backup_run(void *opaque)
                 }
             }
             /* FULL sync mode we copy the whole drive. */
-            if (alloced < 0) {
-                ret = alloced;
-            } else {
-                ret = backup_do_cow(job, start * sectors_per_cluster,
-                                    sectors_per_cluster, &error_is_read,
-                                    false);
-            }
+            ret = backup_do_cow(bs, start * BACKUP_SECTORS_PER_CLUSTER,
+                    BACKUP_SECTORS_PER_CLUSTER, &error_is_read, false);
             if (ret < 0) {
                 /* Depending on error action, fail now or retry cluster */
                 BlockErrorAction action =
@@ -526,96 +470,86 @@ static void coroutine_fn backup_run(void *opaque)
         }
     }
 
-    notifier_with_return_remove(&job->before_write);
+    notifier_with_return_remove(&before_write);
 
     /* wait until pending backup_do_cow() calls have completed */
     qemu_co_rwlock_wrlock(&job->flush_rwlock);
     qemu_co_rwlock_unlock(&job->flush_rwlock);
-    g_free(job->done_bitmap);
+    hbitmap_free(job->bitmap);
+
+    if (target->blk) {
+        blk_iostatus_disable(target->blk);
+    }
+    bdrv_op_unblock_all(target, job->common.blocker);
 
     data = g_malloc(sizeof(*data));
     data->ret = ret;
     block_job_defer_to_main_loop(&job->common, backup_complete, data);
 }
 
-static const BlockJobDriver backup_job_driver = {
-    .instance_size          = sizeof(BackupBlockJob),
-    .job_type               = BLOCK_JOB_TYPE_BACKUP,
-    .start                  = backup_run,
-    .set_speed              = backup_set_speed,
-    .commit                 = backup_commit,
-    .abort                  = backup_abort,
-    .clean                  = backup_clean,
-    .attached_aio_context   = backup_attached_aio_context,
-    .drain                  = backup_drain,
-};
-
-BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
-                  BlockDriverState *target, int64_t speed,
-                  MirrorSyncMode sync_mode, BdrvDirtyBitmap *sync_bitmap,
-                  bool compress,
+void backup_start(BlockDriverState *bs, BlockDriverState *target,
+                  int64_t speed, MirrorSyncMode sync_mode,
+                  BdrvDirtyBitmap *sync_bitmap,
                   BlockdevOnError on_source_error,
                   BlockdevOnError on_target_error,
-                  int creation_flags,
                   BlockCompletionFunc *cb, void *opaque,
                   BlockJobTxn *txn, Error **errp)
 {
     int64_t len;
-    BlockDriverInfo bdi;
-    BackupBlockJob *job = NULL;
-    int ret;
 
     assert(bs);
     assert(target);
+    assert(cb);
 
     if (bs == target) {
         error_setg(errp, "Source and target cannot be the same");
-        return NULL;
+        return;
+    }
+
+    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
+         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
+        (!bs->blk || !blk_iostatus_is_enabled(bs->blk))) {
+        error_setg(errp, QERR_INVALID_PARAMETER, "on-source-error");
+        return;
     }
 
     if (!bdrv_is_inserted(bs)) {
         error_setg(errp, "Device is not inserted: %s",
                    bdrv_get_device_name(bs));
-        return NULL;
+        return;
     }
 
     if (!bdrv_is_inserted(target)) {
         error_setg(errp, "Device is not inserted: %s",
                    bdrv_get_device_name(target));
-        return NULL;
-    }
-
-    if (compress && target->drv->bdrv_co_pwritev_compressed == NULL) {
-        error_setg(errp, "Compression is not supported for this drive %s",
-                   bdrv_get_device_name(target));
-        return NULL;
+        return;
     }
 
     if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_BACKUP_SOURCE, errp)) {
-        return NULL;
+        return;
     }
 
     if (bdrv_op_is_blocked(target, BLOCK_OP_TYPE_BACKUP_TARGET, errp)) {
-        return NULL;
+        return;
     }
 
     if (sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
         if (!sync_bitmap) {
             error_setg(errp, "must provide a valid bitmap name for "
                              "\"incremental\" sync mode");
-            return NULL;
+            return;
         }
 
         /* Create a new bitmap, and freeze/disable this one. */
         if (bdrv_dirty_bitmap_create_successor(bs, sync_bitmap, errp) < 0) {
-            return NULL;
+            return;
         }
     } else if (sync_bitmap) {
         error_setg(errp,
                    "a sync_bitmap was provided to backup_run, "
                    "but received an incompatible sync_mode (%s)",
                    MirrorSyncMode_lookup[sync_mode]);
-        return NULL;
+        return;
     }
 
     len = bdrv_getlength(bs);
@@ -625,75 +559,28 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
         goto error;
     }
 
-    /* job->common.len is fixed, so we can't allow resize */
-    job = block_job_create(job_id, &backup_job_driver, bs,
-                           BLK_PERM_CONSISTENT_READ,
-                           BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
-                           BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD,
-                           speed, creation_flags, cb, opaque, errp);
+    BackupBlockJob *job = block_job_create(&backup_job_driver, bs, speed,
+                                           cb, opaque, errp);
     if (!job) {
         goto error;
     }
 
-    /* The target must match the source in size, so no resize here either */
-    job->target = blk_new(BLK_PERM_WRITE,
-                          BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
-                          BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD);
-    ret = blk_insert_bs(job->target, target, errp);
-    if (ret < 0) {
-        goto error;
-    }
+    bdrv_op_block_all(target, job->common.blocker);
 
     job->on_source_error = on_source_error;
     job->on_target_error = on_target_error;
+    job->target = target;
     job->sync_mode = sync_mode;
     job->sync_bitmap = sync_mode == MIRROR_SYNC_MODE_INCREMENTAL ?
                        sync_bitmap : NULL;
-    job->compress = compress;
-
-    /* If there is no backing file on the target, we cannot rely on COW if our
-     * backup cluster size is smaller than the target cluster size. Even for
-     * targets with a backing file, try to avoid COW if possible. */
-    ret = bdrv_get_info(target, &bdi);
-    if (ret == -ENOTSUP && !target->backing) {
-        /* Cluster size is not defined */
-        error_report("WARNING: The target block device doesn't provide "
-                     "information about the block size and it doesn't have a "
-                     "backing file. The default block size of %u bytes is "
-                     "used. If the actual block size of the target exceeds "
-                     "this default, the backup may be unusable",
-                     BACKUP_CLUSTER_SIZE_DEFAULT);
-        job->cluster_size = BACKUP_CLUSTER_SIZE_DEFAULT;
-    } else if (ret < 0 && !target->backing) {
-        error_setg_errno(errp, -ret,
-            "Couldn't determine the cluster size of the target image, "
-            "which has no backing file");
-        error_append_hint(errp,
-            "Aborting, since this may create an unusable destination image\n");
-        goto error;
-    } else if (ret < 0 && target->backing) {
-        /* Not fatal; just trudge on ahead. */
-        job->cluster_size = BACKUP_CLUSTER_SIZE_DEFAULT;
-    } else {
-        job->cluster_size = MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
-    }
-
-    /* Required permissions are already taken with target's blk_new() */
-    block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
-                       &error_abort);
     job->common.len = len;
+    job->common.co = qemu_coroutine_create(backup_run);
     block_job_txn_add_job(txn, &job->common);
-
-    return &job->common;
+    qemu_coroutine_enter(job->common.co, job);
+    return;
 
  error:
     if (sync_bitmap) {
         bdrv_reclaim_dirty_bitmap(bs, sync_bitmap, NULL);
     }
-    if (job) {
-        backup_clean(&job->common);
-        block_job_early_fail(&job->common);
-    }
-
-    return NULL;
 }

block/blkdebug.c

@@ -1,7 +1,6 @@
 /*
  * Block protocol for I/O error injection
  *
- * Copyright (C) 2016-2017 Red Hat, Inc.
  * Copyright (c) 2010 Kevin Wolf <kwolf@redhat.com>
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
@@ -23,37 +22,28 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
-#include "qapi/error.h"
-#include "qemu/cutils.h"
+#include "qemu-common.h"
 #include "qemu/config-file.h"
 #include "block/block_int.h"
 #include "qemu/module.h"
 #include "qapi/qmp/qbool.h"
 #include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qint.h"
 #include "qapi/qmp/qstring.h"
 #include "sysemu/qtest.h"
 
 typedef struct BDRVBlkdebugState {
     int state;
     int new_state;
-    uint64_t align;
-    uint64_t max_transfer;
-    uint64_t opt_write_zero;
-    uint64_t max_write_zero;
-    uint64_t opt_discard;
-    uint64_t max_discard;
 
-    /* For blkdebug_refresh_filename() */
-    char *config_file;
-
-    QLIST_HEAD(, BlkdebugRule) rules[BLKDBG__MAX];
+    QLIST_HEAD(, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
     QSIMPLEQ_HEAD(, BlkdebugRule) active_rules;
     QLIST_HEAD(, BlkdebugSuspendedReq) suspended_reqs;
 } BDRVBlkdebugState;
 
 typedef struct BlkdebugAIOCB {
     BlockAIOCB common;
+    QEMUBH *bh;
     int ret;
 } BlkdebugAIOCB;
 
@@ -63,6 +53,10 @@ typedef struct BlkdebugSuspendedReq {
     QLIST_ENTRY(BlkdebugSuspendedReq) next;
 } BlkdebugSuspendedReq;
 
+static const AIOCBInfo blkdebug_aiocb_info = {
+    .aiocb_size    = sizeof(BlkdebugAIOCB),
+};
+
 enum {
     ACTION_INJECT_ERROR,
     ACTION_SET_STATE,
@@ -70,7 +64,7 @@ enum {
 };
 
 typedef struct BlkdebugRule {
-    BlkdebugEvent event;
+    BlkDebugEvent event;
     int action;
     int state;
     union {
@@ -78,7 +72,7 @@ typedef struct BlkdebugRule {
             int error;
             int immediately;
             int once;
-            int64_t offset;
+            int64_t sector;
         } inject;
         struct {
             int new_state;
@@ -149,12 +143,69 @@ static QemuOptsList *config_groups[] = {
     NULL
 };
 
-static int get_event_by_name(const char *name, BlkdebugEvent *event)
+static const char *event_names[BLKDBG_EVENT_MAX] = {
+    [BLKDBG_L1_UPDATE]                      = "l1_update",
+    [BLKDBG_L1_GROW_ALLOC_TABLE]            = "l1_grow.alloc_table",
+    [BLKDBG_L1_GROW_WRITE_TABLE]            = "l1_grow.write_table",
+    [BLKDBG_L1_GROW_ACTIVATE_TABLE]         = "l1_grow.activate_table",
+
+    [BLKDBG_L2_LOAD]                        = "l2_load",
+    [BLKDBG_L2_UPDATE]                      = "l2_update",
+    [BLKDBG_L2_UPDATE_COMPRESSED]           = "l2_update_compressed",
+    [BLKDBG_L2_ALLOC_COW_READ]              = "l2_alloc.cow_read",
+    [BLKDBG_L2_ALLOC_WRITE]                 = "l2_alloc.write",
+
+    [BLKDBG_READ_AIO]                       = "read_aio",
+    [BLKDBG_READ_BACKING_AIO]               = "read_backing_aio",
+    [BLKDBG_READ_COMPRESSED]                = "read_compressed",
+
+    [BLKDBG_WRITE_AIO]                      = "write_aio",
+    [BLKDBG_WRITE_COMPRESSED]               = "write_compressed",
+
+    [BLKDBG_VMSTATE_LOAD]                   = "vmstate_load",
+    [BLKDBG_VMSTATE_SAVE]                   = "vmstate_save",
+
+    [BLKDBG_COW_READ]                       = "cow_read",
+    [BLKDBG_COW_WRITE]                      = "cow_write",
+
+    [BLKDBG_REFTABLE_LOAD]                  = "reftable_load",
+    [BLKDBG_REFTABLE_GROW]                  = "reftable_grow",
+    [BLKDBG_REFTABLE_UPDATE]                = "reftable_update",
+
+    [BLKDBG_REFBLOCK_LOAD]                  = "refblock_load",
+    [BLKDBG_REFBLOCK_UPDATE]                = "refblock_update",
+    [BLKDBG_REFBLOCK_UPDATE_PART]           = "refblock_update_part",
+    [BLKDBG_REFBLOCK_ALLOC]                 = "refblock_alloc",
+    [BLKDBG_REFBLOCK_ALLOC_HOOKUP]          = "refblock_alloc.hookup",
+    [BLKDBG_REFBLOCK_ALLOC_WRITE]           = "refblock_alloc.write",
+    [BLKDBG_REFBLOCK_ALLOC_WRITE_BLOCKS]    = "refblock_alloc.write_blocks",
+    [BLKDBG_REFBLOCK_ALLOC_WRITE_TABLE]     = "refblock_alloc.write_table",
+    [BLKDBG_REFBLOCK_ALLOC_SWITCH_TABLE]    = "refblock_alloc.switch_table",
+
+    [BLKDBG_CLUSTER_ALLOC]                  = "cluster_alloc",
+    [BLKDBG_CLUSTER_ALLOC_BYTES]            = "cluster_alloc_bytes",
+    [BLKDBG_CLUSTER_FREE]                   = "cluster_free",
+
+    [BLKDBG_FLUSH_TO_OS]                    = "flush_to_os",
+    [BLKDBG_FLUSH_TO_DISK]                  = "flush_to_disk",
+
+    [BLKDBG_PWRITEV_RMW_HEAD]               = "pwritev_rmw.head",
+    [BLKDBG_PWRITEV_RMW_AFTER_HEAD]         = "pwritev_rmw.after_head",
+    [BLKDBG_PWRITEV_RMW_TAIL]               = "pwritev_rmw.tail",
+    [BLKDBG_PWRITEV_RMW_AFTER_TAIL]         = "pwritev_rmw.after_tail",
+    [BLKDBG_PWRITEV]                        = "pwritev",
+    [BLKDBG_PWRITEV_ZERO]                   = "pwritev_zero",
+    [BLKDBG_PWRITEV_DONE]                   = "pwritev_done",
+
+    [BLKDBG_EMPTY_IMAGE_PREPARE]            = "empty_image_prepare",
+};
+
+static int get_event_by_name(const char *name, BlkDebugEvent *event)
 {
     int i;
 
-    for (i = 0; i < BLKDBG__MAX; i++) {
-        if (!strcmp(BlkdebugEvent_lookup[i], name)) {
+    for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
+        if (!strcmp(event_names[i], name)) {
             *event = i;
             return 0;
         }
@@ -173,9 +224,8 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
     struct add_rule_data *d = opaque;
     BDRVBlkdebugState *s = d->s;
     const char* event_name;
-    BlkdebugEvent event;
+    BlkDebugEvent event;
     struct BlkdebugRule *rule;
-    int64_t sector;
 
     /* Find the right event for the rule */
     event_name = qemu_opt_get(opts, "event");
@@ -202,9 +252,7 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
         rule->options.inject.once  = qemu_opt_get_bool(opts, "once", 0);
         rule->options.inject.immediately =
             qemu_opt_get_bool(opts, "immediately", 0);
-        sector = qemu_opt_get_number(opts, "sector", -1);
-        rule->options.inject.offset =
-            sector == -1 ? -1 : sector * BDRV_SECTOR_SIZE;
+        rule->options.inject.sector = qemu_opt_get_number(opts, "sector", -1);
         break;
 
     case ACTION_SET_STATE:
@@ -306,7 +354,7 @@ static void blkdebug_parse_filename(const char *filename, QDict *options,
     if (!strstart(filename, "blkdebug:", &filename)) {
         /* There was no prefix; therefore, all options have to be already
            present in the QDict (except for the filename) */
-        qdict_put_str(options, "x-image", filename);
+        qdict_put(options, "x-image", qstring_from_str(filename));
         return;
     }
 
@@ -325,7 +373,7 @@ static void blkdebug_parse_filename(const char *filename, QDict *options,
 
     /* TODO Allow multi-level nesting and set file.filename here */
     filename = c + 1;
-    qdict_put_str(options, "x-image", filename);
+    qdict_put(options, "x-image", qstring_from_str(filename));
 }
 
 static QemuOptsList runtime_opts = {
@@ -347,31 +395,6 @@ static QemuOptsList runtime_opts = {
             .type = QEMU_OPT_SIZE,
             .help = "Required alignment in bytes",
         },
-        {
-            .name = "max-transfer",
-            .type = QEMU_OPT_SIZE,
-            .help = "Maximum transfer size in bytes",
-        },
-        {
-            .name = "opt-write-zero",
-            .type = QEMU_OPT_SIZE,
-            .help = "Optimum write zero alignment in bytes",
-        },
-        {
-            .name = "max-write-zero",
-            .type = QEMU_OPT_SIZE,
-            .help = "Maximum write zero size in bytes",
-        },
-        {
-            .name = "opt-discard",
-            .type = QEMU_OPT_SIZE,
-            .help = "Optimum discard alignment in bytes",
-        },
-        {
-            .name = "max-discard",
-            .type = QEMU_OPT_SIZE,
-            .help = "Maximum discard size in bytes",
-        },
         { /* end of list */ }
     },
 };
@@ -382,8 +405,9 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
     BDRVBlkdebugState *s = bs->opaque;
     QemuOpts *opts;
     Error *local_err = NULL;
-    int ret;
+    const char *config;
     uint64_t align;
+    int ret;
 
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
@@ -394,8 +418,8 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     /* Read rules from config file or command line options */
-    s->config_file = g_strdup(qemu_opt_get(opts, "config"));
-    ret = read_config(s, s->config_file, options, errp);
+    config = qemu_opt_get(opts, "config");
+    ret = read_config(s, config, options, errp);
     if (ret) {
         goto out;
     }
@@ -412,234 +436,127 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
         goto out;
     }
 
-    bs->supported_write_flags = BDRV_REQ_FUA &
-        bs->file->bs->supported_write_flags;
-    bs->supported_zero_flags = (BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP) &
-        bs->file->bs->supported_zero_flags;
-    ret = -EINVAL;
-
-    /* Set alignment overrides */
-    s->align = qemu_opt_get_size(opts, "align", 0);
-    if (s->align && (s->align >= INT_MAX || !is_power_of_2(s->align))) {
-        error_setg(errp, "Cannot meet constraints with align %" PRIu64,
-                   s->align);
-        goto out;
-    }
-    align = MAX(s->align, bs->file->bs->bl.request_alignment);
-
-    s->max_transfer = qemu_opt_get_size(opts, "max-transfer", 0);
-    if (s->max_transfer &&
-        (s->max_transfer >= INT_MAX ||
-         !QEMU_IS_ALIGNED(s->max_transfer, align))) {
-        error_setg(errp, "Cannot meet constraints with max-transfer %" PRIu64,
-                   s->max_transfer);
-        goto out;
-    }
-
-    s->opt_write_zero = qemu_opt_get_size(opts, "opt-write-zero", 0);
-    if (s->opt_write_zero &&
-        (s->opt_write_zero >= INT_MAX ||
-         !QEMU_IS_ALIGNED(s->opt_write_zero, align))) {
-        error_setg(errp, "Cannot meet constraints with opt-write-zero %" PRIu64,
-                   s->opt_write_zero);
-        goto out;
-    }
-
-    s->max_write_zero = qemu_opt_get_size(opts, "max-write-zero", 0);
-    if (s->max_write_zero &&
-        (s->max_write_zero >= INT_MAX ||
-         !QEMU_IS_ALIGNED(s->max_write_zero,
-                          MAX(s->opt_write_zero, align)))) {
-        error_setg(errp, "Cannot meet constraints with max-write-zero %" PRIu64,
-                   s->max_write_zero);
-        goto out;
-    }
-
-    s->opt_discard = qemu_opt_get_size(opts, "opt-discard", 0);
-    if (s->opt_discard &&
-        (s->opt_discard >= INT_MAX ||
-         !QEMU_IS_ALIGNED(s->opt_discard, align))) {
-        error_setg(errp, "Cannot meet constraints with opt-discard %" PRIu64,
-                   s->opt_discard);
-        goto out;
-    }
-
-    s->max_discard = qemu_opt_get_size(opts, "max-discard", 0);
-    if (s->max_discard &&
-        (s->max_discard >= INT_MAX ||
-         !QEMU_IS_ALIGNED(s->max_discard,
-                          MAX(s->opt_discard, align)))) {
-        error_setg(errp, "Cannot meet constraints with max-discard %" PRIu64,
-                   s->max_discard);
-        goto out;
+    /* Set request alignment */
+    align = qemu_opt_get_size(opts, "align", bs->request_alignment);
+    if (align > 0 && align < INT_MAX && !(align & (align - 1))) {
+        bs->request_alignment = align;
+    } else {
+        error_setg(errp, "Invalid alignment");
+        ret = -EINVAL;
+        goto fail_unref;
     }
 
     ret = 0;
+    goto out;
+
+fail_unref:
+    bdrv_unref_child(bs, bs->file);
 out:
-    if (ret < 0) {
-        g_free(s->config_file);
-    }
     qemu_opts_del(opts);
     return ret;
 }
 
-static int rule_check(BlockDriverState *bs, uint64_t offset, uint64_t bytes)
+static void error_callback_bh(void *opaque)
+{
+    struct BlkdebugAIOCB *acb = opaque;
+    qemu_bh_delete(acb->bh);
+    acb->common.cb(acb->common.opaque, acb->ret);
+    qemu_aio_unref(acb);
+}
+
+static BlockAIOCB *inject_error(BlockDriverState *bs,
+    BlockCompletionFunc *cb, void *opaque, BlkdebugRule *rule)
 {
     BDRVBlkdebugState *s = bs->opaque;
-    BlkdebugRule *rule = NULL;
-    int error;
-    bool immediately;
-
-    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
-        uint64_t inject_offset = rule->options.inject.offset;
-
-        if (inject_offset == -1 ||
-            (bytes && inject_offset >= offset &&
-             inject_offset < offset + bytes))
-        {
-            break;
-        }
-    }
-
-    if (!rule || !rule->options.inject.error) {
-        return 0;
-    }
-
-    immediately = rule->options.inject.immediately;
-    error = rule->options.inject.error;
+    int error = rule->options.inject.error;
+    struct BlkdebugAIOCB *acb;
+    QEMUBH *bh;
+    bool immediately = rule->options.inject.immediately;
 
     if (rule->options.inject.once) {
         QSIMPLEQ_REMOVE(&s->active_rules, rule, BlkdebugRule, active_next);
         remove_rule(rule);
     }
 
-    if (!immediately) {
-        aio_co_schedule(qemu_get_current_aio_context(), qemu_coroutine_self());
-        qemu_coroutine_yield();
+    if (immediately) {
+        return NULL;
     }
 
-    return -error;
+    acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque);
+    acb->ret = -error;
+
+    bh = aio_bh_new(bdrv_get_aio_context(bs), error_callback_bh, acb);
+    acb->bh = bh;
+    qemu_bh_schedule(bh);
+
+    return &acb->common;
 }
 
-static int coroutine_fn
-blkdebug_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
-                   QEMUIOVector *qiov, int flags)
+static BlockAIOCB *blkdebug_aio_readv(BlockDriverState *bs,
+    int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+    BlockCompletionFunc *cb, void *opaque)
 {
-    int err;
+    BDRVBlkdebugState *s = bs->opaque;
+    BlkdebugRule *rule = NULL;
 
-    /* Sanity check block layer guarantees */
-    assert(QEMU_IS_ALIGNED(offset, bs->bl.request_alignment));
-    assert(QEMU_IS_ALIGNED(bytes, bs->bl.request_alignment));
-    if (bs->bl.max_transfer) {
-        assert(bytes <= bs->bl.max_transfer);
+    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
+        if (rule->options.inject.sector == -1 ||
+            (rule->options.inject.sector >= sector_num &&
+             rule->options.inject.sector < sector_num + nb_sectors)) {
+            break;
+        }
     }
 
-    err = rule_check(bs, offset, bytes);
-    if (err) {
-        return err;
+    if (rule && rule->options.inject.error) {
+        return inject_error(bs, cb, opaque, rule);
     }
 
-    return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
+    return bdrv_aio_readv(bs->file->bs, sector_num, qiov, nb_sectors,
+                          cb, opaque);
 }
 
-static int coroutine_fn
-blkdebug_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
-                    QEMUIOVector *qiov, int flags)
+static BlockAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
+    int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+    BlockCompletionFunc *cb, void *opaque)
 {
-    int err;
+    BDRVBlkdebugState *s = bs->opaque;
+    BlkdebugRule *rule = NULL;
 
-    /* Sanity check block layer guarantees */
-    assert(QEMU_IS_ALIGNED(offset, bs->bl.request_alignment));
-    assert(QEMU_IS_ALIGNED(bytes, bs->bl.request_alignment));
-    if (bs->bl.max_transfer) {
-        assert(bytes <= bs->bl.max_transfer);
+    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
+        if (rule->options.inject.sector == -1 ||
+            (rule->options.inject.sector >= sector_num &&
+             rule->options.inject.sector < sector_num + nb_sectors)) {
+            break;
+        }
     }
 
-    err = rule_check(bs, offset, bytes);
-    if (err) {
-        return err;
+    if (rule && rule->options.inject.error) {
+        return inject_error(bs, cb, opaque, rule);
     }
 
-    return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
+    return bdrv_aio_writev(bs->file->bs, sector_num, qiov, nb_sectors,
+                           cb, opaque);
 }
 
-static int blkdebug_co_flush(BlockDriverState *bs)
+static BlockAIOCB *blkdebug_aio_flush(BlockDriverState *bs,
+    BlockCompletionFunc *cb, void *opaque)
 {
-    int err = rule_check(bs, 0, 0);
+    BDRVBlkdebugState *s = bs->opaque;
+    BlkdebugRule *rule = NULL;
 
-    if (err) {
-        return err;
+    QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
+        if (rule->options.inject.sector == -1) {
+            break;
+        }
     }
 
-    return bdrv_co_flush(bs->file->bs);
+    if (rule && rule->options.inject.error) {
+        return inject_error(bs, cb, opaque, rule);
+    }
+
+    return bdrv_aio_flush(bs->file->bs, cb, opaque);
 }
 
-static int coroutine_fn blkdebug_co_pwrite_zeroes(BlockDriverState *bs,
-                                                  int64_t offset, int count,
-                                                  BdrvRequestFlags flags)
-{
-    uint32_t align = MAX(bs->bl.request_alignment,
-                         bs->bl.pwrite_zeroes_alignment);
-    int err;
-
-    /* Only pass through requests that are larger than requested
-     * preferred alignment (so that we test the fallback to writes on
-     * unaligned portions), and check that the block layer never hands
-     * us anything unaligned that crosses an alignment boundary.  */
-    if (count < align) {
-        assert(QEMU_IS_ALIGNED(offset, align) ||
-               QEMU_IS_ALIGNED(offset + count, align) ||
-               DIV_ROUND_UP(offset, align) ==
-               DIV_ROUND_UP(offset + count, align));
-        return -ENOTSUP;
-    }
-    assert(QEMU_IS_ALIGNED(offset, align));
-    assert(QEMU_IS_ALIGNED(count, align));
-    if (bs->bl.max_pwrite_zeroes) {
-        assert(count <= bs->bl.max_pwrite_zeroes);
-    }
-
-    err = rule_check(bs, offset, count);
-    if (err) {
-        return err;
-    }
-
-    return bdrv_co_pwrite_zeroes(bs->file, offset, count, flags);
-}
-
-static int coroutine_fn blkdebug_co_pdiscard(BlockDriverState *bs,
-                                             int64_t offset, int count)
-{
-    uint32_t align = bs->bl.pdiscard_alignment;
-    int err;
-
-    /* Only pass through requests that are larger than requested
-     * minimum alignment, and ensure that unaligned requests do not
-     * cross optimum discard boundaries. */
-    if (count < bs->bl.request_alignment) {
-        assert(QEMU_IS_ALIGNED(offset, align) ||
-               QEMU_IS_ALIGNED(offset + count, align) ||
-               DIV_ROUND_UP(offset, align) ==
-               DIV_ROUND_UP(offset + count, align));
-        return -ENOTSUP;
-    }
-    assert(QEMU_IS_ALIGNED(offset, bs->bl.request_alignment));
-    assert(QEMU_IS_ALIGNED(count, bs->bl.request_alignment));
-    if (align && count >= align) {
-        assert(QEMU_IS_ALIGNED(offset, align));
-        assert(QEMU_IS_ALIGNED(count, align));
-    }
-    if (bs->bl.max_pdiscard) {
-        assert(count <= bs->bl.max_pdiscard);
-    }
-
-    err = rule_check(bs, offset, count);
-    if (err) {
-        return err;
-    }
-
-    return bdrv_co_pdiscard(bs->file->bs, offset, count);
-}
 
 static void blkdebug_close(BlockDriverState *bs)
 {
@@ -647,13 +564,11 @@ static void blkdebug_close(BlockDriverState *bs)
     BlkdebugRule *rule, *next;
     int i;
 
-    for (i = 0; i < BLKDBG__MAX; i++) {
+    for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
         QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
             remove_rule(rule);
         }
     }
-
-    g_free(s->config_file);
 }
 
 static void suspend_request(BlockDriverState *bs, BlkdebugRule *rule)
@@ -712,13 +627,13 @@ static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
     return injected;
 }
 
-static void blkdebug_debug_event(BlockDriverState *bs, BlkdebugEvent event)
+static void blkdebug_debug_event(BlockDriverState *bs, BlkDebugEvent event)
 {
     BDRVBlkdebugState *s = bs->opaque;
     struct BlkdebugRule *rule, *next;
     bool injected;
 
-    assert((int)event >= 0 && event < BLKDBG__MAX);
+    assert((int)event >= 0 && event < BLKDBG_EVENT_MAX);
 
     injected = false;
     s->new_state = s->state;
@@ -733,7 +648,7 @@ static int blkdebug_debug_breakpoint(BlockDriverState *bs, const char *event,
 {
     BDRVBlkdebugState *s = bs->opaque;
     struct BlkdebugRule *rule;
-    BlkdebugEvent blkdebug_event;
+    BlkDebugEvent blkdebug_event;
 
     if (get_event_by_name(event, &blkdebug_event) < 0) {
         return -ENOENT;
@@ -760,7 +675,7 @@ static int blkdebug_debug_resume(BlockDriverState *bs, const char *tag)
 
     QLIST_FOREACH_SAFE(r, &s->suspended_reqs, next, next) {
         if (!strcmp(r->tag, tag)) {
-            qemu_coroutine_enter(r->co);
+            qemu_coroutine_enter(r->co, NULL);
             return 0;
         }
     }
@@ -775,7 +690,7 @@ static int blkdebug_debug_remove_breakpoint(BlockDriverState *bs,
     BlkdebugRule *rule, *next;
     int i, ret = -ENOENT;
 
-    for (i = 0; i < BLKDBG__MAX; i++) {
+    for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
         QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
             if (rule->action == ACTION_SUSPEND &&
                 !strcmp(rule->options.suspend.tag, tag)) {
@@ -786,7 +701,7 @@ static int blkdebug_debug_remove_breakpoint(BlockDriverState *bs,
     }
     QLIST_FOREACH_SAFE(r, &s->suspended_reqs, next, r_next) {
         if (!strcmp(r->tag, tag)) {
-            qemu_coroutine_enter(r->co);
+            qemu_coroutine_enter(r->co, NULL);
             ret = 0;
         }
     }
@@ -811,21 +726,22 @@ static int64_t blkdebug_getlength(BlockDriverState *bs)
     return bdrv_getlength(bs->file->bs);
 }
 
-static int blkdebug_truncate(BlockDriverState *bs, int64_t offset, Error **errp)
+static int blkdebug_truncate(BlockDriverState *bs, int64_t offset)
 {
-    return bdrv_truncate(bs->file, offset, errp);
+    return bdrv_truncate(bs->file->bs, offset);
 }
 
-static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
+static void blkdebug_refresh_filename(BlockDriverState *bs)
 {
-    BDRVBlkdebugState *s = bs->opaque;
     QDict *opts;
     const QDictEntry *e;
     bool force_json = false;
 
-    for (e = qdict_first(options); e; e = qdict_next(options, e)) {
+    for (e = qdict_first(bs->options); e; e = qdict_next(bs->options, e)) {
         if (strcmp(qdict_entry_key(e), "config") &&
-            strcmp(qdict_entry_key(e), "x-image"))
+            strcmp(qdict_entry_key(e), "x-image") &&
+            strcmp(qdict_entry_key(e), "image") &&
+            strncmp(qdict_entry_key(e), "image.", strlen("image.")))
         {
             force_json = true;
             break;
@@ -840,18 +756,22 @@ static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
 
     if (!force_json && bs->file->bs->exact_filename[0]) {
         snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "blkdebug:%s:%s", s->config_file ?: "",
+                 "blkdebug:%s:%s",
+                 qdict_get_try_str(bs->options, "config") ?: "",
                  bs->file->bs->exact_filename);
     }
 
     opts = qdict_new();
-    qdict_put_str(opts, "driver", "blkdebug");
+    qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("blkdebug")));
 
     QINCREF(bs->file->bs->full_open_options);
-    qdict_put(opts, "image", bs->file->bs->full_open_options);
+    qdict_put_obj(opts, "image", QOBJECT(bs->file->bs->full_open_options));
 
-    for (e = qdict_first(options); e; e = qdict_next(options, e)) {
-        if (strcmp(qdict_entry_key(e), "x-image")) {
+    for (e = qdict_first(bs->options); e; e = qdict_next(bs->options, e)) {
+        if (strcmp(qdict_entry_key(e), "x-image") &&
+            strcmp(qdict_entry_key(e), "image") &&
+            strncmp(qdict_entry_key(e), "image.", strlen("image.")))
+        {
             qobject_incref(qdict_entry_value(e));
             qdict_put_obj(opts, qdict_entry_key(e), qdict_entry_value(e));
         }
@@ -860,36 +780,6 @@ static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
     bs->full_open_options = opts;
 }
 
-static void blkdebug_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    BDRVBlkdebugState *s = bs->opaque;
-
-    if (s->align) {
-        bs->bl.request_alignment = s->align;
-    }
-    if (s->max_transfer) {
-        bs->bl.max_transfer = s->max_transfer;
-    }
-    if (s->opt_write_zero) {
-        bs->bl.pwrite_zeroes_alignment = s->opt_write_zero;
-    }
-    if (s->max_write_zero) {
-        bs->bl.max_pwrite_zeroes = s->max_write_zero;
-    }
-    if (s->opt_discard) {
-        bs->bl.pdiscard_alignment = s->opt_discard;
-    }
-    if (s->max_discard) {
-        bs->bl.max_pdiscard = s->max_discard;
-    }
-}
-
-static int blkdebug_reopen_prepare(BDRVReopenState *reopen_state,
-                                   BlockReopenQueue *queue, Error **errp)
-{
-    return 0;
-}
-
 static BlockDriver bdrv_blkdebug = {
     .format_name            = "blkdebug",
     .protocol_name          = "blkdebug",
@@ -898,19 +788,13 @@ static BlockDriver bdrv_blkdebug = {
     .bdrv_parse_filename    = blkdebug_parse_filename,
     .bdrv_file_open         = blkdebug_open,
     .bdrv_close             = blkdebug_close,
-    .bdrv_reopen_prepare    = blkdebug_reopen_prepare,
-    .bdrv_child_perm        = bdrv_filter_default_perms,
-
     .bdrv_getlength         = blkdebug_getlength,
     .bdrv_truncate          = blkdebug_truncate,
     .bdrv_refresh_filename  = blkdebug_refresh_filename,
-    .bdrv_refresh_limits    = blkdebug_refresh_limits,
 
-    .bdrv_co_preadv         = blkdebug_co_preadv,
-    .bdrv_co_pwritev        = blkdebug_co_pwritev,
-    .bdrv_co_flush_to_disk  = blkdebug_co_flush,
-    .bdrv_co_pwrite_zeroes  = blkdebug_co_pwrite_zeroes,
-    .bdrv_co_pdiscard       = blkdebug_co_pdiscard,
+    .bdrv_aio_readv         = blkdebug_aio_readv,
+    .bdrv_aio_writev        = blkdebug_aio_writev,
+    .bdrv_aio_flush         = blkdebug_aio_flush,
 
     .bdrv_debug_event           = blkdebug_debug_event,
     .bdrv_debug_breakpoint      = blkdebug_debug_breakpoint,

block/blkreplay.c

@@ -1,153 +0,0 @@
-/*
- * Block protocol for record/replay
- *
- * Copyright (c) 2010-2016 Institute for System Programming
- *                         of the Russian Academy of Sciences.
- *
- * 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/osdep.h"
-#include "qemu-common.h"
-#include "block/block_int.h"
-#include "sysemu/replay.h"
-#include "qapi/error.h"
-
-typedef struct Request {
-    Coroutine *co;
-    QEMUBH *bh;
-} Request;
-
-static int blkreplay_open(BlockDriverState *bs, QDict *options, int flags,
-                          Error **errp)
-{
-    Error *local_err = NULL;
-    int ret;
-
-    /* Open the image file */
-    bs->file = bdrv_open_child(NULL, options, "image",
-                               bs, &child_file, false, &local_err);
-    if (local_err) {
-        ret = -EINVAL;
-        error_propagate(errp, local_err);
-        goto fail;
-    }
-
-    ret = 0;
-fail:
-    return ret;
-}
-
-static void blkreplay_close(BlockDriverState *bs)
-{
-}
-
-static int64_t blkreplay_getlength(BlockDriverState *bs)
-{
-    return bdrv_getlength(bs->file->bs);
-}
-
-/* This bh is used for synchronization of return from coroutines.
-   It continues yielded coroutine which then finishes its execution.
-   BH is called adjusted to some replay checkpoint, therefore
-   record and replay will always finish coroutines deterministically.
-*/
-static void blkreplay_bh_cb(void *opaque)
-{
-    Request *req = opaque;
-    aio_co_wake(req->co);
-    qemu_bh_delete(req->bh);
-    g_free(req);
-}
-
-static void block_request_create(uint64_t reqid, BlockDriverState *bs,
-                                 Coroutine *co)
-{
-    Request *req = g_new(Request, 1);
-    *req = (Request) {
-        .co = co,
-        .bh = aio_bh_new(bdrv_get_aio_context(bs), blkreplay_bh_cb, req),
-    };
-    replay_block_event(req->bh, reqid);
-}
-
-static int coroutine_fn blkreplay_co_preadv(BlockDriverState *bs,
-    uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
-{
-    uint64_t reqid = blkreplay_next_id();
-    int ret = bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
-    block_request_create(reqid, bs, qemu_coroutine_self());
-    qemu_coroutine_yield();
-
-    return ret;
-}
-
-static int coroutine_fn blkreplay_co_pwritev(BlockDriverState *bs,
-    uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
-{
-    uint64_t reqid = blkreplay_next_id();
-    int ret = bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
-    block_request_create(reqid, bs, qemu_coroutine_self());
-    qemu_coroutine_yield();
-
-    return ret;
-}
-
-static int coroutine_fn blkreplay_co_pwrite_zeroes(BlockDriverState *bs,
-    int64_t offset, int count, BdrvRequestFlags flags)
-{
-    uint64_t reqid = blkreplay_next_id();
-    int ret = bdrv_co_pwrite_zeroes(bs->file, offset, count, flags);
-    block_request_create(reqid, bs, qemu_coroutine_self());
-    qemu_coroutine_yield();
-
-    return ret;
-}
-
-static int coroutine_fn blkreplay_co_pdiscard(BlockDriverState *bs,
-                                              int64_t offset, int count)
-{
-    uint64_t reqid = blkreplay_next_id();
-    int ret = bdrv_co_pdiscard(bs->file->bs, offset, count);
-    block_request_create(reqid, bs, qemu_coroutine_self());
-    qemu_coroutine_yield();
-
-    return ret;
-}
-
-static int coroutine_fn blkreplay_co_flush(BlockDriverState *bs)
-{
-    uint64_t reqid = blkreplay_next_id();
-    int ret = bdrv_co_flush(bs->file->bs);
-    block_request_create(reqid, bs, qemu_coroutine_self());
-    qemu_coroutine_yield();
-
-    return ret;
-}
-
-static BlockDriver bdrv_blkreplay = {
-    .format_name            = "blkreplay",
-    .protocol_name          = "blkreplay",
-    .instance_size          = 0,
-
-    .bdrv_file_open         = blkreplay_open,
-    .bdrv_close             = blkreplay_close,
-    .bdrv_child_perm        = bdrv_filter_default_perms,
-    .bdrv_getlength         = blkreplay_getlength,
-
-    .bdrv_co_preadv         = blkreplay_co_preadv,
-    .bdrv_co_pwritev        = blkreplay_co_pwritev,
-
-    .bdrv_co_pwrite_zeroes  = blkreplay_co_pwrite_zeroes,
-    .bdrv_co_pdiscard       = blkreplay_co_pdiscard,
-    .bdrv_co_flush          = blkreplay_co_flush,
-};
-
-static void bdrv_blkreplay_init(void)
-{
-    bdrv_register(&bdrv_blkreplay);
-}
-
-block_init(bdrv_blkreplay_init);

block/blkverify.c

@@ -7,48 +7,49 @@
  * See the COPYING file in the top-level directory.
  */
 
-#include "qemu/osdep.h"
-#include "qapi/error.h"
+#include <stdarg.h>
 #include "qemu/sockets.h" /* for EINPROGRESS on Windows */
 #include "block/block_int.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qstring.h"
-#include "qemu/cutils.h"
 
 typedef struct {
     BdrvChild *test_file;
 } BDRVBlkverifyState;
 
-typedef struct BlkverifyRequest {
-    Coroutine *co;
-    BlockDriverState *bs;
+typedef struct BlkverifyAIOCB BlkverifyAIOCB;
+struct BlkverifyAIOCB {
+    BlockAIOCB common;
+    QEMUBH *bh;
 
     /* Request metadata */
     bool is_write;
-    uint64_t offset;
-    uint64_t bytes;
-    int flags;
-
-    int (*request_fn)(BdrvChild *, int64_t, unsigned int, QEMUIOVector *,
-                      BdrvRequestFlags);
-
-    int ret;                    /* test image result */
-    int raw_ret;                /* raw image result */
+    int64_t sector_num;
+    int nb_sectors;
 
+    int ret;                    /* first completed request's result */
     unsigned int done;          /* completion counter */
 
     QEMUIOVector *qiov;         /* user I/O vector */
-    QEMUIOVector *raw_qiov;     /* cloned I/O vector for raw file */
-} BlkverifyRequest;
+    QEMUIOVector raw_qiov;      /* cloned I/O vector for raw file */
+    void *buf;                  /* buffer for raw file I/O */
 
-static void GCC_FMT_ATTR(2, 3) blkverify_err(BlkverifyRequest *r,
+    void (*verify)(BlkverifyAIOCB *acb);
+};
+
+static const AIOCBInfo blkverify_aiocb_info = {
+    .aiocb_size         = sizeof(BlkverifyAIOCB),
+};
+
+static void GCC_FMT_ATTR(2, 3) blkverify_err(BlkverifyAIOCB *acb,
                                              const char *fmt, ...)
 {
     va_list ap;
 
     va_start(ap, fmt);
-    fprintf(stderr, "blkverify: %s offset=%" PRId64 " bytes=%" PRId64 " ",
-            r->is_write ? "write" : "read", r->offset, r->bytes);
+    fprintf(stderr, "blkverify: %s sector_num=%" PRId64 " nb_sectors=%d ",
+            acb->is_write ? "write" : "read", acb->sector_num,
+            acb->nb_sectors);
     vfprintf(stderr, fmt, ap);
     fprintf(stderr, "\n");
     va_end(ap);
@@ -67,7 +68,7 @@ static void blkverify_parse_filename(const char *filename, QDict *options,
     if (!strstart(filename, "blkverify:", &filename)) {
         /* There was no prefix; therefore, all options have to be already
            present in the QDict (except for the filename) */
-        qdict_put_str(options, "x-image", filename);
+        qdict_put(options, "x-image", qstring_from_str(filename));
         return;
     }
 
@@ -84,7 +85,7 @@ static void blkverify_parse_filename(const char *filename, QDict *options,
 
     /* TODO Allow multi-level nesting and set file.filename here */
     filename = c + 1;
-    qdict_put_str(options, "x-image", filename);
+    qdict_put(options, "x-image", qstring_from_str(filename));
 }
 
 static QemuOptsList runtime_opts = {
@@ -142,6 +143,9 @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
 
     ret = 0;
 fail:
+    if (ret < 0) {
+        bdrv_unref_child(bs, bs->file);
+    }
     qemu_opts_del(opts);
     return ret;
 }
@@ -161,106 +165,116 @@ static int64_t blkverify_getlength(BlockDriverState *bs)
     return bdrv_getlength(s->test_file->bs);
 }
 
-static void coroutine_fn blkverify_do_test_req(void *opaque)
+static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
+                                         int64_t sector_num, QEMUIOVector *qiov,
+                                         int nb_sectors,
+                                         BlockCompletionFunc *cb,
+                                         void *opaque)
 {
-    BlkverifyRequest *r = opaque;
-    BDRVBlkverifyState *s = r->bs->opaque;
+    BlkverifyAIOCB *acb = qemu_aio_get(&blkverify_aiocb_info, bs, cb, opaque);
 
-    r->ret = r->request_fn(s->test_file, r->offset, r->bytes, r->qiov,
-                           r->flags);
-    r->done++;
-    qemu_coroutine_enter_if_inactive(r->co);
+    acb->bh = NULL;
+    acb->is_write = is_write;
+    acb->sector_num = sector_num;
+    acb->nb_sectors = nb_sectors;
+    acb->ret = -EINPROGRESS;
+    acb->done = 0;
+    acb->qiov = qiov;
+    acb->buf = NULL;
+    acb->verify = NULL;
+    return acb;
 }
 
-static void coroutine_fn blkverify_do_raw_req(void *opaque)
+static void blkverify_aio_bh(void *opaque)
 {
-    BlkverifyRequest *r = opaque;
+    BlkverifyAIOCB *acb = opaque;
 
-    r->raw_ret = r->request_fn(r->bs->file, r->offset, r->bytes, r->raw_qiov,
-                               r->flags);
-    r->done++;
-    qemu_coroutine_enter_if_inactive(r->co);
-}
-
-static int coroutine_fn
-blkverify_co_prwv(BlockDriverState *bs, BlkverifyRequest *r, uint64_t offset,
-                  uint64_t bytes, QEMUIOVector *qiov, QEMUIOVector *raw_qiov,
-                  int flags, bool is_write)
-{
-    Coroutine *co_a, *co_b;
-
-    *r = (BlkverifyRequest) {
-        .co         = qemu_coroutine_self(),
-        .bs         = bs,
-        .offset     = offset,
-        .bytes      = bytes,
-        .qiov       = qiov,
-        .raw_qiov   = raw_qiov,
-        .flags      = flags,
-        .is_write   = is_write,
-        .request_fn = is_write ? bdrv_co_pwritev : bdrv_co_preadv,
-    };
-
-    co_a = qemu_coroutine_create(blkverify_do_test_req, r);
-    co_b = qemu_coroutine_create(blkverify_do_raw_req, r);
-
-    qemu_coroutine_enter(co_a);
-    qemu_coroutine_enter(co_b);
-
-    while (r->done < 2) {
-        qemu_coroutine_yield();
+    qemu_bh_delete(acb->bh);
+    if (acb->buf) {
+        qemu_iovec_destroy(&acb->raw_qiov);
+        qemu_vfree(acb->buf);
     }
-
-    if (r->ret != r->raw_ret) {
-        blkverify_err(r, "return value mismatch %d != %d", r->ret, r->raw_ret);
-    }
-
-    return r->ret;
+    acb->common.cb(acb->common.opaque, acb->ret);
+    qemu_aio_unref(acb);
 }
 
-static int coroutine_fn
-blkverify_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
-                    QEMUIOVector *qiov, int flags)
+static void blkverify_aio_cb(void *opaque, int ret)
 {
-    BlkverifyRequest r;
-    QEMUIOVector raw_qiov;
-    void *buf;
-    ssize_t cmp_offset;
-    int ret;
+    BlkverifyAIOCB *acb = opaque;
 
-    buf = qemu_blockalign(bs->file->bs, qiov->size);
-    qemu_iovec_init(&raw_qiov, qiov->niov);
-    qemu_iovec_clone(&raw_qiov, qiov, buf);
+    switch (++acb->done) {
+    case 1:
+        acb->ret = ret;
+        break;
 
-    ret = blkverify_co_prwv(bs, &r, offset, bytes, qiov, &raw_qiov, flags,
-                            false);
+    case 2:
+        if (acb->ret != ret) {
+            blkverify_err(acb, "return value mismatch %d != %d", acb->ret, ret);
+        }
 
-    cmp_offset = qemu_iovec_compare(qiov, &raw_qiov);
-    if (cmp_offset != -1) {
-        blkverify_err(&r, "contents mismatch at offset %" PRId64,
-                      offset + cmp_offset);
+        if (acb->verify) {
+            acb->verify(acb);
+        }
+
+        acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
+                             blkverify_aio_bh, acb);
+        qemu_bh_schedule(acb->bh);
+        break;
     }
-
-    qemu_iovec_destroy(&raw_qiov);
-    qemu_vfree(buf);
-
-    return ret;
 }
 
-static int coroutine_fn
-blkverify_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
-                     QEMUIOVector *qiov, int flags)
+static void blkverify_verify_readv(BlkverifyAIOCB *acb)
 {
-    BlkverifyRequest r;
-    return blkverify_co_prwv(bs, &r, offset, bytes, qiov, qiov, flags, true);
+    ssize_t offset = qemu_iovec_compare(acb->qiov, &acb->raw_qiov);
+    if (offset != -1) {
+        blkverify_err(acb, "contents mismatch in sector %" PRId64,
+                      acb->sector_num + (int64_t)(offset / BDRV_SECTOR_SIZE));
+    }
 }
 
-static int blkverify_co_flush(BlockDriverState *bs)
+static BlockAIOCB *blkverify_aio_readv(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockCompletionFunc *cb, void *opaque)
+{
+    BDRVBlkverifyState *s = bs->opaque;
+    BlkverifyAIOCB *acb = blkverify_aio_get(bs, false, sector_num, qiov,
+                                            nb_sectors, cb, opaque);
+
+    acb->verify = blkverify_verify_readv;
+    acb->buf = qemu_blockalign(bs->file->bs, qiov->size);
+    qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov);
+    qemu_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
+
+    bdrv_aio_readv(s->test_file->bs, sector_num, qiov, nb_sectors,
+                   blkverify_aio_cb, acb);
+    bdrv_aio_readv(bs->file->bs, sector_num, &acb->raw_qiov, nb_sectors,
+                   blkverify_aio_cb, acb);
+    return &acb->common;
+}
+
+static BlockAIOCB *blkverify_aio_writev(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockCompletionFunc *cb, void *opaque)
+{
+    BDRVBlkverifyState *s = bs->opaque;
+    BlkverifyAIOCB *acb = blkverify_aio_get(bs, true, sector_num, qiov,
+                                            nb_sectors, cb, opaque);
+
+    bdrv_aio_writev(s->test_file->bs, sector_num, qiov, nb_sectors,
+                    blkverify_aio_cb, acb);
+    bdrv_aio_writev(bs->file->bs, sector_num, qiov, nb_sectors,
+                    blkverify_aio_cb, acb);
+    return &acb->common;
+}
+
+static BlockAIOCB *blkverify_aio_flush(BlockDriverState *bs,
+                                       BlockCompletionFunc *cb,
+                                       void *opaque)
 {
     BDRVBlkverifyState *s = bs->opaque;
 
     /* Only flush test file, the raw file is not important */
-    return bdrv_co_flush(s->test_file->bs);
+    return bdrv_aio_flush(s->test_file->bs, cb, opaque);
 }
 
 static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs,
@@ -277,7 +291,23 @@ static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs,
     return bdrv_recurse_is_first_non_filter(s->test_file->bs, candidate);
 }
 
-static void blkverify_refresh_filename(BlockDriverState *bs, QDict *options)
+/* Propagate AioContext changes to ->test_file */
+static void blkverify_detach_aio_context(BlockDriverState *bs)
+{
+    BDRVBlkverifyState *s = bs->opaque;
+
+    bdrv_detach_aio_context(s->test_file->bs);
+}
+
+static void blkverify_attach_aio_context(BlockDriverState *bs,
+                                         AioContext *new_context)
+{
+    BDRVBlkverifyState *s = bs->opaque;
+
+    bdrv_attach_aio_context(s->test_file->bs, new_context);
+}
+
+static void blkverify_refresh_filename(BlockDriverState *bs)
 {
     BDRVBlkverifyState *s = bs->opaque;
 
@@ -288,12 +318,13 @@ static void blkverify_refresh_filename(BlockDriverState *bs, QDict *options)
         && s->test_file->bs->full_open_options)
     {
         QDict *opts = qdict_new();
-        qdict_put_str(opts, "driver", "blkverify");
+        qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("blkverify")));
 
         QINCREF(bs->file->bs->full_open_options);
-        qdict_put(opts, "raw", bs->file->bs->full_open_options);
+        qdict_put_obj(opts, "raw", QOBJECT(bs->file->bs->full_open_options));
         QINCREF(s->test_file->bs->full_open_options);
-        qdict_put(opts, "test", s->test_file->bs->full_open_options);
+        qdict_put_obj(opts, "test",
+                      QOBJECT(s->test_file->bs->full_open_options));
 
         bs->full_open_options = opts;
     }
@@ -316,13 +347,15 @@ static BlockDriver bdrv_blkverify = {
     .bdrv_parse_filename              = blkverify_parse_filename,
     .bdrv_file_open                   = blkverify_open,
     .bdrv_close                       = blkverify_close,
-    .bdrv_child_perm                  = bdrv_filter_default_perms,
     .bdrv_getlength                   = blkverify_getlength,
     .bdrv_refresh_filename            = blkverify_refresh_filename,
 
-    .bdrv_co_preadv                   = blkverify_co_preadv,
-    .bdrv_co_pwritev                  = blkverify_co_pwritev,
-    .bdrv_co_flush                    = blkverify_co_flush,
+    .bdrv_aio_readv                   = blkverify_aio_readv,
+    .bdrv_aio_writev                  = blkverify_aio_writev,
+    .bdrv_aio_flush                   = blkverify_aio_flush,
+
+    .bdrv_attach_aio_context          = blkverify_attach_aio_context,
+    .bdrv_detach_aio_context          = blkverify_detach_aio_context,
 
     .is_filter                        = true,
     .bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter,

block/bochs.c

@@ -22,12 +22,9 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
-#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "qemu/module.h"
-#include "qemu/bswap.h"
 
 /**************************************************************/
 
@@ -104,18 +101,9 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
     struct bochs_header bochs;
     int ret;
 
-    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
-                               false, errp);
-    if (!bs->file) {
-        return -EINVAL;
-    }
+    bs->read_only = 1; // no write support yet
 
-    ret = bdrv_set_read_only(bs, true, errp); /* no write support yet */
-    if (ret < 0) {
-        return ret;
-    }
-
-    ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));
+    ret = bdrv_pread(bs->file->bs, 0, &bochs, sizeof(bochs));
     if (ret < 0) {
         return ret;
     }
@@ -149,7 +137,7 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
         return -ENOMEM;
     }
 
-    ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
+    ret = bdrv_pread(bs->file->bs, le32_to_cpu(bochs.header), s->catalog_bitmap,
                      s->catalog_size * 4);
     if (ret < 0) {
         goto fail;
@@ -197,11 +185,6 @@ fail:
     return ret;
 }
 
-static void bochs_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    bs->bl.request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O */
-}
-
 static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
 {
     BDRVBochsState *s = bs->opaque;
@@ -223,7 +206,7 @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
         (s->extent_blocks + s->bitmap_blocks));
 
     /* read in bitmap for current extent */
-    ret = bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),
+    ret = bdrv_pread(bs->file->bs, bitmap_offset + (extent_offset / 8),
                      &bitmap_entry, 1);
     if (ret < 0) {
         return ret;
@@ -236,52 +219,38 @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
     return bitmap_offset + (512 * (s->bitmap_blocks + extent_offset));
 }
 
-static int coroutine_fn
-bochs_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
-                QEMUIOVector *qiov, int flags)
+static int bochs_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
 {
-    BDRVBochsState *s = bs->opaque;
-    uint64_t sector_num = offset >> BDRV_SECTOR_BITS;
-    int nb_sectors = bytes >> BDRV_SECTOR_BITS;
-    uint64_t bytes_done = 0;
-    QEMUIOVector local_qiov;
     int ret;
 
-    assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
-    assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
-
-    qemu_iovec_init(&local_qiov, qiov->niov);
-    qemu_co_mutex_lock(&s->lock);
-
     while (nb_sectors > 0) {
         int64_t block_offset = seek_to_sector(bs, sector_num);
         if (block_offset < 0) {
-            ret = block_offset;
-            goto fail;
-        }
-
-        qemu_iovec_reset(&local_qiov);
-        qemu_iovec_concat(&local_qiov, qiov, bytes_done, 512);
-
-        if (block_offset > 0) {
-            ret = bdrv_co_preadv(bs->file, block_offset, 512,
-                                 &local_qiov, 0);
+            return block_offset;
+        } else if (block_offset > 0) {
+            ret = bdrv_pread(bs->file->bs, block_offset, buf, 512);
             if (ret < 0) {
-                goto fail;
+                return ret;
             }
         } else {
-            qemu_iovec_memset(&local_qiov, 0, 0, 512);
+            memset(buf, 0, 512);
         }
         nb_sectors--;
         sector_num++;
-        bytes_done += 512;
+        buf += 512;
     }
+    return 0;
+}
 
-    ret = 0;
-fail:
+static coroutine_fn int bochs_co_read(BlockDriverState *bs, int64_t sector_num,
+                                      uint8_t *buf, int nb_sectors)
+{
+    int ret;
+    BDRVBochsState *s = bs->opaque;
+    qemu_co_mutex_lock(&s->lock);
+    ret = bochs_read(bs, sector_num, buf, nb_sectors);
     qemu_co_mutex_unlock(&s->lock);
-    qemu_iovec_destroy(&local_qiov);
-
     return ret;
 }
 
@@ -296,9 +265,7 @@ static BlockDriver bdrv_bochs = {
     .instance_size	= sizeof(BDRVBochsState),
     .bdrv_probe		= bochs_probe,
     .bdrv_open		= bochs_open,
-    .bdrv_child_perm     = bdrv_format_default_perms,
-    .bdrv_refresh_limits = bochs_refresh_limits,
-    .bdrv_co_preadv = bochs_co_preadv,
+    .bdrv_read          = bochs_co_read,
     .bdrv_close		= bochs_close,
 };
 

block/cloop.c

@@ -21,12 +21,9 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
-#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "qemu/module.h"
-#include "qemu/bswap.h"
 #include <zlib.h>
 
 /* Maximum compressed block size */
@@ -66,19 +63,10 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
     uint32_t offsets_size, max_compressed_block_size = 1, i;
     int ret;
 
-    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
-                               false, errp);
-    if (!bs->file) {
-        return -EINVAL;
-    }
-
-    ret = bdrv_set_read_only(bs, true, errp);
-    if (ret < 0) {
-        return ret;
-    }
+    bs->read_only = 1;
 
     /* read header */
-    ret = bdrv_pread(bs->file, 128, &s->block_size, 4);
+    ret = bdrv_pread(bs->file->bs, 128, &s->block_size, 4);
     if (ret < 0) {
         return ret;
     }
@@ -104,7 +92,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         return -EINVAL;
     }
 
-    ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4);
+    ret = bdrv_pread(bs->file->bs, 128 + 4, &s->n_blocks, 4);
     if (ret < 0) {
         return ret;
     }
@@ -135,7 +123,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         return -ENOMEM;
     }
 
-    ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size);
+    ret = bdrv_pread(bs->file->bs, 128 + 4 + 4, s->offsets, offsets_size);
     if (ret < 0) {
         goto fail;
     }
@@ -207,11 +195,6 @@ fail:
     return ret;
 }
 
-static void cloop_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    bs->bl.request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O */
-}
-
 static inline int cloop_read_block(BlockDriverState *bs, int block_num)
 {
     BDRVCloopState *s = bs->opaque;
@@ -220,7 +203,7 @@ static inline int cloop_read_block(BlockDriverState *bs, int block_num)
         int ret;
         uint32_t bytes = s->offsets[block_num + 1] - s->offsets[block_num];
 
-        ret = bdrv_pread(bs->file, s->offsets[block_num],
+        ret = bdrv_pread(bs->file->bs, s->offsets[block_num],
                          s->compressed_block, bytes);
         if (ret != bytes) {
             return -1;
@@ -244,38 +227,33 @@ static inline int cloop_read_block(BlockDriverState *bs, int block_num)
     return 0;
 }
 
-static int coroutine_fn
-cloop_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
-                QEMUIOVector *qiov, int flags)
+static int cloop_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
 {
     BDRVCloopState *s = bs->opaque;
-    uint64_t sector_num = offset >> BDRV_SECTOR_BITS;
-    int nb_sectors = bytes >> BDRV_SECTOR_BITS;
-    int ret, i;
-
-    assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
-    assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
-
-    qemu_co_mutex_lock(&s->lock);
+    int i;
 
     for (i = 0; i < nb_sectors; i++) {
-        void *data;
         uint32_t sector_offset_in_block =
             ((sector_num + i) % s->sectors_per_block),
             block_num = (sector_num + i) / s->sectors_per_block;
         if (cloop_read_block(bs, block_num) != 0) {
-            ret = -EIO;
-            goto fail;
+            return -1;
         }
-
-        data = s->uncompressed_block + sector_offset_in_block * 512;
-        qemu_iovec_from_buf(qiov, i * 512, data, 512);
+        memcpy(buf + i * 512,
+            s->uncompressed_block + sector_offset_in_block * 512, 512);
     }
+    return 0;
+}
 
-    ret = 0;
-fail:
+static coroutine_fn int cloop_co_read(BlockDriverState *bs, int64_t sector_num,
+                                      uint8_t *buf, int nb_sectors)
+{
+    int ret;
+    BDRVCloopState *s = bs->opaque;
+    qemu_co_mutex_lock(&s->lock);
+    ret = cloop_read(bs, sector_num, buf, nb_sectors);
     qemu_co_mutex_unlock(&s->lock);
-
     return ret;
 }
 
@@ -293,9 +271,7 @@ static BlockDriver bdrv_cloop = {
     .instance_size  = sizeof(BDRVCloopState),
     .bdrv_probe     = cloop_probe,
     .bdrv_open      = cloop_open,
-    .bdrv_child_perm     = bdrv_format_default_perms,
-    .bdrv_refresh_limits = cloop_refresh_limits,
-    .bdrv_co_preadv = cloop_co_preadv,
+    .bdrv_read      = cloop_co_read,
     .bdrv_close     = cloop_close,
 };
 

block/commit.c

@@ -12,12 +12,9 @@
  *
  */
 
-#include "qemu/osdep.h"
-#include "qemu/cutils.h"
 #include "trace.h"
 #include "block/block_int.h"
-#include "block/blockjob_int.h"
-#include "qapi/error.h"
+#include "block/blockjob.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
 #include "sysemu/block-backend.h"
@@ -37,37 +34,28 @@ typedef struct CommitBlockJob {
     BlockJob common;
     RateLimit limit;
     BlockDriverState *active;
-    BlockDriverState *commit_top_bs;
-    BlockBackend *top;
-    BlockBackend *base;
+    BlockDriverState *top;
+    BlockDriverState *base;
     BlockdevOnError on_error;
     int base_flags;
     int orig_overlay_flags;
     char *backing_file_str;
 } CommitBlockJob;
 
-static int coroutine_fn commit_populate(BlockBackend *bs, BlockBackend *base,
+static int coroutine_fn commit_populate(BlockDriverState *bs,
+                                        BlockDriverState *base,
                                         int64_t sector_num, int nb_sectors,
                                         void *buf)
 {
     int ret = 0;
-    QEMUIOVector qiov;
-    struct iovec iov = {
-        .iov_base = buf,
-        .iov_len = nb_sectors * BDRV_SECTOR_SIZE,
-    };
 
-    qemu_iovec_init_external(&qiov, &iov, 1);
-
-    ret = blk_co_preadv(bs, sector_num * BDRV_SECTOR_SIZE,
-                        qiov.size, &qiov, 0);
-    if (ret < 0) {
+    ret = bdrv_read(bs, sector_num, buf, nb_sectors);
+    if (ret) {
         return ret;
     }
 
-    ret = blk_co_pwritev(base, sector_num * BDRV_SECTOR_SIZE,
-                         qiov.size, &qiov, 0);
-    if (ret < 0) {
+    ret = bdrv_write(base, sector_num, buf, nb_sectors);
+    if (ret) {
         return ret;
     }
 
@@ -83,29 +71,14 @@ static void commit_complete(BlockJob *job, void *opaque)
     CommitBlockJob *s = container_of(job, CommitBlockJob, common);
     CommitCompleteData *data = opaque;
     BlockDriverState *active = s->active;
-    BlockDriverState *top = blk_bs(s->top);
-    BlockDriverState *base = blk_bs(s->base);
-    BlockDriverState *overlay_bs = bdrv_find_overlay(active, s->commit_top_bs);
+    BlockDriverState *top = s->top;
+    BlockDriverState *base = s->base;
+    BlockDriverState *overlay_bs;
     int ret = data->ret;
-    bool remove_commit_top_bs = false;
-
-    /* Make sure overlay_bs and top stay around until bdrv_set_backing_hd() */
-    bdrv_ref(top);
-    bdrv_ref(overlay_bs);
-
-    /* Remove base node parent that still uses BLK_PERM_WRITE/RESIZE before
-     * the normal backing chain can be restored. */
-    blk_unref(s->base);
 
     if (!block_job_is_cancelled(&s->common) && ret == 0) {
         /* success */
-        ret = bdrv_drop_intermediate(active, s->commit_top_bs, base,
-                                     s->backing_file_str);
-    } else if (overlay_bs) {
-        /* XXX Can (or should) we somehow keep 'consistent read' blocked even
-         * after the failed/cancelled commit job is gone? If we already wrote
-         * something to base, the intermediate images aren't valid any more. */
-        remove_commit_top_bs = true;
+        ret = bdrv_drop_intermediate(active, top, base, s->backing_file_str);
     }
 
     /* restore base open flags here if appropriate (e.g., change the base back
@@ -114,62 +87,55 @@ static void commit_complete(BlockJob *job, void *opaque)
     if (s->base_flags != bdrv_get_flags(base)) {
         bdrv_reopen(base, s->base_flags, NULL);
     }
+    overlay_bs = bdrv_find_overlay(active, top);
     if (overlay_bs && s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
         bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
     }
     g_free(s->backing_file_str);
-    blk_unref(s->top);
     block_job_completed(&s->common, ret);
     g_free(data);
-
-    /* If bdrv_drop_intermediate() didn't already do that, remove the commit
-     * filter driver from the backing chain. Do this as the final step so that
-     * the 'consistent read' permission can be granted.  */
-    if (remove_commit_top_bs) {
-        bdrv_set_backing_hd(overlay_bs, top, &error_abort);
-    }
-
-    bdrv_unref(overlay_bs);
-    bdrv_unref(top);
 }
 
 static void coroutine_fn commit_run(void *opaque)
 {
     CommitBlockJob *s = opaque;
     CommitCompleteData *data;
+    BlockDriverState *top = s->top;
+    BlockDriverState *base = s->base;
     int64_t sector_num, end;
-    uint64_t delay_ns = 0;
     int ret = 0;
     int n = 0;
     void *buf = NULL;
     int bytes_written = 0;
     int64_t base_len;
 
-    ret = s->common.len = blk_getlength(s->top);
+    ret = s->common.len = bdrv_getlength(top);
 
 
     if (s->common.len < 0) {
         goto out;
     }
 
-    ret = base_len = blk_getlength(s->base);
+    ret = base_len = bdrv_getlength(base);
     if (base_len < 0) {
         goto out;
     }
 
     if (base_len < s->common.len) {
-        ret = blk_truncate(s->base, s->common.len, NULL);
+        ret = bdrv_truncate(base, s->common.len);
         if (ret) {
             goto out;
         }
     }
 
     end = s->common.len >> BDRV_SECTOR_BITS;
-    buf = blk_blockalign(s->top, COMMIT_BUFFER_SIZE);
+    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.
          */
@@ -178,20 +144,25 @@ static void coroutine_fn commit_run(void *opaque)
             break;
         }
         /* Copy if allocated above the base */
-        ret = bdrv_is_allocated_above(blk_bs(s->top), blk_bs(s->base),
-                                      sector_num,
+        ret = bdrv_is_allocated_above(top, base, sector_num,
                                       COMMIT_BUFFER_SIZE / BDRV_SECTOR_SIZE,
                                       &n);
         copy = (ret == 1);
         trace_commit_one_iteration(s, sector_num, n, ret);
         if (copy) {
-            ret = commit_populate(s->top, s->base, sector_num, n, buf);
+            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) {
-            BlockErrorAction action =
-                block_job_error_action(&s->common, false, s->on_error, -ret);
-            if (action == BLOCK_ERROR_ACTION_REPORT) {
+            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 out;
             } else {
                 n = 0;
@@ -200,10 +171,6 @@ static void coroutine_fn commit_run(void *opaque)
         }
         /* Publish progress */
         s->common.offset += n * BDRV_SECTOR_SIZE;
-
-        if (copy && s->common.speed) {
-            delay_ns = ratelimit_calculate_delay(&s->limit, n);
-        }
     }
 
     ret = 0;
@@ -231,70 +198,26 @@ static const BlockJobDriver commit_job_driver = {
     .instance_size = sizeof(CommitBlockJob),
     .job_type      = BLOCK_JOB_TYPE_COMMIT,
     .set_speed     = commit_set_speed,
-    .start         = commit_run,
 };
 
-static int coroutine_fn bdrv_commit_top_preadv(BlockDriverState *bs,
-    uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
-{
-    return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
-}
-
-static int64_t coroutine_fn bdrv_commit_top_get_block_status(
-    BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum,
-    BlockDriverState **file)
-{
-    *pnum = nb_sectors;
-    *file = bs->backing->bs;
-    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID | BDRV_BLOCK_DATA |
-           (sector_num << BDRV_SECTOR_BITS);
-}
-
-static void bdrv_commit_top_refresh_filename(BlockDriverState *bs, QDict *opts)
-{
-    bdrv_refresh_filename(bs->backing->bs);
-    pstrcpy(bs->exact_filename, sizeof(bs->exact_filename),
-            bs->backing->bs->filename);
-}
-
-static void bdrv_commit_top_close(BlockDriverState *bs)
-{
-}
-
-static void bdrv_commit_top_child_perm(BlockDriverState *bs, BdrvChild *c,
-                                       const BdrvChildRole *role,
-                                       uint64_t perm, uint64_t shared,
-                                       uint64_t *nperm, uint64_t *nshared)
-{
-    *nperm = 0;
-    *nshared = BLK_PERM_ALL;
-}
-
-/* Dummy node that provides consistent read to its users without requiring it
- * from its backing file and that allows writes on the backing file chain. */
-static BlockDriver bdrv_commit_top = {
-    .format_name                = "commit_top",
-    .bdrv_co_preadv             = bdrv_commit_top_preadv,
-    .bdrv_co_get_block_status   = bdrv_commit_top_get_block_status,
-    .bdrv_refresh_filename      = bdrv_commit_top_refresh_filename,
-    .bdrv_close                 = bdrv_commit_top_close,
-    .bdrv_child_perm            = bdrv_commit_top_child_perm,
-};
-
-void commit_start(const char *job_id, BlockDriverState *bs,
-                  BlockDriverState *base, BlockDriverState *top, int64_t speed,
-                  BlockdevOnError on_error, const char *backing_file_str,
-                  const char *filter_node_name, Error **errp)
+void commit_start(BlockDriverState *bs, BlockDriverState *base,
+                  BlockDriverState *top, int64_t speed,
+                  BlockdevOnError on_error, BlockCompletionFunc *cb,
+                  void *opaque, const char *backing_file_str, Error **errp)
 {
     CommitBlockJob *s;
     BlockReopenQueue *reopen_queue = NULL;
     int orig_overlay_flags;
     int orig_base_flags;
-    BlockDriverState *iter;
     BlockDriverState *overlay_bs;
-    BlockDriverState *commit_top_bs = NULL;
     Error *local_err = NULL;
-    int ret;
+
+    if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
+         on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
+        (!bs->blk || !blk_iostatus_is_enabled(bs->blk))) {
+        error_setg(errp, "Invalid parameter combination");
+        return;
+    }
 
     assert(top != bs);
     if (top == base) {
@@ -309,107 +232,34 @@ void commit_start(const char *job_id, BlockDriverState *bs,
         return;
     }
 
-    s = block_job_create(job_id, &commit_job_driver, bs, 0, BLK_PERM_ALL,
-                         speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp);
-    if (!s) {
-        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, NULL,
-                                         orig_base_flags | BDRV_O_RDWR);
-    }
     if (!(orig_overlay_flags & BDRV_O_RDWR)) {
         reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs, NULL,
                                          orig_overlay_flags | BDRV_O_RDWR);
     }
+    if (!(orig_base_flags & BDRV_O_RDWR)) {
+        reopen_queue = bdrv_reopen_queue(reopen_queue, base, NULL,
+                                         orig_base_flags | BDRV_O_RDWR);
+    }
     if (reopen_queue) {
-        bdrv_reopen_multiple(bdrv_get_aio_context(bs), reopen_queue, &local_err);
+        bdrv_reopen_multiple(reopen_queue, &local_err);
         if (local_err != NULL) {
             error_propagate(errp, local_err);
-            goto fail;
+            return;
         }
     }
 
-    /* Insert commit_top block node above top, so we can block consistent read
-     * on the backing chain below it */
-    commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, filter_node_name, 0,
-                                         errp);
-    if (commit_top_bs == NULL) {
-        goto fail;
-    }
-    commit_top_bs->total_sectors = top->total_sectors;
-    bdrv_set_aio_context(commit_top_bs, bdrv_get_aio_context(top));
 
-    bdrv_set_backing_hd(commit_top_bs, top, &local_err);
-    if (local_err) {
-        bdrv_unref(commit_top_bs);
-        commit_top_bs = NULL;
-        error_propagate(errp, local_err);
-        goto fail;
-    }
-    bdrv_set_backing_hd(overlay_bs, commit_top_bs, &local_err);
-    if (local_err) {
-        bdrv_unref(commit_top_bs);
-        commit_top_bs = NULL;
-        error_propagate(errp, local_err);
-        goto fail;
-    }
-
-    s->commit_top_bs = commit_top_bs;
-    bdrv_unref(commit_top_bs);
-
-    /* Block all nodes between top and base, because they will
-     * disappear from the chain after this operation. */
-    assert(bdrv_chain_contains(top, base));
-    for (iter = top; iter != base; iter = backing_bs(iter)) {
-        /* XXX BLK_PERM_WRITE needs to be allowed so we don't block ourselves
-         * at s->base (if writes are blocked for a node, they are also blocked
-         * for its backing file). The other options would be a second filter
-         * driver above s->base. */
-        ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
-                                 BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
-                                 errp);
-        if (ret < 0) {
-            goto fail;
-        }
-    }
-
-    ret = block_job_add_bdrv(&s->common, "base", base, 0, BLK_PERM_ALL, errp);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    /* overlay_bs must be blocked because it needs to be modified to
-     * update the backing image string. */
-    ret = block_job_add_bdrv(&s->common, "overlay of top", overlay_bs,
-                             BLK_PERM_GRAPH_MOD, BLK_PERM_ALL, errp);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    s->base = blk_new(BLK_PERM_CONSISTENT_READ
-                      | BLK_PERM_WRITE
-                      | BLK_PERM_RESIZE,
-                      BLK_PERM_CONSISTENT_READ
-                      | BLK_PERM_GRAPH_MOD
-                      | BLK_PERM_WRITE_UNCHANGED);
-    ret = blk_insert_bs(s->base, base, errp);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    /* Required permissions are already taken with block_job_add_bdrv() */
-    s->top = blk_new(0, BLK_PERM_ALL);
-    ret = blk_insert_bs(s->top, top, errp);
-    if (ret < 0) {
-        goto fail;
+    s = block_job_create(&commit_job_driver, bs, speed, cb, opaque, errp);
+    if (!s) {
+        return;
     }
 
+    s->base   = base;
+    s->top    = top;
     s->active = bs;
 
     s->base_flags          = orig_base_flags;
@@ -418,172 +268,8 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     s->backing_file_str = g_strdup(backing_file_str);
 
     s->on_error = on_error;
+    s->common.co = qemu_coroutine_create(commit_run);
 
-    trace_commit_start(bs, base, top, s);
-    block_job_start(&s->common);
-    return;
-
-fail:
-    if (s->base) {
-        blk_unref(s->base);
-    }
-    if (s->top) {
-        blk_unref(s->top);
-    }
-    if (commit_top_bs) {
-        bdrv_set_backing_hd(overlay_bs, top, &error_abort);
-    }
-    block_job_early_fail(&s->common);
-}
-
-
-#define COMMIT_BUF_SECTORS 2048
-
-/* commit COW file into the raw image */
-int bdrv_commit(BlockDriverState *bs)
-{
-    BlockBackend *src, *backing;
-    BlockDriverState *backing_file_bs = NULL;
-    BlockDriverState *commit_top_bs = NULL;
-    BlockDriver *drv = bs->drv;
-    int64_t sector, total_sectors, length, backing_length;
-    int n, ro, open_flags;
-    int ret = 0;
-    uint8_t *buf = NULL;
-    Error *local_err = NULL;
-
-    if (!drv)
-        return -ENOMEDIUM;
-
-    if (!bs->backing) {
-        return -ENOTSUP;
-    }
-
-    if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT_SOURCE, NULL) ||
-        bdrv_op_is_blocked(bs->backing->bs, BLOCK_OP_TYPE_COMMIT_TARGET, NULL)) {
-        return -EBUSY;
-    }
-
-    ro = bs->backing->bs->read_only;
-    open_flags =  bs->backing->bs->open_flags;
-
-    if (ro) {
-        if (bdrv_reopen(bs->backing->bs, open_flags | BDRV_O_RDWR, NULL)) {
-            return -EACCES;
-        }
-    }
-
-    src = blk_new(BLK_PERM_CONSISTENT_READ, BLK_PERM_ALL);
-    backing = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
-
-    ret = blk_insert_bs(src, bs, &local_err);
-    if (ret < 0) {
-        error_report_err(local_err);
-        goto ro_cleanup;
-    }
-
-    /* Insert commit_top block node above backing, so we can write to it */
-    backing_file_bs = backing_bs(bs);
-
-    commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, NULL, BDRV_O_RDWR,
-                                         &local_err);
-    if (commit_top_bs == NULL) {
-        error_report_err(local_err);
-        goto ro_cleanup;
-    }
-    bdrv_set_aio_context(commit_top_bs, bdrv_get_aio_context(backing_file_bs));
-
-    bdrv_set_backing_hd(commit_top_bs, backing_file_bs, &error_abort);
-    bdrv_set_backing_hd(bs, commit_top_bs, &error_abort);
-
-    ret = blk_insert_bs(backing, backing_file_bs, &local_err);
-    if (ret < 0) {
-        error_report_err(local_err);
-        goto ro_cleanup;
-    }
-
-    length = blk_getlength(src);
-    if (length < 0) {
-        ret = length;
-        goto ro_cleanup;
-    }
-
-    backing_length = blk_getlength(backing);
-    if (backing_length < 0) {
-        ret = backing_length;
-        goto ro_cleanup;
-    }
-
-    /* If our top snapshot is larger than the backing file image,
-     * grow the backing file image if possible.  If not possible,
-     * we must return an error */
-    if (length > backing_length) {
-        ret = blk_truncate(backing, length, &local_err);
-        if (ret < 0) {
-            error_report_err(local_err);
-            goto ro_cleanup;
-        }
-    }
-
-    total_sectors = length >> BDRV_SECTOR_BITS;
-
-    /* blk_try_blockalign() for src will choose an alignment that works for
-     * backing as well, so no need to compare the alignment manually. */
-    buf = blk_try_blockalign(src, COMMIT_BUF_SECTORS * BDRV_SECTOR_SIZE);
-    if (buf == NULL) {
-        ret = -ENOMEM;
-        goto ro_cleanup;
-    }
-
-    for (sector = 0; sector < total_sectors; sector += n) {
-        ret = bdrv_is_allocated(bs, sector, COMMIT_BUF_SECTORS, &n);
-        if (ret < 0) {
-            goto ro_cleanup;
-        }
-        if (ret) {
-            ret = blk_pread(src, sector * BDRV_SECTOR_SIZE, buf,
-                            n * BDRV_SECTOR_SIZE);
-            if (ret < 0) {
-                goto ro_cleanup;
-            }
-
-            ret = blk_pwrite(backing, sector * BDRV_SECTOR_SIZE, buf,
-                             n * BDRV_SECTOR_SIZE, 0);
-            if (ret < 0) {
-                goto ro_cleanup;
-            }
-        }
-    }
-
-    if (drv->bdrv_make_empty) {
-        ret = drv->bdrv_make_empty(bs);
-        if (ret < 0) {
-            goto ro_cleanup;
-        }
-        blk_flush(src);
-    }
-
-    /*
-     * Make sure all data we wrote to the backing device is actually
-     * stable on disk.
-     */
-    blk_flush(backing);
-
-    ret = 0;
-ro_cleanup:
-    qemu_vfree(buf);
-
-    blk_unref(backing);
-    if (backing_file_bs) {
-        bdrv_set_backing_hd(bs, backing_file_bs, &error_abort);
-    }
-    bdrv_unref(commit_top_bs);
-    blk_unref(src);
-
-    if (ro) {
-        /* ignoring error return here */
-        bdrv_reopen(bs->backing->bs, open_flags & ~BDRV_O_RDWR, NULL);
-    }
-
-    return ret;
+    trace_commit_start(bs, base, top, s, s->common.co, opaque);
+    qemu_coroutine_enter(s->common.co, s);
 }

block/crypto.c

@@ -1,649 +0,0 @@
-/*
- * QEMU block full disk encryption
- *
- * Copyright (c) 2015-2016 Red Hat, Inc.
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Lesser General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public
- * License along with this library; if not, see <http://www.gnu.org/licenses/>.
- *
- */
-
-#include "qemu/osdep.h"
-
-#include "block/block_int.h"
-#include "sysemu/block-backend.h"
-#include "crypto/block.h"
-#include "qapi/opts-visitor.h"
-#include "qapi-visit.h"
-#include "qapi/error.h"
-
-#define BLOCK_CRYPTO_OPT_LUKS_KEY_SECRET "key-secret"
-#define BLOCK_CRYPTO_OPT_LUKS_CIPHER_ALG "cipher-alg"
-#define BLOCK_CRYPTO_OPT_LUKS_CIPHER_MODE "cipher-mode"
-#define BLOCK_CRYPTO_OPT_LUKS_IVGEN_ALG "ivgen-alg"
-#define BLOCK_CRYPTO_OPT_LUKS_IVGEN_HASH_ALG "ivgen-hash-alg"
-#define BLOCK_CRYPTO_OPT_LUKS_HASH_ALG "hash-alg"
-#define BLOCK_CRYPTO_OPT_LUKS_ITER_TIME "iter-time"
-
-typedef struct BlockCrypto BlockCrypto;
-
-struct BlockCrypto {
-    QCryptoBlock *block;
-};
-
-
-static int block_crypto_probe_generic(QCryptoBlockFormat format,
-                                      const uint8_t *buf,
-                                      int buf_size,
-                                      const char *filename)
-{
-    if (qcrypto_block_has_format(format, buf, buf_size)) {
-        return 100;
-    } else {
-        return 0;
-    }
-}
-
-
-static ssize_t block_crypto_read_func(QCryptoBlock *block,
-                                      size_t offset,
-                                      uint8_t *buf,
-                                      size_t buflen,
-                                      void *opaque,
-                                      Error **errp)
-{
-    BlockDriverState *bs = opaque;
-    ssize_t ret;
-
-    ret = bdrv_pread(bs->file, offset, buf, buflen);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not read encryption header");
-        return ret;
-    }
-    return ret;
-}
-
-
-struct BlockCryptoCreateData {
-    const char *filename;
-    QemuOpts *opts;
-    BlockBackend *blk;
-    uint64_t size;
-};
-
-
-static ssize_t block_crypto_write_func(QCryptoBlock *block,
-                                       size_t offset,
-                                       const uint8_t *buf,
-                                       size_t buflen,
-                                       void *opaque,
-                                       Error **errp)
-{
-    struct BlockCryptoCreateData *data = opaque;
-    ssize_t ret;
-
-    ret = blk_pwrite(data->blk, offset, buf, buflen, 0);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not write encryption header");
-        return ret;
-    }
-    return ret;
-}
-
-
-static ssize_t block_crypto_init_func(QCryptoBlock *block,
-                                      size_t headerlen,
-                                      void *opaque,
-                                      Error **errp)
-{
-    struct BlockCryptoCreateData *data = opaque;
-    int ret;
-
-    /* User provided size should reflect amount of space made
-     * available to the guest, so we must take account of that
-     * which will be used by the crypto header
-     */
-    data->size += headerlen;
-
-    qemu_opt_set_number(data->opts, BLOCK_OPT_SIZE, data->size, &error_abort);
-    ret = bdrv_create_file(data->filename, data->opts, errp);
-    if (ret < 0) {
-        return -1;
-    }
-
-    data->blk = blk_new_open(data->filename, NULL, NULL,
-                             BDRV_O_RDWR | BDRV_O_PROTOCOL, errp);
-    if (!data->blk) {
-        return -1;
-    }
-
-    return 0;
-}
-
-
-static QemuOptsList block_crypto_runtime_opts_luks = {
-    .name = "crypto",
-    .head = QTAILQ_HEAD_INITIALIZER(block_crypto_runtime_opts_luks.head),
-    .desc = {
-        {
-            .name = BLOCK_CRYPTO_OPT_LUKS_KEY_SECRET,
-            .type = QEMU_OPT_STRING,
-            .help = "ID of the secret that provides the encryption key",
-        },
-        { /* end of list */ }
-    },
-};
-
-
-static QemuOptsList block_crypto_create_opts_luks = {
-    .name = "crypto",
-    .head = QTAILQ_HEAD_INITIALIZER(block_crypto_create_opts_luks.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size"
-        },
-        {
-            .name = BLOCK_CRYPTO_OPT_LUKS_KEY_SECRET,
-            .type = QEMU_OPT_STRING,
-            .help = "ID of the secret that provides the encryption key",
-        },
-        {
-            .name = BLOCK_CRYPTO_OPT_LUKS_CIPHER_ALG,
-            .type = QEMU_OPT_STRING,
-            .help = "Name of encryption cipher algorithm",
-        },
-        {
-            .name = BLOCK_CRYPTO_OPT_LUKS_CIPHER_MODE,
-            .type = QEMU_OPT_STRING,
-            .help = "Name of encryption cipher mode",
-        },
-        {
-            .name = BLOCK_CRYPTO_OPT_LUKS_IVGEN_ALG,
-            .type = QEMU_OPT_STRING,
-            .help = "Name of IV generator algorithm",
-        },
-        {
-            .name = BLOCK_CRYPTO_OPT_LUKS_IVGEN_HASH_ALG,
-            .type = QEMU_OPT_STRING,
-            .help = "Name of IV generator hash algorithm",
-        },
-        {
-            .name = BLOCK_CRYPTO_OPT_LUKS_HASH_ALG,
-            .type = QEMU_OPT_STRING,
-            .help = "Name of encryption hash algorithm",
-        },
-        {
-            .name = BLOCK_CRYPTO_OPT_LUKS_ITER_TIME,
-            .type = QEMU_OPT_NUMBER,
-            .help = "Time to spend in PBKDF in milliseconds",
-        },
-        { /* end of list */ }
-    },
-};
-
-
-static QCryptoBlockOpenOptions *
-block_crypto_open_opts_init(QCryptoBlockFormat format,
-                            QemuOpts *opts,
-                            Error **errp)
-{
-    Visitor *v;
-    QCryptoBlockOpenOptions *ret = NULL;
-    Error *local_err = NULL;
-
-    ret = g_new0(QCryptoBlockOpenOptions, 1);
-    ret->format = format;
-
-    v = opts_visitor_new(opts);
-
-    visit_start_struct(v, NULL, NULL, 0, &local_err);
-    if (local_err) {
-        goto out;
-    }
-
-    switch (format) {
-    case Q_CRYPTO_BLOCK_FORMAT_LUKS:
-        visit_type_QCryptoBlockOptionsLUKS_members(
-            v, &ret->u.luks, &local_err);
-        break;
-
-    default:
-        error_setg(&local_err, "Unsupported block format %d", format);
-        break;
-    }
-    if (!local_err) {
-        visit_check_struct(v, &local_err);
-    }
-
-    visit_end_struct(v, NULL);
-
- out:
-    if (local_err) {
-        error_propagate(errp, local_err);
-        qapi_free_QCryptoBlockOpenOptions(ret);
-        ret = NULL;
-    }
-    visit_free(v);
-    return ret;
-}
-
-
-static QCryptoBlockCreateOptions *
-block_crypto_create_opts_init(QCryptoBlockFormat format,
-                              QemuOpts *opts,
-                              Error **errp)
-{
-    Visitor *v;
-    QCryptoBlockCreateOptions *ret = NULL;
-    Error *local_err = NULL;
-
-    ret = g_new0(QCryptoBlockCreateOptions, 1);
-    ret->format = format;
-
-    v = opts_visitor_new(opts);
-
-    visit_start_struct(v, NULL, NULL, 0, &local_err);
-    if (local_err) {
-        goto out;
-    }
-
-    switch (format) {
-    case Q_CRYPTO_BLOCK_FORMAT_LUKS:
-        visit_type_QCryptoBlockCreateOptionsLUKS_members(
-            v, &ret->u.luks, &local_err);
-        break;
-
-    default:
-        error_setg(&local_err, "Unsupported block format %d", format);
-        break;
-    }
-    if (!local_err) {
-        visit_check_struct(v, &local_err);
-    }
-
-    visit_end_struct(v, NULL);
-
- out:
-    if (local_err) {
-        error_propagate(errp, local_err);
-        qapi_free_QCryptoBlockCreateOptions(ret);
-        ret = NULL;
-    }
-    visit_free(v);
-    return ret;
-}
-
-
-static int block_crypto_open_generic(QCryptoBlockFormat format,
-                                     QemuOptsList *opts_spec,
-                                     BlockDriverState *bs,
-                                     QDict *options,
-                                     int flags,
-                                     Error **errp)
-{
-    BlockCrypto *crypto = bs->opaque;
-    QemuOpts *opts = NULL;
-    Error *local_err = NULL;
-    int ret = -EINVAL;
-    QCryptoBlockOpenOptions *open_opts = NULL;
-    unsigned int cflags = 0;
-
-    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
-                               false, errp);
-    if (!bs->file) {
-        return -EINVAL;
-    }
-
-    opts = qemu_opts_create(opts_spec, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        goto cleanup;
-    }
-
-    open_opts = block_crypto_open_opts_init(format, opts, errp);
-    if (!open_opts) {
-        goto cleanup;
-    }
-
-    if (flags & BDRV_O_NO_IO) {
-        cflags |= QCRYPTO_BLOCK_OPEN_NO_IO;
-    }
-    crypto->block = qcrypto_block_open(open_opts,
-                                       block_crypto_read_func,
-                                       bs,
-                                       cflags,
-                                       errp);
-
-    if (!crypto->block) {
-        ret = -EIO;
-        goto cleanup;
-    }
-
-    bs->encrypted = true;
-    bs->valid_key = true;
-
-    ret = 0;
- cleanup:
-    qapi_free_QCryptoBlockOpenOptions(open_opts);
-    return ret;
-}
-
-
-static int block_crypto_create_generic(QCryptoBlockFormat format,
-                                       const char *filename,
-                                       QemuOpts *opts,
-                                       Error **errp)
-{
-    int ret = -EINVAL;
-    QCryptoBlockCreateOptions *create_opts = NULL;
-    QCryptoBlock *crypto = NULL;
-    struct BlockCryptoCreateData data = {
-        .size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
-                         BDRV_SECTOR_SIZE),
-        .opts = opts,
-        .filename = filename,
-    };
-
-    create_opts = block_crypto_create_opts_init(format, opts, errp);
-    if (!create_opts) {
-        return -1;
-    }
-
-    crypto = qcrypto_block_create(create_opts,
-                                  block_crypto_init_func,
-                                  block_crypto_write_func,
-                                  &data,
-                                  errp);
-
-    if (!crypto) {
-        ret = -EIO;
-        goto cleanup;
-    }
-
-    ret = 0;
- cleanup:
-    qcrypto_block_free(crypto);
-    blk_unref(data.blk);
-    qapi_free_QCryptoBlockCreateOptions(create_opts);
-    return ret;
-}
-
-static int block_crypto_truncate(BlockDriverState *bs, int64_t offset,
-                                 Error **errp)
-{
-    BlockCrypto *crypto = bs->opaque;
-    size_t payload_offset =
-        qcrypto_block_get_payload_offset(crypto->block);
-
-    offset += payload_offset;
-
-    return bdrv_truncate(bs->file, offset, errp);
-}
-
-static void block_crypto_close(BlockDriverState *bs)
-{
-    BlockCrypto *crypto = bs->opaque;
-    qcrypto_block_free(crypto->block);
-}
-
-
-#define BLOCK_CRYPTO_MAX_SECTORS 32
-
-static coroutine_fn int
-block_crypto_co_readv(BlockDriverState *bs, int64_t sector_num,
-                      int remaining_sectors, QEMUIOVector *qiov)
-{
-    BlockCrypto *crypto = bs->opaque;
-    int cur_nr_sectors; /* number of sectors in current iteration */
-    uint64_t bytes_done = 0;
-    uint8_t *cipher_data = NULL;
-    QEMUIOVector hd_qiov;
-    int ret = 0;
-    size_t payload_offset =
-        qcrypto_block_get_payload_offset(crypto->block) / 512;
-
-    qemu_iovec_init(&hd_qiov, qiov->niov);
-
-    /* Bounce buffer so we have a linear mem region for
-     * entire sector. XXX optimize so we avoid bounce
-     * buffer in case that qiov->niov == 1
-     */
-    cipher_data =
-        qemu_try_blockalign(bs->file->bs, MIN(BLOCK_CRYPTO_MAX_SECTORS * 512,
-                                              qiov->size));
-    if (cipher_data == NULL) {
-        ret = -ENOMEM;
-        goto cleanup;
-    }
-
-    while (remaining_sectors) {
-        cur_nr_sectors = remaining_sectors;
-
-        if (cur_nr_sectors > BLOCK_CRYPTO_MAX_SECTORS) {
-            cur_nr_sectors = BLOCK_CRYPTO_MAX_SECTORS;
-        }
-
-        qemu_iovec_reset(&hd_qiov);
-        qemu_iovec_add(&hd_qiov, cipher_data, cur_nr_sectors * 512);
-
-        ret = bdrv_co_readv(bs->file,
-                            payload_offset + sector_num,
-                            cur_nr_sectors, &hd_qiov);
-        if (ret < 0) {
-            goto cleanup;
-        }
-
-        if (qcrypto_block_decrypt(crypto->block,
-                                  sector_num,
-                                  cipher_data, cur_nr_sectors * 512,
-                                  NULL) < 0) {
-            ret = -EIO;
-            goto cleanup;
-        }
-
-        qemu_iovec_from_buf(qiov, bytes_done,
-                            cipher_data, cur_nr_sectors * 512);
-
-        remaining_sectors -= cur_nr_sectors;
-        sector_num += cur_nr_sectors;
-        bytes_done += cur_nr_sectors * 512;
-    }
-
- cleanup:
-    qemu_iovec_destroy(&hd_qiov);
-    qemu_vfree(cipher_data);
-
-    return ret;
-}
-
-
-static coroutine_fn int
-block_crypto_co_writev(BlockDriverState *bs, int64_t sector_num,
-                       int remaining_sectors, QEMUIOVector *qiov)
-{
-    BlockCrypto *crypto = bs->opaque;
-    int cur_nr_sectors; /* number of sectors in current iteration */
-    uint64_t bytes_done = 0;
-    uint8_t *cipher_data = NULL;
-    QEMUIOVector hd_qiov;
-    int ret = 0;
-    size_t payload_offset =
-        qcrypto_block_get_payload_offset(crypto->block) / 512;
-
-    qemu_iovec_init(&hd_qiov, qiov->niov);
-
-    /* Bounce buffer so we have a linear mem region for
-     * entire sector. XXX optimize so we avoid bounce
-     * buffer in case that qiov->niov == 1
-     */
-    cipher_data =
-        qemu_try_blockalign(bs->file->bs, MIN(BLOCK_CRYPTO_MAX_SECTORS * 512,
-                                              qiov->size));
-    if (cipher_data == NULL) {
-        ret = -ENOMEM;
-        goto cleanup;
-    }
-
-    while (remaining_sectors) {
-        cur_nr_sectors = remaining_sectors;
-
-        if (cur_nr_sectors > BLOCK_CRYPTO_MAX_SECTORS) {
-            cur_nr_sectors = BLOCK_CRYPTO_MAX_SECTORS;
-        }
-
-        qemu_iovec_to_buf(qiov, bytes_done,
-                          cipher_data, cur_nr_sectors * 512);
-
-        if (qcrypto_block_encrypt(crypto->block,
-                                  sector_num,
-                                  cipher_data, cur_nr_sectors * 512,
-                                  NULL) < 0) {
-            ret = -EIO;
-            goto cleanup;
-        }
-
-        qemu_iovec_reset(&hd_qiov);
-        qemu_iovec_add(&hd_qiov, cipher_data, cur_nr_sectors * 512);
-
-        ret = bdrv_co_writev(bs->file,
-                             payload_offset + sector_num,
-                             cur_nr_sectors, &hd_qiov);
-        if (ret < 0) {
-            goto cleanup;
-        }
-
-        remaining_sectors -= cur_nr_sectors;
-        sector_num += cur_nr_sectors;
-        bytes_done += cur_nr_sectors * 512;
-    }
-
- cleanup:
-    qemu_iovec_destroy(&hd_qiov);
-    qemu_vfree(cipher_data);
-
-    return ret;
-}
-
-
-static int64_t block_crypto_getlength(BlockDriverState *bs)
-{
-    BlockCrypto *crypto = bs->opaque;
-    int64_t len = bdrv_getlength(bs->file->bs);
-
-    ssize_t offset = qcrypto_block_get_payload_offset(crypto->block);
-
-    len -= offset;
-
-    return len;
-}
-
-
-static int block_crypto_probe_luks(const uint8_t *buf,
-                                   int buf_size,
-                                   const char *filename) {
-    return block_crypto_probe_generic(Q_CRYPTO_BLOCK_FORMAT_LUKS,
-                                      buf, buf_size, filename);
-}
-
-static int block_crypto_open_luks(BlockDriverState *bs,
-                                  QDict *options,
-                                  int flags,
-                                  Error **errp)
-{
-    return block_crypto_open_generic(Q_CRYPTO_BLOCK_FORMAT_LUKS,
-                                     &block_crypto_runtime_opts_luks,
-                                     bs, options, flags, errp);
-}
-
-static int block_crypto_create_luks(const char *filename,
-                                    QemuOpts *opts,
-                                    Error **errp)
-{
-    return block_crypto_create_generic(Q_CRYPTO_BLOCK_FORMAT_LUKS,
-                                       filename, opts, errp);
-}
-
-static int block_crypto_get_info_luks(BlockDriverState *bs,
-                                      BlockDriverInfo *bdi)
-{
-    BlockDriverInfo subbdi;
-    int ret;
-
-    ret = bdrv_get_info(bs->file->bs, &subbdi);
-    if (ret != 0) {
-        return ret;
-    }
-
-    bdi->unallocated_blocks_are_zero = false;
-    bdi->can_write_zeroes_with_unmap = false;
-    bdi->cluster_size = subbdi.cluster_size;
-
-    return 0;
-}
-
-static ImageInfoSpecific *
-block_crypto_get_specific_info_luks(BlockDriverState *bs)
-{
-    BlockCrypto *crypto = bs->opaque;
-    ImageInfoSpecific *spec_info;
-    QCryptoBlockInfo *info;
-
-    info = qcrypto_block_get_info(crypto->block, NULL);
-    if (!info) {
-        return NULL;
-    }
-    if (info->format != Q_CRYPTO_BLOCK_FORMAT_LUKS) {
-        qapi_free_QCryptoBlockInfo(info);
-        return NULL;
-    }
-
-    spec_info = g_new(ImageInfoSpecific, 1);
-    spec_info->type = IMAGE_INFO_SPECIFIC_KIND_LUKS;
-    spec_info->u.luks.data = g_new(QCryptoBlockInfoLUKS, 1);
-    *spec_info->u.luks.data = info->u.luks;
-
-    /* Blank out pointers we've just stolen to avoid double free */
-    memset(&info->u.luks, 0, sizeof(info->u.luks));
-
-    qapi_free_QCryptoBlockInfo(info);
-
-    return spec_info;
-}
-
-BlockDriver bdrv_crypto_luks = {
-    .format_name        = "luks",
-    .instance_size      = sizeof(BlockCrypto),
-    .bdrv_probe         = block_crypto_probe_luks,
-    .bdrv_open          = block_crypto_open_luks,
-    .bdrv_close         = block_crypto_close,
-    .bdrv_child_perm    = bdrv_format_default_perms,
-    .bdrv_create        = block_crypto_create_luks,
-    .bdrv_truncate      = block_crypto_truncate,
-    .create_opts        = &block_crypto_create_opts_luks,
-
-    .bdrv_co_readv      = block_crypto_co_readv,
-    .bdrv_co_writev     = block_crypto_co_writev,
-    .bdrv_getlength     = block_crypto_getlength,
-    .bdrv_get_info      = block_crypto_get_info_luks,
-    .bdrv_get_specific_info = block_crypto_get_specific_info_luks,
-};
-
-static void block_crypto_init(void)
-{
-    bdrv_register(&bdrv_crypto_luks);
-}
-
-block_init(block_crypto_init);

block/curl.c

@@ -21,31 +21,21 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
-#include "qapi/error.h"
 #include "qemu-common.h"
 #include "qemu/error-report.h"
 #include "block/block_int.h"
 #include "qapi/qmp/qbool.h"
 #include "qapi/qmp/qstring.h"
-#include "crypto/secret.h"
 #include <curl/curl.h>
-#include "qemu/cutils.h"
 
 // #define DEBUG_CURL
 // #define DEBUG_VERBOSE
 
 #ifdef DEBUG_CURL
-#define DEBUG_CURL_PRINT 1
+#define DPRINTF(fmt, ...) do { printf(fmt, ## __VA_ARGS__); } while (0)
 #else
-#define DEBUG_CURL_PRINT 0
+#define DPRINTF(fmt, ...) do { } while (0)
 #endif
-#define DPRINTF(fmt, ...)                                            \
-    do {                                                             \
-        if (DEBUG_CURL_PRINT) {                                      \
-            fprintf(stderr, fmt, ## __VA_ARGS__);                    \
-        }                                                            \
-    } while (0)
 
 #if LIBCURL_VERSION_NUM >= 0x071000
 /* The multi interface timer callback was introduced in 7.16.0 */
@@ -68,54 +58,48 @@ static CURLMcode __curl_multi_socket_action(CURLM *multi_handle,
 #endif
 
 #define PROTOCOLS (CURLPROTO_HTTP | CURLPROTO_HTTPS | \
-                   CURLPROTO_FTP | CURLPROTO_FTPS)
+                   CURLPROTO_FTP | CURLPROTO_FTPS | \
+                   CURLPROTO_TFTP)
 
 #define CURL_NUM_STATES 8
 #define CURL_NUM_ACB    8
+#define SECTOR_SIZE     512
 #define READ_AHEAD_DEFAULT (256 * 1024)
 #define CURL_TIMEOUT_DEFAULT 5
 #define CURL_TIMEOUT_MAX 10000
 
+#define FIND_RET_NONE   0
+#define FIND_RET_OK     1
+#define FIND_RET_WAIT   2
+
 #define CURL_BLOCK_OPT_URL       "url"
 #define CURL_BLOCK_OPT_READAHEAD "readahead"
 #define CURL_BLOCK_OPT_SSLVERIFY "sslverify"
 #define CURL_BLOCK_OPT_TIMEOUT "timeout"
 #define CURL_BLOCK_OPT_COOKIE    "cookie"
-#define CURL_BLOCK_OPT_COOKIE_SECRET "cookie-secret"
-#define CURL_BLOCK_OPT_USERNAME "username"
-#define CURL_BLOCK_OPT_PASSWORD_SECRET "password-secret"
-#define CURL_BLOCK_OPT_PROXY_USERNAME "proxy-username"
-#define CURL_BLOCK_OPT_PROXY_PASSWORD_SECRET "proxy-password-secret"
 
 struct BDRVCURLState;
 
 typedef struct CURLAIOCB {
-    Coroutine *co;
+    BlockAIOCB common;
+    QEMUBH *bh;
     QEMUIOVector *qiov;
 
-    uint64_t offset;
-    uint64_t bytes;
-    int ret;
+    int64_t sector_num;
+    int nb_sectors;
 
     size_t start;
     size_t end;
-
-    QSIMPLEQ_ENTRY(CURLAIOCB) next;
 } CURLAIOCB;
 
-typedef struct CURLSocket {
-    int fd;
-    QLIST_ENTRY(CURLSocket) next;
-} CURLSocket;
-
 typedef struct CURLState
 {
     struct BDRVCURLState *s;
     CURLAIOCB *acb[CURL_NUM_ACB];
     CURL *curl;
-    QLIST_HEAD(, CURLSocket) sockets;
+    curl_socket_t sock_fd;
     char *orig_buf;
-    uint64_t buf_start;
+    size_t buf_start;
     size_t buf_off;
     size_t buf_len;
     char range[128];
@@ -126,7 +110,7 @@ typedef struct CURLState
 typedef struct BDRVCURLState {
     CURLM *multi;
     QEMUTimer timer;
-    uint64_t len;
+    size_t len;
     CURLState states[CURL_NUM_STATES];
     char *url;
     size_t readahead_size;
@@ -135,12 +119,6 @@ typedef struct BDRVCURLState {
     char *cookie;
     bool accept_range;
     AioContext *aio_context;
-    QemuMutex mutex;
-    QSIMPLEQ_HEAD(, CURLAIOCB) free_state_waitq;
-    char *username;
-    char *password;
-    char *proxyusername;
-    char *proxypassword;
 } BDRVCURLState;
 
 static void curl_clean_state(CURLState *s);
@@ -148,7 +126,6 @@ static void curl_multi_do(void *arg);
 static void curl_multi_read(void *arg);
 
 #ifdef NEED_CURL_TIMER_CALLBACK
-/* Called from curl_multi_do_locked, with s->mutex held.  */
 static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
 {
     BDRVCURLState *s = opaque;
@@ -165,57 +142,38 @@ static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
 }
 #endif
 
-/* Called from curl_multi_do_locked, with s->mutex held.  */
 static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
                         void *userp, void *sp)
 {
     BDRVCURLState *s;
     CURLState *state = NULL;
-    CURLSocket *socket;
-
     curl_easy_getinfo(curl, CURLINFO_PRIVATE, (char **)&state);
+    state->sock_fd = fd;
     s = state->s;
 
-    QLIST_FOREACH(socket, &state->sockets, next) {
-        if (socket->fd == fd) {
-            if (action == CURL_POLL_REMOVE) {
-                QLIST_REMOVE(socket, next);
-                g_free(socket);
-            }
-            break;
-        }
-    }
-    if (!socket) {
-        socket = g_new0(CURLSocket, 1);
-        socket->fd = fd;
-        QLIST_INSERT_HEAD(&state->sockets, socket, next);
-    }
-    socket = NULL;
-
-    DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, (int)fd);
+    DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, fd);
     switch (action) {
         case CURL_POLL_IN:
             aio_set_fd_handler(s->aio_context, fd, false,
-                               curl_multi_read, NULL, NULL, state);
+                               curl_multi_read, NULL, state);
             break;
         case CURL_POLL_OUT:
             aio_set_fd_handler(s->aio_context, fd, false,
-                               NULL, curl_multi_do, NULL, state);
+                               NULL, curl_multi_do, state);
             break;
         case CURL_POLL_INOUT:
             aio_set_fd_handler(s->aio_context, fd, false,
-                               curl_multi_read, curl_multi_do, NULL, state);
+                               curl_multi_read, curl_multi_do, state);
             break;
         case CURL_POLL_REMOVE:
             aio_set_fd_handler(s->aio_context, fd, false,
-                               NULL, NULL, NULL, NULL);
+                               NULL, NULL, NULL);
             break;
     }
 
     return 0;
 }
 
-/* Called from curl_multi_do_locked, with s->mutex held.  */
 static size_t curl_header_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
 {
     BDRVCURLState *s = opaque;
@@ -230,7 +188,6 @@ static size_t curl_header_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
     return realsize;
 }
 
-/* Called from curl_multi_do_locked, with s->mutex held.  */
 static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
 {
     CURLState *s = ((CURLState*)opaque);
@@ -239,13 +196,12 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
 
     DPRINTF("CURL: Just reading %zd bytes\n", realsize);
 
-    if (!s || !s->orig_buf) {
-        goto read_end;
-    }
+    if (!s || !s->orig_buf)
+        return 0;
 
     if (s->buf_off >= s->buf_len) {
         /* buffer full, read nothing */
-        goto read_end;
+        return 0;
     }
     realsize = MIN(realsize, s->buf_len - s->buf_off);
     memcpy(s->orig_buf + s->buf_off, ptr, realsize);
@@ -258,43 +214,27 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
             continue;
 
         if ((s->buf_off >= acb->end)) {
-            size_t request_length = acb->bytes;
-
             qemu_iovec_from_buf(acb->qiov, 0, s->orig_buf + acb->start,
                                 acb->end - acb->start);
-
-            if (acb->end - acb->start < request_length) {
-                size_t offset = acb->end - acb->start;
-                qemu_iovec_memset(acb->qiov, offset, 0,
-                                  request_length - offset);
-            }
-
-            acb->ret = 0;
+            acb->common.cb(acb->common.opaque, 0);
+            qemu_aio_unref(acb);
             s->acb[i] = NULL;
-            qemu_mutex_unlock(&s->s->mutex);
-            aio_co_wake(acb->co);
-            qemu_mutex_lock(&s->s->mutex);
         }
     }
 
-read_end:
-    /* curl will error out if we do not return this value */
-    return size * nmemb;
+    return realsize;
 }
 
-/* Called with s->mutex held.  */
-static bool curl_find_buf(BDRVCURLState *s, uint64_t start, uint64_t len,
-                          CURLAIOCB *acb)
+static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
+                         CURLAIOCB *acb)
 {
     int i;
-    uint64_t end = start + len;
-    uint64_t clamped_end = MIN(end, s->len);
-    uint64_t clamped_len = clamped_end - start;
+    size_t end = start + len;
 
     for (i=0; i<CURL_NUM_STATES; i++) {
         CURLState *state = &s->states[i];
-        uint64_t buf_end = (state->buf_start + state->buf_off);
-        uint64_t buf_fend = (state->buf_start + state->buf_len);
+        size_t buf_end = (state->buf_start + state->buf_off);
+        size_t buf_fend = (state->buf_start + state->buf_len);
 
         if (!state->orig_buf)
             continue;
@@ -304,44 +244,41 @@ static bool curl_find_buf(BDRVCURLState *s, uint64_t start, uint64_t len,
         // Does the existing buffer cover our section?
         if ((start >= state->buf_start) &&
             (start <= buf_end) &&
-            (clamped_end >= state->buf_start) &&
-            (clamped_end <= buf_end))
+            (end >= state->buf_start) &&
+            (end <= buf_end))
         {
             char *buf = state->orig_buf + (start - state->buf_start);
 
-            qemu_iovec_from_buf(acb->qiov, 0, buf, clamped_len);
-            if (clamped_len < len) {
-                qemu_iovec_memset(acb->qiov, clamped_len, 0, len - clamped_len);
-            }
-            acb->ret = 0;
-            return true;
+            qemu_iovec_from_buf(acb->qiov, 0, buf, len);
+            acb->common.cb(acb->common.opaque, 0);
+
+            return FIND_RET_OK;
         }
 
         // Wait for unfinished chunks
         if (state->in_use &&
             (start >= state->buf_start) &&
             (start <= buf_fend) &&
-            (clamped_end >= state->buf_start) &&
-            (clamped_end <= buf_fend))
+            (end >= state->buf_start) &&
+            (end <= buf_fend))
         {
             int j;
 
             acb->start = start - state->buf_start;
-            acb->end = acb->start + clamped_len;
+            acb->end = acb->start + len;
 
             for (j=0; j<CURL_NUM_ACB; j++) {
                 if (!state->acb[j]) {
                     state->acb[j] = acb;
-                    return true;
+                    return FIND_RET_WAIT;
                 }
             }
         }
     }
 
-    return false;
+    return FIND_RET_NONE;
 }
 
-/* Called with s->mutex held.  */
 static void curl_multi_check_completion(BDRVCURLState *s)
 {
     int msgs_in_queue;
@@ -383,11 +320,9 @@ static void curl_multi_check_completion(BDRVCURLState *s)
                         continue;
                     }
 
-                    acb->ret = -EIO;
+                    acb->common.cb(acb->common.opaque, -EPROTO);
+                    qemu_aio_unref(acb);
                     state->acb[i] = NULL;
-                    qemu_mutex_unlock(&s->mutex);
-                    aio_co_wake(acb->co);
-                    qemu_mutex_lock(&s->mutex);
                 }
             }
 
@@ -397,10 +332,9 @@ static void curl_multi_check_completion(BDRVCURLState *s)
     }
 }
 
-/* Called with s->mutex held.  */
-static void curl_multi_do_locked(CURLState *s)
+static void curl_multi_do(void *arg)
 {
-    CURLSocket *socket, *next_socket;
+    CURLState *s = (CURLState *)arg;
     int running;
     int r;
 
@@ -408,32 +342,18 @@ static void curl_multi_do_locked(CURLState *s)
         return;
     }
 
-    /* Need to use _SAFE because curl_multi_socket_action() may trigger
-     * curl_sock_cb() which might modify this list */
-    QLIST_FOREACH_SAFE(socket, &s->sockets, next, next_socket) {
-        do {
-            r = curl_multi_socket_action(s->s->multi, socket->fd, 0, &running);
-        } while (r == CURLM_CALL_MULTI_PERFORM);
-    }
-}
+    do {
+        r = curl_multi_socket_action(s->s->multi, s->sock_fd, 0, &running);
+    } while(r == CURLM_CALL_MULTI_PERFORM);
 
-static void curl_multi_do(void *arg)
-{
-    CURLState *s = (CURLState *)arg;
-
-    qemu_mutex_lock(&s->s->mutex);
-    curl_multi_do_locked(s);
-    qemu_mutex_unlock(&s->s->mutex);
 }
 
 static void curl_multi_read(void *arg)
 {
     CURLState *s = (CURLState *)arg;
 
-    qemu_mutex_lock(&s->s->mutex);
-    curl_multi_do_locked(s);
+    curl_multi_do(arg);
     curl_multi_check_completion(s->s);
-    qemu_mutex_unlock(&s->s->mutex);
 }
 
 static void curl_multi_timeout_do(void *arg)
@@ -446,38 +366,40 @@ static void curl_multi_timeout_do(void *arg)
         return;
     }
 
-    qemu_mutex_lock(&s->mutex);
     curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
 
     curl_multi_check_completion(s);
-    qemu_mutex_unlock(&s->mutex);
 #else
     abort();
 #endif
 }
 
-/* Called with s->mutex held.  */
-static CURLState *curl_find_state(BDRVCURLState *s)
+static CURLState *curl_init_state(BlockDriverState *bs, BDRVCURLState *s)
 {
     CURLState *state = NULL;
-    int i;
+    int i, j;
+
+    do {
+        for (i=0; i<CURL_NUM_STATES; i++) {
+            for (j=0; j<CURL_NUM_ACB; j++)
+                if (s->states[i].acb[j])
+                    continue;
+            if (s->states[i].in_use)
+                continue;
 
-    for (i = 0; i < CURL_NUM_STATES; i++) {
-        if (!s->states[i].in_use) {
             state = &s->states[i];
             state->in_use = 1;
             break;
         }
-    }
-    return state;
-}
+        if (!state) {
+            aio_poll(bdrv_get_aio_context(bs), true);
+        }
+    } while(!state);
 
-static int curl_init_state(BDRVCURLState *s, CURLState *state)
-{
     if (!state->curl) {
         state->curl = curl_easy_init();
         if (!state->curl) {
-            return -EIO;
+            return NULL;
         }
         curl_easy_setopt(state->curl, CURLOPT_URL, s->url);
         curl_easy_setopt(state->curl, CURLOPT_SSL_VERIFYPEER,
@@ -496,21 +418,6 @@ static int curl_init_state(BDRVCURLState *s, CURLState *state)
         curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
         curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
 
-        if (s->username) {
-            curl_easy_setopt(state->curl, CURLOPT_USERNAME, s->username);
-        }
-        if (s->password) {
-            curl_easy_setopt(state->curl, CURLOPT_PASSWORD, s->password);
-        }
-        if (s->proxyusername) {
-            curl_easy_setopt(state->curl,
-                             CURLOPT_PROXYUSERNAME, s->proxyusername);
-        }
-        if (s->proxypassword) {
-            curl_easy_setopt(state->curl,
-                             CURLOPT_PROXYPASSWORD, s->proxypassword);
-        }
-
         /* Restrict supported protocols to avoid security issues in the more
          * obscure protocols.  For example, do not allow POP3/SMTP/IMAP see
          * CVE-2013-0249.
@@ -527,46 +434,22 @@ static int curl_init_state(BDRVCURLState *s, CURLState *state)
 #endif
     }
 
-    QLIST_INIT(&state->sockets);
     state->s = s;
 
-    return 0;
+    return state;
 }
 
-/* Called with s->mutex held.  */
 static void curl_clean_state(CURLState *s)
 {
-    CURLAIOCB *next;
-    int j;
-    for (j = 0; j < CURL_NUM_ACB; j++) {
-        assert(!s->acb[j]);
-    }
-
     if (s->s->multi)
         curl_multi_remove_handle(s->s->multi, s->curl);
-
-    while (!QLIST_EMPTY(&s->sockets)) {
-        CURLSocket *socket = QLIST_FIRST(&s->sockets);
-
-        QLIST_REMOVE(socket, next);
-        g_free(socket);
-    }
-
     s->in_use = 0;
-
-    next = QSIMPLEQ_FIRST(&s->s->free_state_waitq);
-    if (next) {
-        QSIMPLEQ_REMOVE_HEAD(&s->s->free_state_waitq, next);
-        qemu_mutex_unlock(&s->s->mutex);
-        aio_co_wake(next->co);
-        qemu_mutex_lock(&s->s->mutex);
-    }
 }
 
 static void curl_parse_filename(const char *filename, QDict *options,
                                 Error **errp)
 {
-    qdict_put_str(options, CURL_BLOCK_OPT_URL, filename);
+    qdict_put(options, CURL_BLOCK_OPT_URL, qstring_from_str(filename));
 }
 
 static void curl_detach_aio_context(BlockDriverState *bs)
@@ -574,7 +457,6 @@ static void curl_detach_aio_context(BlockDriverState *bs)
     BDRVCURLState *s = bs->opaque;
     int i;
 
-    qemu_mutex_lock(&s->mutex);
     for (i = 0; i < CURL_NUM_STATES; i++) {
         if (s->states[i].in_use) {
             curl_clean_state(&s->states[i]);
@@ -590,7 +472,6 @@ static void curl_detach_aio_context(BlockDriverState *bs)
         curl_multi_cleanup(s->multi);
         s->multi = NULL;
     }
-    qemu_mutex_unlock(&s->mutex);
 
     timer_del(&s->timer);
 }
@@ -643,36 +524,10 @@ static QemuOptsList runtime_opts = {
             .type = QEMU_OPT_STRING,
             .help = "Pass the cookie or list of cookies with each request"
         },
-        {
-            .name = CURL_BLOCK_OPT_COOKIE_SECRET,
-            .type = QEMU_OPT_STRING,
-            .help = "ID of secret used as cookie passed with each request"
-        },
-        {
-            .name = CURL_BLOCK_OPT_USERNAME,
-            .type = QEMU_OPT_STRING,
-            .help = "Username for HTTP auth"
-        },
-        {
-            .name = CURL_BLOCK_OPT_PASSWORD_SECRET,
-            .type = QEMU_OPT_STRING,
-            .help = "ID of secret used as password for HTTP auth",
-        },
-        {
-            .name = CURL_BLOCK_OPT_PROXY_USERNAME,
-            .type = QEMU_OPT_STRING,
-            .help = "Username for HTTP proxy auth"
-        },
-        {
-            .name = CURL_BLOCK_OPT_PROXY_PASSWORD_SECRET,
-            .type = QEMU_OPT_STRING,
-            .help = "ID of secret used as password for HTTP proxy auth",
-        },
         { /* end of list */ }
     },
 };
 
-
 static int curl_open(BlockDriverState *bs, QDict *options, int flags,
                      Error **errp)
 {
@@ -682,10 +537,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     Error *local_err = NULL;
     const char *file;
     const char *cookie;
-    const char *cookie_secret;
     double d;
-    const char *secretid;
-    const char *protocol_delimiter;
 
     static int inited = 0;
 
@@ -694,7 +546,6 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
         return -EROFS;
     }
 
-    qemu_mutex_init(&s->mutex);
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
@@ -720,22 +571,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     s->sslverify = qemu_opt_get_bool(opts, CURL_BLOCK_OPT_SSLVERIFY, true);
 
     cookie = qemu_opt_get(opts, CURL_BLOCK_OPT_COOKIE);
-    cookie_secret = qemu_opt_get(opts, CURL_BLOCK_OPT_COOKIE_SECRET);
-
-    if (cookie && cookie_secret) {
-        error_setg(errp,
-                   "curl driver cannot handle both cookie and cookie secret");
-        goto out_noclean;
-    }
-
-    if (cookie_secret) {
-        s->cookie = qcrypto_secret_lookup_as_utf8(cookie_secret, errp);
-        if (!s->cookie) {
-            goto out_noclean;
-        }
-    } else {
-        s->cookie = g_strdup(cookie);
-    }
+    s->cookie = g_strdup(cookie);
 
     file = qemu_opt_get(opts, CURL_BLOCK_OPT_URL);
     if (file == NULL) {
@@ -743,57 +579,20 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
         goto out_noclean;
     }
 
-    if (!strstart(file, bs->drv->protocol_name, &protocol_delimiter) ||
-        !strstart(protocol_delimiter, "://", NULL))
-    {
-        error_setg(errp, "%s curl driver cannot handle the URL '%s' (does not "
-                   "start with '%s://')", bs->drv->protocol_name, file,
-                   bs->drv->protocol_name);
-        goto out_noclean;
-    }
-
-    s->username = g_strdup(qemu_opt_get(opts, CURL_BLOCK_OPT_USERNAME));
-    secretid = qemu_opt_get(opts, CURL_BLOCK_OPT_PASSWORD_SECRET);
-
-    if (secretid) {
-        s->password = qcrypto_secret_lookup_as_utf8(secretid, errp);
-        if (!s->password) {
-            goto out_noclean;
-        }
-    }
-
-    s->proxyusername = g_strdup(
-        qemu_opt_get(opts, CURL_BLOCK_OPT_PROXY_USERNAME));
-    secretid = qemu_opt_get(opts, CURL_BLOCK_OPT_PROXY_PASSWORD_SECRET);
-    if (secretid) {
-        s->proxypassword = qcrypto_secret_lookup_as_utf8(secretid, errp);
-        if (!s->proxypassword) {
-            goto out_noclean;
-        }
-    }
-
     if (!inited) {
         curl_global_init(CURL_GLOBAL_ALL);
         inited = 1;
     }
 
     DPRINTF("CURL: Opening %s\n", file);
-    QSIMPLEQ_INIT(&s->free_state_waitq);
     s->aio_context = bdrv_get_aio_context(bs);
     s->url = g_strdup(file);
-    qemu_mutex_lock(&s->mutex);
-    state = curl_find_state(s);
-    qemu_mutex_unlock(&s->mutex);
-    if (!state) {
+    state = curl_init_state(bs, s);
+    if (!state)
         goto out_noclean;
-    }
 
     // Get file size
 
-    if (curl_init_state(s, state) < 0) {
-        goto out;
-    }
-
     s->accept_range = false;
     curl_easy_setopt(state->curl, CURLOPT_NOBODY, 1);
     curl_easy_setopt(state->curl, CURLOPT_HEADERFUNCTION,
@@ -801,28 +600,11 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     curl_easy_setopt(state->curl, CURLOPT_HEADERDATA, s);
     if (curl_easy_perform(state->curl))
         goto out;
-    if (curl_easy_getinfo(state->curl, CURLINFO_CONTENT_LENGTH_DOWNLOAD, &d)) {
+    curl_easy_getinfo(state->curl, CURLINFO_CONTENT_LENGTH_DOWNLOAD, &d);
+    if (d)
+        s->len = (size_t)d;
+    else if(!s->len)
         goto out;
-    }
-    /* Prior CURL 7.19.4 return value of 0 could mean that the file size is not
-     * know or the size is zero. From 7.19.4 CURL returns -1 if size is not
-     * known and zero if it is realy zero-length file. */
-#if LIBCURL_VERSION_NUM >= 0x071304
-    if (d < 0) {
-        pstrcpy(state->errmsg, CURL_ERROR_SIZE,
-                "Server didn't report file size.");
-        goto out;
-    }
-#else
-    if (d <= 0) {
-        pstrcpy(state->errmsg, CURL_ERROR_SIZE,
-                "Unknown file size or zero-length file.");
-        goto out;
-    }
-#endif
-
-    s->len = d;
-
     if ((!strncasecmp(s->url, "http://", strlen("http://"))
         || !strncasecmp(s->url, "https://", strlen("https://")))
         && !s->accept_range) {
@@ -830,11 +612,9 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
                 "Server does not support 'range' (byte ranges).");
         goto out;
     }
-    DPRINTF("CURL: Size = %" PRIu64 "\n", s->len);
+    DPRINTF("CURL: Size = %zd\n", s->len);
 
-    qemu_mutex_lock(&s->mutex);
     curl_clean_state(state);
-    qemu_mutex_unlock(&s->mutex);
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 
@@ -848,95 +628,94 @@ out:
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 out_noclean:
-    qemu_mutex_destroy(&s->mutex);
     g_free(s->cookie);
     g_free(s->url);
     qemu_opts_del(opts);
     return -EINVAL;
 }
 
-static void curl_setup_preadv(BlockDriverState *bs, CURLAIOCB *acb)
+static const AIOCBInfo curl_aiocb_info = {
+    .aiocb_size         = sizeof(CURLAIOCB),
+};
+
+
+static void curl_readv_bh_cb(void *p)
 {
     CURLState *state;
     int running;
 
-    BDRVCURLState *s = bs->opaque;
+    CURLAIOCB *acb = p;
+    BDRVCURLState *s = acb->common.bs->opaque;
 
-    uint64_t start = acb->offset;
-    uint64_t end;
+    qemu_bh_delete(acb->bh);
+    acb->bh = NULL;
 
-    qemu_mutex_lock(&s->mutex);
+    size_t start = acb->sector_num * SECTOR_SIZE;
+    size_t end;
 
     // In case we have the requested data already (e.g. read-ahead),
     // we can just call the callback and be done.
-    if (curl_find_buf(s, start, acb->bytes, acb)) {
-        goto out;
+    switch (curl_find_buf(s, start, acb->nb_sectors * SECTOR_SIZE, acb)) {
+        case FIND_RET_OK:
+            qemu_aio_unref(acb);
+            // fall through
+        case FIND_RET_WAIT:
+            return;
+        default:
+            break;
     }
 
     // No cache found, so let's start a new request
-    for (;;) {
-        state = curl_find_state(s);
-        if (state) {
-            break;
-        }
-        QSIMPLEQ_INSERT_TAIL(&s->free_state_waitq, acb, next);
-        qemu_mutex_unlock(&s->mutex);
-        qemu_coroutine_yield();
-        qemu_mutex_lock(&s->mutex);
-    }
-
-    if (curl_init_state(s, state) < 0) {
-        curl_clean_state(state);
-        acb->ret = -EIO;
-        goto out;
+    state = curl_init_state(acb->common.bs, s);
+    if (!state) {
+        acb->common.cb(acb->common.opaque, -EIO);
+        qemu_aio_unref(acb);
+        return;
     }
 
     acb->start = 0;
-    acb->end = MIN(acb->bytes, s->len - start);
+    acb->end = (acb->nb_sectors * SECTOR_SIZE);
 
     state->buf_off = 0;
     g_free(state->orig_buf);
     state->buf_start = start;
-    state->buf_len = MIN(acb->end + s->readahead_size, s->len - start);
-    end = start + state->buf_len - 1;
+    state->buf_len = acb->end + s->readahead_size;
+    end = MIN(start + state->buf_len, s->len) - 1;
     state->orig_buf = g_try_malloc(state->buf_len);
     if (state->buf_len && state->orig_buf == NULL) {
         curl_clean_state(state);
-        acb->ret = -ENOMEM;
-        goto out;
+        acb->common.cb(acb->common.opaque, -ENOMEM);
+        qemu_aio_unref(acb);
+        return;
     }
     state->acb[0] = acb;
 
-    snprintf(state->range, 127, "%" PRIu64 "-%" PRIu64, start, end);
-    DPRINTF("CURL (AIO): Reading %" PRIu64 " at %" PRIu64 " (%s)\n",
-            acb->bytes, start, state->range);
+    snprintf(state->range, 127, "%zd-%zd", start, end);
+    DPRINTF("CURL (AIO): Reading %d at %zd (%s)\n",
+            (acb->nb_sectors * SECTOR_SIZE), start, state->range);
     curl_easy_setopt(state->curl, CURLOPT_RANGE, state->range);
 
     curl_multi_add_handle(s->multi, state->curl);
 
     /* Tell curl it needs to kick things off */
     curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
-
-out:
-    qemu_mutex_unlock(&s->mutex);
 }
 
-static int coroutine_fn curl_co_preadv(BlockDriverState *bs,
-        uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+static BlockAIOCB *curl_aio_readv(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockCompletionFunc *cb, void *opaque)
 {
-    CURLAIOCB acb = {
-        .co = qemu_coroutine_self(),
-        .ret = -EINPROGRESS,
-        .qiov = qiov,
-        .offset = offset,
-        .bytes = bytes
-    };
+    CURLAIOCB *acb;
 
-    curl_setup_preadv(bs, &acb);
-    while (acb.ret == -EINPROGRESS) {
-        qemu_coroutine_yield();
-    }
-    return acb.ret;
+    acb = qemu_aio_get(&curl_aiocb_info, bs, cb, opaque);
+
+    acb->qiov = qiov;
+    acb->sector_num = sector_num;
+    acb->nb_sectors = nb_sectors;
+
+    acb->bh = aio_bh_new(bdrv_get_aio_context(bs), curl_readv_bh_cb, acb);
+    qemu_bh_schedule(acb->bh);
+    return &acb->common;
 }
 
 static void curl_close(BlockDriverState *bs)
@@ -945,7 +724,6 @@ static void curl_close(BlockDriverState *bs)
 
     DPRINTF("CURL: Close\n");
     curl_detach_aio_context(bs);
-    qemu_mutex_destroy(&s->mutex);
 
     g_free(s->cookie);
     g_free(s->url);
@@ -967,7 +745,7 @@ static BlockDriver bdrv_http = {
     .bdrv_close                 = curl_close,
     .bdrv_getlength             = curl_getlength,
 
-    .bdrv_co_preadv             = curl_co_preadv,
+    .bdrv_aio_readv             = curl_aio_readv,
 
     .bdrv_detach_aio_context    = curl_detach_aio_context,
     .bdrv_attach_aio_context    = curl_attach_aio_context,
@@ -983,7 +761,7 @@ static BlockDriver bdrv_https = {
     .bdrv_close                 = curl_close,
     .bdrv_getlength             = curl_getlength,
 
-    .bdrv_co_preadv             = curl_co_preadv,
+    .bdrv_aio_readv             = curl_aio_readv,
 
     .bdrv_detach_aio_context    = curl_detach_aio_context,
     .bdrv_attach_aio_context    = curl_attach_aio_context,
@@ -999,7 +777,7 @@ static BlockDriver bdrv_ftp = {
     .bdrv_close                 = curl_close,
     .bdrv_getlength             = curl_getlength,
 
-    .bdrv_co_preadv             = curl_co_preadv,
+    .bdrv_aio_readv             = curl_aio_readv,
 
     .bdrv_detach_aio_context    = curl_detach_aio_context,
     .bdrv_attach_aio_context    = curl_attach_aio_context,
@@ -1015,7 +793,23 @@ static BlockDriver bdrv_ftps = {
     .bdrv_close                 = curl_close,
     .bdrv_getlength             = curl_getlength,
 
-    .bdrv_co_preadv             = curl_co_preadv,
+    .bdrv_aio_readv             = curl_aio_readv,
+
+    .bdrv_detach_aio_context    = curl_detach_aio_context,
+    .bdrv_attach_aio_context    = curl_attach_aio_context,
+};
+
+static BlockDriver bdrv_tftp = {
+    .format_name                = "tftp",
+    .protocol_name              = "tftp",
+
+    .instance_size              = sizeof(BDRVCURLState),
+    .bdrv_parse_filename        = curl_parse_filename,
+    .bdrv_file_open             = curl_open,
+    .bdrv_close                 = curl_close,
+    .bdrv_getlength             = curl_getlength,
+
+    .bdrv_aio_readv             = curl_aio_readv,
 
     .bdrv_detach_aio_context    = curl_detach_aio_context,
     .bdrv_attach_aio_context    = curl_attach_aio_context,
@@ -1027,6 +821,7 @@ static void curl_block_init(void)
     bdrv_register(&bdrv_https);
     bdrv_register(&bdrv_ftp);
     bdrv_register(&bdrv_ftps);
+    bdrv_register(&bdrv_tftp);
 }
 
 block_init(curl_block_init);

block/dictzip.c

@@ -0,0 +1,584 @@
+/*
+ * DictZip Block driver for dictzip enabled gzip files
+ *
+ * Use the "dictzip" tool from the "dictd" package to create gzip files that
+ * contain the extra DictZip headers.
+ *
+ * dictzip(1) is a compression program which creates compressed files in the
+ * gzip format (see RFC 1952). However, unlike gzip(1), dictzip(1) compresses
+ * the file in pieces and stores an index to the pieces in the gzip header.
+ * This allows random access to the file at the granularity of the compressed
+ * pieces (currently about 64kB) while maintaining good compression ratios
+ * (within 5% of the expected ratio for dictionary data).
+ * dictd(8) uses files stored in this format.
+ *
+ * For details on DictZip see http://dict.org/.
+ *
+ * Copyright (c) 2009 Alexander Graf <agraf@suse.de>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu-common.h"
+#include "block/block_int.h"
+#include <zlib.h>
+
+// #define DEBUG
+
+#ifdef DEBUG
+#define dprintf(fmt, ...) do { printf("dzip: " fmt, ## __VA_ARGS__); } while (0)
+#else
+#define dprintf(fmt, ...) do { } while (0)
+#endif
+
+#define SECTOR_SIZE 512
+#define Z_STREAM_COUNT 4
+#define CACHE_COUNT 20
+
+/* magic values */
+
+#define GZ_MAGIC1     0x1f
+#define GZ_MAGIC2     0x8b
+#define DZ_MAGIC1      'R'
+#define DZ_MAGIC2      'A'
+
+#define GZ_FEXTRA     0x04      /* Optional field (random access index)    */
+#define GZ_FNAME      0x08      /* Original name                           */
+#define GZ_COMMENT    0x10      /* Zero-terminated, human-readable comment */
+#define GZ_FHCRC      0x02      /* Header CRC16                            */
+
+/* offsets */
+
+#define GZ_ID            0      /* GZ_MAGIC (16bit)                        */
+#define GZ_FLG           3      /* FLaGs (see above)                       */
+#define GZ_XLEN         10      /* eXtra LENgth (16bit)                    */
+#define GZ_SI           12      /* Subfield ID (16bit)                     */
+#define GZ_VERSION      16      /* Version for subfield format             */
+#define GZ_CHUNKSIZE    18      /* Chunk size (16bit)                      */
+#define GZ_CHUNKCNT     20      /* Number of chunks (16bit)                */
+#define GZ_RNDDATA      22      /* Random access data (16bit)              */
+
+#define GZ_99_CHUNKSIZE 18      /* Chunk size (32bit)                      */
+#define GZ_99_CHUNKCNT  22      /* Number of chunks (32bit)                */
+#define GZ_99_FILESIZE  26      /* Size of unpacked file (64bit)           */
+#define GZ_99_RNDDATA   34      /* Random access data (32bit)              */
+
+struct BDRVDictZipState;
+
+typedef struct DictZipAIOCB {
+    BlockAIOCB common;
+    struct BDRVDictZipState *s;
+    QEMUIOVector *qiov;          /* QIOV of the original request */
+    QEMUIOVector *qiov_gz;       /* QIOV of the gz subrequest */
+    QEMUBH *bh;                  /* BH for cache */
+    z_stream *zStream;           /* stream to use for decoding */
+    int zStream_id;              /* stream id of the above pointer */
+    size_t start;                /* offset into the uncompressed file */
+    size_t len;                  /* uncompressed bytes to read */
+    uint8_t *gzipped;            /* the gzipped data */
+    uint8_t *buf;                /* cached result */
+    size_t gz_len;               /* amount of gzip data */
+    size_t gz_start;             /* uncompressed starting point of gzip data */
+    uint64_t offset;             /* offset for "start" into the uncompressed chunk */
+    int chunks_len;              /* amount of uncompressed data in all gzip data */
+} DictZipAIOCB;
+
+typedef struct dict_cache {
+    size_t start;
+    size_t len;
+    uint8_t *buf;
+} DictCache;
+
+typedef struct BDRVDictZipState {
+    BlockDriverState *hd;
+    z_stream zStream[Z_STREAM_COUNT];
+    DictCache cache[CACHE_COUNT];
+    int cache_index;
+    uint8_t  stream_in_use;
+    uint64_t chunk_len;
+    uint32_t chunk_cnt;
+    uint16_t *chunks;
+    uint32_t *chunks32;
+    uint64_t *offsets;
+    int64_t file_len;
+} BDRVDictZipState;
+
+static int start_zStream(z_stream *zStream)
+{
+    zStream->zalloc    = NULL;
+    zStream->zfree     = NULL;
+    zStream->opaque    = NULL;
+    zStream->next_in   = 0;
+    zStream->avail_in  = 0;
+    zStream->next_out  = NULL;
+    zStream->avail_out = 0;
+
+    return inflateInit2( zStream, -15 );
+}
+
+static QemuOptsList runtime_opts = {
+    .name = "dzip",
+    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
+    .desc = {
+        {
+            .name = "filename",
+            .type = QEMU_OPT_STRING,
+            .help = "URL to the dictzip file",
+        },
+        { /* end of list */ }
+    },
+};
+
+static int dictzip_open(BlockDriverState *bs, QDict *options, int flags, Error **errp)
+{
+    BDRVDictZipState *s = bs->opaque;
+    const char *err = "Unknown (read error?)";
+    uint8_t magic[2];
+    char buf[100];
+    uint8_t header_flags;
+    uint16_t chunk_len16;
+    uint16_t chunk_cnt16;
+    uint32_t chunk_len32;
+    uint16_t header_ver;
+    uint16_t tmp_short;
+    uint64_t offset;
+    int chunks_len;
+    int headerLength = GZ_XLEN - 1;
+    int rnd_offs;
+    int ret;
+    int i;
+    QemuOpts *opts;
+    Error *local_err = NULL;
+    const char *filename;
+
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    qemu_opts_absorb_qdict(opts, options, &local_err);
+    if (local_err != NULL) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    filename = qemu_opt_get(opts, "filename");
+
+    if (!strncmp(filename, "dzip://", 7))
+        filename += 7;
+    else if (!strncmp(filename, "dzip:", 5))
+        filename += 5;
+
+    ret = bdrv_open(&s->hd, filename, NULL, NULL, flags | BDRV_O_PROTOCOL, &local_err);
+    if (ret < 0) {
+        error_propagate(errp, local_err);
+        qemu_opts_del(opts);
+        return ret;
+    }
+
+    /* initialize zlib streams */
+    for (i = 0; i < Z_STREAM_COUNT; i++) {
+        if (start_zStream( &s->zStream[i] ) != Z_OK) {
+            err = s->zStream[i].msg;
+            goto fail;
+        }
+    }
+
+    /* gzip header */
+    if (bdrv_pread(s->hd, GZ_ID, &magic, sizeof(magic)) != sizeof(magic))
+        goto fail;
+
+    if (!((magic[0] == GZ_MAGIC1) && (magic[1] == GZ_MAGIC2))) {
+        err = "No gzip file";
+        goto fail;
+    }
+
+    /* dzip header */
+    if (bdrv_pread(s->hd, GZ_FLG, &header_flags, 1) != 1)
+        goto fail;
+
+    if (!(header_flags & GZ_FEXTRA)) {
+        err = "Not a dictzip file (wrong flags)";
+        goto fail;
+    }
+
+    /* extra length */
+    if (bdrv_pread(s->hd, GZ_XLEN, &tmp_short, 2) != 2)
+        goto fail;
+
+    headerLength += le16_to_cpu(tmp_short) + 2;
+
+    /* DictZip magic */
+    if (bdrv_pread(s->hd, GZ_SI, &magic, 2) != 2)
+        goto fail;
+
+    if (magic[0] != DZ_MAGIC1 || magic[1] != DZ_MAGIC2) {
+        err = "Not a dictzip file (missing extra magic)";
+        goto fail;
+    }
+
+    /* DictZip version */
+    if (bdrv_pread(s->hd, GZ_VERSION, &header_ver, 2) != 2)
+        goto fail;
+
+    header_ver = le16_to_cpu(header_ver);
+
+    switch (header_ver) {
+        case 1: /* Normal DictZip */
+            /* number of chunks */
+            if (bdrv_pread(s->hd, GZ_CHUNKSIZE, &chunk_len16, 2) != 2)
+                goto fail;
+
+            s->chunk_len = le16_to_cpu(chunk_len16);
+
+            /* chunk count */
+            if (bdrv_pread(s->hd, GZ_CHUNKCNT, &chunk_cnt16, 2) != 2)
+                goto fail;
+
+            s->chunk_cnt = le16_to_cpu(chunk_cnt16);
+            chunks_len = sizeof(short) * s->chunk_cnt;
+            rnd_offs = GZ_RNDDATA;
+            break;
+        case 99: /* Special Alex pigz version */
+            /* number of chunks */
+            if (bdrv_pread(s->hd, GZ_99_CHUNKSIZE, &chunk_len32, 4) != 4)
+                goto fail;
+
+            dprintf("chunk len [%#x] = %d\n", GZ_99_CHUNKSIZE, chunk_len32);
+            s->chunk_len = le32_to_cpu(chunk_len32);
+
+            /* chunk count */
+            if (bdrv_pread(s->hd, GZ_99_CHUNKCNT, &s->chunk_cnt, 4) != 4)
+                goto fail;
+
+            s->chunk_cnt = le32_to_cpu(s->chunk_cnt);
+
+            dprintf("chunk len | count = %"PRId64" | %d\n", s->chunk_len, s->chunk_cnt);
+
+            /* file size */
+            if (bdrv_pread(s->hd, GZ_99_FILESIZE, &s->file_len, 8) != 8)
+                goto fail;
+
+            s->file_len = le64_to_cpu(s->file_len);
+            chunks_len = sizeof(int) * s->chunk_cnt;
+            rnd_offs = GZ_99_RNDDATA;
+            break;
+        default:
+            err = "Invalid DictZip version";
+            goto fail;
+    }
+
+    /* random access data */
+    s->chunks = g_malloc(chunks_len);
+    if (header_ver == 99)
+        s->chunks32 = (uint32_t *)s->chunks;
+
+    if (bdrv_pread(s->hd, rnd_offs, s->chunks, chunks_len) != chunks_len)
+        goto fail;
+
+    /* orig filename */
+    if (header_flags & GZ_FNAME) {
+        if (bdrv_pread(s->hd, headerLength + 1, buf, sizeof(buf)) != sizeof(buf))
+            goto fail;
+
+        buf[sizeof(buf) - 1] = '\0';
+        headerLength += strlen(buf) + 1;
+
+        if (strlen(buf) == sizeof(buf))
+            goto fail;
+
+        dprintf("filename: %s\n", buf);
+    }
+
+    /* comment field */
+    if (header_flags & GZ_COMMENT) {
+        if (bdrv_pread(s->hd, headerLength, buf, sizeof(buf)) != sizeof(buf))
+            goto fail;
+
+        buf[sizeof(buf) - 1] = '\0';
+        headerLength += strlen(buf) + 1;
+
+        if (strlen(buf) == sizeof(buf))
+            goto fail;
+
+        dprintf("comment: %s\n", buf);
+    }
+
+    if (header_flags & GZ_FHCRC)
+        headerLength += 2;
+
+    /* uncompressed file length*/
+    if (!s->file_len) {
+        uint32_t file_len;
+
+        if (bdrv_pread(s->hd, bdrv_getlength(s->hd) - 4, &file_len, 4) != 4)
+            goto fail;
+
+        s->file_len = le32_to_cpu(file_len);
+    }
+
+    /* compute offsets */
+    s->offsets = g_malloc(sizeof( *s->offsets ) * s->chunk_cnt);
+
+    for (offset = headerLength + 1, i = 0; i < s->chunk_cnt; i++) {
+        s->offsets[i] = offset;
+        switch (header_ver) {
+        case 1:
+            offset += le16_to_cpu(s->chunks[i]);
+            break;
+        case 99:
+            offset += le32_to_cpu(s->chunks32[i]);
+            break;
+        }
+
+        dprintf("chunk %#"PRIx64" - %#"PRIx64" = offset %#"PRIx64" -> %#"PRIx64"\n", i * s->chunk_len, (i+1) * s->chunk_len, s->offsets[i], offset);
+    }
+    qemu_opts_del(opts);
+
+    return 0;
+
+fail:
+    fprintf(stderr, "DictZip: Error opening file: %s\n", err);
+    bdrv_unref(s->hd);
+    if (s->chunks)
+        g_free(s->chunks);
+    qemu_opts_del(opts);
+    return -EINVAL;
+}
+
+/* This callback gets invoked when we have the result in cache already */
+static void dictzip_cache_cb(void *opaque)
+{
+    DictZipAIOCB *acb = (DictZipAIOCB *)opaque;
+
+    qemu_iovec_from_buf(acb->qiov, 0, acb->buf, acb->len);
+    acb->common.cb(acb->common.opaque, 0);
+    qemu_bh_delete(acb->bh);
+    qemu_aio_unref(acb);
+}
+
+/* This callback gets invoked by the underlying block reader when we have
+ * all compressed data. We uncompress in here. */
+static void dictzip_read_cb(void *opaque, int ret)
+{
+    DictZipAIOCB *acb = (DictZipAIOCB *)opaque;
+    struct BDRVDictZipState *s = acb->s;
+    uint8_t *buf;
+    DictCache *cache;
+    int r, i;
+
+    buf = g_malloc(acb->chunks_len);
+
+    /* try to find zlib stream for decoding */
+    do {
+        for (i = 0; i < Z_STREAM_COUNT; i++) {
+            if (!(s->stream_in_use & (1 << i))) {
+                s->stream_in_use |= (1 << i);
+                acb->zStream_id = i;
+                acb->zStream = &s->zStream[i];
+                break;
+            }
+        }
+    } while(!acb->zStream);
+
+    /* sure, we could handle more streams, but this callback should be single
+       threaded and when it's not, we really want to know! */
+    assert(i == 0);
+
+    /* uncompress the chunk */
+    acb->zStream->next_in   = acb->gzipped;
+    acb->zStream->avail_in  = acb->gz_len;
+    acb->zStream->next_out  = buf;
+    acb->zStream->avail_out = acb->chunks_len;
+
+    r = inflate( acb->zStream,  Z_PARTIAL_FLUSH );
+    if ( (r != Z_OK) && (r != Z_STREAM_END) )
+        fprintf(stderr, "Error inflating: [%d] %s\n", r, acb->zStream->msg);
+
+    if ( r == Z_STREAM_END )
+        inflateReset(acb->zStream);
+
+    dprintf("inflating [%d] left: %d | %d bytes\n", r, acb->zStream->avail_in, acb->zStream->avail_out);
+    s->stream_in_use &= ~(1 << acb->zStream_id);
+
+    /* nofity the caller */
+    qemu_iovec_from_buf(acb->qiov, 0, buf + acb->offset, acb->len);
+    acb->common.cb(acb->common.opaque, 0);
+
+    /* fill the cache */
+    cache = &s->cache[s->cache_index];
+    s->cache_index++;
+    if (s->cache_index == CACHE_COUNT)
+        s->cache_index = 0;
+
+    cache->len = 0;
+    if (cache->buf)
+        g_free(cache->buf);
+    cache->start = acb->gz_start;
+    cache->buf = buf;
+    cache->len = acb->chunks_len;
+
+    /* free occupied ressources */
+    g_free(acb->qiov_gz);
+    qemu_aio_unref(acb);
+}
+
+static const AIOCBInfo dictzip_aiocb_info = {
+    .aiocb_size         = sizeof(DictZipAIOCB),
+};
+
+/* This is where we get a request from a caller to read something */
+static BlockAIOCB *dictzip_aio_readv(BlockDriverState *bs,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockCompletionFunc *cb, void *opaque)
+{
+    BDRVDictZipState *s = bs->opaque;
+    DictZipAIOCB *acb;
+    QEMUIOVector *qiov_gz;
+    struct iovec *iov;
+    uint8_t *buf;
+    size_t  start = sector_num * SECTOR_SIZE;
+    size_t  len = nb_sectors * SECTOR_SIZE;
+    size_t  end = start + len;
+    size_t  gz_start;
+    size_t  gz_len;
+    int64_t gz_sector_num;
+    int     gz_nb_sectors;
+    int     first_chunk, last_chunk;
+    int     first_offset;
+    int     i;
+
+    acb = qemu_aio_get(&dictzip_aiocb_info, bs, cb, opaque);
+    if (!acb)
+        return NULL;
+
+    /* Search Cache */
+    for (i = 0; i < CACHE_COUNT; i++) {
+        if (!s->cache[i].len)
+            continue;
+
+        if ((start >= s->cache[i].start) &&
+            (end <= (s->cache[i].start + s->cache[i].len))) {
+            acb->buf = s->cache[i].buf + (start - s->cache[i].start);
+            acb->len = len;
+            acb->qiov = qiov;
+            acb->bh = qemu_bh_new(dictzip_cache_cb, acb);
+            qemu_bh_schedule(acb->bh);
+
+            return &acb->common;
+        }
+    }
+
+    /* No cache, so let's decode */
+    /* We need to read these chunks */
+    first_chunk  = start / s->chunk_len;
+    first_offset = start - first_chunk * s->chunk_len;
+    last_chunk   = end / s->chunk_len;
+
+    gz_start = s->offsets[first_chunk];
+    gz_len = 0;
+    for (i = first_chunk; i <= last_chunk; i++) {
+        if (s->chunks32)
+            gz_len += le32_to_cpu(s->chunks32[i]);
+        else
+            gz_len += le16_to_cpu(s->chunks[i]);
+    }
+
+    gz_sector_num = gz_start / SECTOR_SIZE;
+    gz_nb_sectors = (gz_len / SECTOR_SIZE);
+
+    /* account for tail and heads */
+    while ((gz_start + gz_len) > ((gz_sector_num + gz_nb_sectors) * SECTOR_SIZE))
+        gz_nb_sectors++;
+
+    /* Allocate qiov, iov and buf in one chunk so we only need to free qiov */
+    qiov_gz = g_malloc0(sizeof(QEMUIOVector) + sizeof(struct iovec) +
+                           (gz_nb_sectors * SECTOR_SIZE));
+    iov = (struct iovec *)(((char *)qiov_gz) + sizeof(QEMUIOVector));
+    buf = ((uint8_t *)iov) + sizeof(struct iovec *);
+
+    /* Kick off the read by the backing file, so we can start decompressing */
+    iov->iov_base = (void *)buf;
+    iov->iov_len = gz_nb_sectors * 512;
+    qemu_iovec_init_external(qiov_gz, iov, 1);
+
+    dprintf("read %zd - %zd => %zd - %zd\n", start, end, gz_start, gz_start + gz_len);
+
+    acb->s = s;
+    acb->qiov = qiov;
+    acb->qiov_gz = qiov_gz;
+    acb->start = start;
+    acb->len = len;
+    acb->gzipped = buf + (gz_start % SECTOR_SIZE);
+    acb->gz_len = gz_len;
+    acb->gz_start = first_chunk * s->chunk_len;
+    acb->offset = first_offset;
+    acb->chunks_len = (last_chunk - first_chunk + 1) * s->chunk_len;
+
+    return bdrv_aio_readv(s->hd, gz_sector_num, qiov_gz, gz_nb_sectors,
+                          dictzip_read_cb, acb);
+}
+
+static void dictzip_close(BlockDriverState *bs)
+{
+    BDRVDictZipState *s = bs->opaque;
+    int i;
+
+    for (i = 0; i < CACHE_COUNT; i++) {
+        if (!s->cache[i].len)
+            continue;
+
+        g_free(s->cache[i].buf);
+    }
+
+    for (i = 0; i < Z_STREAM_COUNT; i++) {
+        inflateEnd(&s->zStream[i]);
+    }
+
+    if (s->chunks)
+        g_free(s->chunks);
+
+    if (s->offsets)
+        g_free(s->offsets);
+
+    dprintf("Close\n");
+}
+
+static int64_t dictzip_getlength(BlockDriverState *bs)
+{
+    BDRVDictZipState *s = bs->opaque;
+    dprintf("getlength -> %ld\n", s->file_len);
+    return s->file_len;
+}
+
+static BlockDriver bdrv_dictzip = {
+    .format_name     = "dzip",
+    .protocol_name   = "dzip",
+
+    .instance_size   = sizeof(BDRVDictZipState),
+    .bdrv_file_open  = dictzip_open,
+    .bdrv_close      = dictzip_close,
+    .bdrv_getlength  = dictzip_getlength,
+
+    .bdrv_aio_readv  = dictzip_aio_readv,
+};
+
+static void dictzip_block_init(void)
+{
+    bdrv_register(&bdrv_dictzip);
+}
+
+block_init(dictzip_block_init);

block/dirty-bitmap.c

@@ -1,629 +0,0 @@
-/*
- * Block Dirty Bitmap
- *
- * Copyright (c) 2016 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 "qemu/osdep.h"
-#include "qapi/error.h"
-#include "qemu-common.h"
-#include "trace.h"
-#include "block/block_int.h"
-#include "block/blockjob.h"
-
-/**
- * A BdrvDirtyBitmap can be in three possible states:
- * (1) successor is NULL and disabled is false: full r/w mode
- * (2) successor is NULL and disabled is true: read only mode ("disabled")
- * (3) successor is set: frozen mode.
- *     A frozen bitmap cannot be renamed, deleted, anonymized, cleared, set,
- *     or enabled. A frozen bitmap can only abdicate() or reclaim().
- */
-struct BdrvDirtyBitmap {
-    QemuMutex *mutex;
-    HBitmap *bitmap;            /* Dirty sector bitmap implementation */
-    HBitmap *meta;              /* Meta dirty bitmap */
-    BdrvDirtyBitmap *successor; /* Anonymous child; implies frozen status */
-    char *name;                 /* Optional non-empty unique ID */
-    int64_t size;               /* Size of the bitmap (Number of sectors) */
-    bool disabled;              /* Bitmap is read-only */
-    int active_iterators;       /* How many iterators are active */
-    QLIST_ENTRY(BdrvDirtyBitmap) list;
-};
-
-struct BdrvDirtyBitmapIter {
-    HBitmapIter hbi;
-    BdrvDirtyBitmap *bitmap;
-};
-
-static inline void bdrv_dirty_bitmaps_lock(BlockDriverState *bs)
-{
-    qemu_mutex_lock(&bs->dirty_bitmap_mutex);
-}
-
-static inline void bdrv_dirty_bitmaps_unlock(BlockDriverState *bs)
-{
-    qemu_mutex_unlock(&bs->dirty_bitmap_mutex);
-}
-
-void bdrv_dirty_bitmap_lock(BdrvDirtyBitmap *bitmap)
-{
-    qemu_mutex_lock(bitmap->mutex);
-}
-
-void bdrv_dirty_bitmap_unlock(BdrvDirtyBitmap *bitmap)
-{
-    qemu_mutex_unlock(bitmap->mutex);
-}
-
-/* Called with BQL or dirty_bitmap lock taken.  */
-BdrvDirtyBitmap *bdrv_find_dirty_bitmap(BlockDriverState *bs, const char *name)
-{
-    BdrvDirtyBitmap *bm;
-
-    assert(name);
-    QLIST_FOREACH(bm, &bs->dirty_bitmaps, list) {
-        if (bm->name && !strcmp(name, bm->name)) {
-            return bm;
-        }
-    }
-    return NULL;
-}
-
-/* Called with BQL taken.  */
-void bdrv_dirty_bitmap_make_anon(BdrvDirtyBitmap *bitmap)
-{
-    assert(!bdrv_dirty_bitmap_frozen(bitmap));
-    g_free(bitmap->name);
-    bitmap->name = NULL;
-}
-
-/* Called with BQL taken.  */
-BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs,
-                                          uint32_t granularity,
-                                          const char *name,
-                                          Error **errp)
-{
-    int64_t bitmap_size;
-    BdrvDirtyBitmap *bitmap;
-    uint32_t sector_granularity;
-
-    assert((granularity & (granularity - 1)) == 0);
-
-    if (name && bdrv_find_dirty_bitmap(bs, name)) {
-        error_setg(errp, "Bitmap already exists: %s", name);
-        return NULL;
-    }
-    sector_granularity = granularity >> BDRV_SECTOR_BITS;
-    assert(sector_granularity);
-    bitmap_size = bdrv_nb_sectors(bs);
-    if (bitmap_size < 0) {
-        error_setg_errno(errp, -bitmap_size, "could not get length of device");
-        errno = -bitmap_size;
-        return NULL;
-    }
-    bitmap = g_new0(BdrvDirtyBitmap, 1);
-    bitmap->mutex = &bs->dirty_bitmap_mutex;
-    bitmap->bitmap = hbitmap_alloc(bitmap_size, ctz32(sector_granularity));
-    bitmap->size = bitmap_size;
-    bitmap->name = g_strdup(name);
-    bitmap->disabled = false;
-    bdrv_dirty_bitmaps_lock(bs);
-    QLIST_INSERT_HEAD(&bs->dirty_bitmaps, bitmap, list);
-    bdrv_dirty_bitmaps_unlock(bs);
-    return bitmap;
-}
-
-/* bdrv_create_meta_dirty_bitmap
- *
- * Create a meta dirty bitmap that tracks the changes of bits in @bitmap. I.e.
- * when a dirty status bit in @bitmap is changed (either from reset to set or
- * the other way around), its respective meta dirty bitmap bit will be marked
- * dirty as well.
- *
- * @bitmap: the block dirty bitmap for which to create a meta dirty bitmap.
- * @chunk_size: how many bytes of bitmap data does each bit in the meta bitmap
- * track.
- */
-void bdrv_create_meta_dirty_bitmap(BdrvDirtyBitmap *bitmap,
-                                   int chunk_size)
-{
-    assert(!bitmap->meta);
-    qemu_mutex_lock(bitmap->mutex);
-    bitmap->meta = hbitmap_create_meta(bitmap->bitmap,
-                                       chunk_size * BITS_PER_BYTE);
-    qemu_mutex_unlock(bitmap->mutex);
-}
-
-void bdrv_release_meta_dirty_bitmap(BdrvDirtyBitmap *bitmap)
-{
-    assert(bitmap->meta);
-    qemu_mutex_lock(bitmap->mutex);
-    hbitmap_free_meta(bitmap->bitmap);
-    bitmap->meta = NULL;
-    qemu_mutex_unlock(bitmap->mutex);
-}
-
-int bdrv_dirty_bitmap_get_meta_locked(BlockDriverState *bs,
-                                      BdrvDirtyBitmap *bitmap, int64_t sector,
-                                      int nb_sectors)
-{
-    uint64_t i;
-    int sectors_per_bit = 1 << hbitmap_granularity(bitmap->meta);
-
-    /* To optimize: we can make hbitmap to internally check the range in a
-     * coarse level, or at least do it word by word. */
-    for (i = sector; i < sector + nb_sectors; i += sectors_per_bit) {
-        if (hbitmap_get(bitmap->meta, i)) {
-            return true;
-        }
-    }
-    return false;
-}
-
-int bdrv_dirty_bitmap_get_meta(BlockDriverState *bs,
-                               BdrvDirtyBitmap *bitmap, int64_t sector,
-                               int nb_sectors)
-{
-    bool dirty;
-
-    qemu_mutex_lock(bitmap->mutex);
-    dirty = bdrv_dirty_bitmap_get_meta_locked(bs, bitmap, sector, nb_sectors);
-    qemu_mutex_unlock(bitmap->mutex);
-
-    return dirty;
-}
-
-void bdrv_dirty_bitmap_reset_meta(BlockDriverState *bs,
-                                  BdrvDirtyBitmap *bitmap, int64_t sector,
-                                  int nb_sectors)
-{
-    qemu_mutex_lock(bitmap->mutex);
-    hbitmap_reset(bitmap->meta, sector, nb_sectors);
-    qemu_mutex_unlock(bitmap->mutex);
-}
-
-int64_t bdrv_dirty_bitmap_size(const BdrvDirtyBitmap *bitmap)
-{
-    return bitmap->size;
-}
-
-const char *bdrv_dirty_bitmap_name(const BdrvDirtyBitmap *bitmap)
-{
-    return bitmap->name;
-}
-
-/* Called with BQL taken.  */
-bool bdrv_dirty_bitmap_frozen(BdrvDirtyBitmap *bitmap)
-{
-    return bitmap->successor;
-}
-
-/* Called with BQL taken.  */
-bool bdrv_dirty_bitmap_enabled(BdrvDirtyBitmap *bitmap)
-{
-    return !(bitmap->disabled || bitmap->successor);
-}
-
-/* Called with BQL taken.  */
-DirtyBitmapStatus bdrv_dirty_bitmap_status(BdrvDirtyBitmap *bitmap)
-{
-    if (bdrv_dirty_bitmap_frozen(bitmap)) {
-        return DIRTY_BITMAP_STATUS_FROZEN;
-    } else if (!bdrv_dirty_bitmap_enabled(bitmap)) {
-        return DIRTY_BITMAP_STATUS_DISABLED;
-    } else {
-        return DIRTY_BITMAP_STATUS_ACTIVE;
-    }
-}
-
-/**
- * Create a successor bitmap destined to replace this bitmap after an operation.
- * Requires that the bitmap is not frozen and has no successor.
- * Called with BQL taken.
- */
-int bdrv_dirty_bitmap_create_successor(BlockDriverState *bs,
-                                       BdrvDirtyBitmap *bitmap, Error **errp)
-{
-    uint64_t granularity;
-    BdrvDirtyBitmap *child;
-
-    if (bdrv_dirty_bitmap_frozen(bitmap)) {
-        error_setg(errp, "Cannot create a successor for a bitmap that is "
-                   "currently frozen");
-        return -1;
-    }
-    assert(!bitmap->successor);
-
-    /* Create an anonymous successor */
-    granularity = bdrv_dirty_bitmap_granularity(bitmap);
-    child = bdrv_create_dirty_bitmap(bs, granularity, NULL, errp);
-    if (!child) {
-        return -1;
-    }
-
-    /* Successor will be on or off based on our current state. */
-    child->disabled = bitmap->disabled;
-
-    /* Install the successor and freeze the parent */
-    bitmap->successor = child;
-    return 0;
-}
-
-/**
- * For a bitmap with a successor, yield our name to the successor,
- * delete the old bitmap, and return a handle to the new bitmap.
- * Called with BQL taken.
- */
-BdrvDirtyBitmap *bdrv_dirty_bitmap_abdicate(BlockDriverState *bs,
-                                            BdrvDirtyBitmap *bitmap,
-                                            Error **errp)
-{
-    char *name;
-    BdrvDirtyBitmap *successor = bitmap->successor;
-
-    if (successor == NULL) {
-        error_setg(errp, "Cannot relinquish control if "
-                   "there's no successor present");
-        return NULL;
-    }
-
-    name = bitmap->name;
-    bitmap->name = NULL;
-    successor->name = name;
-    bitmap->successor = NULL;
-    bdrv_release_dirty_bitmap(bs, bitmap);
-
-    return successor;
-}
-
-/**
- * In cases of failure where we can no longer safely delete the parent,
- * we may wish to re-join the parent and child/successor.
- * The merged parent will be un-frozen, but not explicitly re-enabled.
- * Called with BQL taken.
- */
-BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap(BlockDriverState *bs,
-                                           BdrvDirtyBitmap *parent,
-                                           Error **errp)
-{
-    BdrvDirtyBitmap *successor = parent->successor;
-
-    if (!successor) {
-        error_setg(errp, "Cannot reclaim a successor when none is present");
-        return NULL;
-    }
-
-    if (!hbitmap_merge(parent->bitmap, successor->bitmap)) {
-        error_setg(errp, "Merging of parent and successor bitmap failed");
-        return NULL;
-    }
-    bdrv_release_dirty_bitmap(bs, successor);
-    parent->successor = NULL;
-
-    return parent;
-}
-
-/**
- * Truncates _all_ bitmaps attached to a BDS.
- * Called with BQL taken.
- */
-void bdrv_dirty_bitmap_truncate(BlockDriverState *bs)
-{
-    BdrvDirtyBitmap *bitmap;
-    uint64_t size = bdrv_nb_sectors(bs);
-
-    bdrv_dirty_bitmaps_lock(bs);
-    QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) {
-        assert(!bdrv_dirty_bitmap_frozen(bitmap));
-        assert(!bitmap->active_iterators);
-        hbitmap_truncate(bitmap->bitmap, size);
-        bitmap->size = size;
-    }
-    bdrv_dirty_bitmaps_unlock(bs);
-}
-
-/* Called with BQL taken.  */
-static void bdrv_do_release_matching_dirty_bitmap(BlockDriverState *bs,
-                                                  BdrvDirtyBitmap *bitmap,
-                                                  bool only_named)
-{
-    BdrvDirtyBitmap *bm, *next;
-    bdrv_dirty_bitmaps_lock(bs);
-    QLIST_FOREACH_SAFE(bm, &bs->dirty_bitmaps, list, next) {
-        if ((!bitmap || bm == bitmap) && (!only_named || bm->name)) {
-            assert(!bm->active_iterators);
-            assert(!bdrv_dirty_bitmap_frozen(bm));
-            assert(!bm->meta);
-            QLIST_REMOVE(bm, list);
-            hbitmap_free(bm->bitmap);
-            g_free(bm->name);
-            g_free(bm);
-
-            if (bitmap) {
-                goto out;
-            }
-        }
-    }
-    if (bitmap) {
-        abort();
-    }
-
-out:
-    bdrv_dirty_bitmaps_unlock(bs);
-}
-
-/* Called with BQL taken.  */
-void bdrv_release_dirty_bitmap(BlockDriverState *bs, BdrvDirtyBitmap *bitmap)
-{
-    bdrv_do_release_matching_dirty_bitmap(bs, bitmap, false);
-}
-
-/**
- * Release all named dirty bitmaps attached to a BDS (for use in bdrv_close()).
- * There must not be any frozen bitmaps attached.
- * Called with BQL taken.
- */
-void bdrv_release_named_dirty_bitmaps(BlockDriverState *bs)
-{
-    bdrv_do_release_matching_dirty_bitmap(bs, NULL, true);
-}
-
-/* Called with BQL taken.  */
-void bdrv_disable_dirty_bitmap(BdrvDirtyBitmap *bitmap)
-{
-    assert(!bdrv_dirty_bitmap_frozen(bitmap));
-    bitmap->disabled = true;
-}
-
-/* Called with BQL taken.  */
-void bdrv_enable_dirty_bitmap(BdrvDirtyBitmap *bitmap)
-{
-    assert(!bdrv_dirty_bitmap_frozen(bitmap));
-    bitmap->disabled = false;
-}
-
-BlockDirtyInfoList *bdrv_query_dirty_bitmaps(BlockDriverState *bs)
-{
-    BdrvDirtyBitmap *bm;
-    BlockDirtyInfoList *list = NULL;
-    BlockDirtyInfoList **plist = &list;
-
-    bdrv_dirty_bitmaps_lock(bs);
-    QLIST_FOREACH(bm, &bs->dirty_bitmaps, list) {
-        BlockDirtyInfo *info = g_new0(BlockDirtyInfo, 1);
-        BlockDirtyInfoList *entry = g_new0(BlockDirtyInfoList, 1);
-        info->count = bdrv_get_dirty_count(bm);
-        info->granularity = bdrv_dirty_bitmap_granularity(bm);
-        info->has_name = !!bm->name;
-        info->name = g_strdup(bm->name);
-        info->status = bdrv_dirty_bitmap_status(bm);
-        entry->value = info;
-        *plist = entry;
-        plist = &entry->next;
-    }
-    bdrv_dirty_bitmaps_unlock(bs);
-
-    return list;
-}
-
-/* Called within bdrv_dirty_bitmap_lock..unlock */
-int bdrv_get_dirty_locked(BlockDriverState *bs, BdrvDirtyBitmap *bitmap,
-                          int64_t sector)
-{
-    if (bitmap) {
-        return hbitmap_get(bitmap->bitmap, sector);
-    } else {
-        return 0;
-    }
-}
-
-/**
- * Chooses a default granularity based on the existing cluster size,
- * but clamped between [4K, 64K]. Defaults to 64K in the case that there
- * is no cluster size information available.
- */
-uint32_t bdrv_get_default_bitmap_granularity(BlockDriverState *bs)
-{
-    BlockDriverInfo bdi;
-    uint32_t granularity;
-
-    if (bdrv_get_info(bs, &bdi) >= 0 && bdi.cluster_size > 0) {
-        granularity = MAX(4096, bdi.cluster_size);
-        granularity = MIN(65536, granularity);
-    } else {
-        granularity = 65536;
-    }
-
-    return granularity;
-}
-
-uint32_t bdrv_dirty_bitmap_granularity(BdrvDirtyBitmap *bitmap)
-{
-    return BDRV_SECTOR_SIZE << hbitmap_granularity(bitmap->bitmap);
-}
-
-uint32_t bdrv_dirty_bitmap_meta_granularity(BdrvDirtyBitmap *bitmap)
-{
-    return BDRV_SECTOR_SIZE << hbitmap_granularity(bitmap->meta);
-}
-
-BdrvDirtyBitmapIter *bdrv_dirty_iter_new(BdrvDirtyBitmap *bitmap,
-                                         uint64_t first_sector)
-{
-    BdrvDirtyBitmapIter *iter = g_new(BdrvDirtyBitmapIter, 1);
-    hbitmap_iter_init(&iter->hbi, bitmap->bitmap, first_sector);
-    iter->bitmap = bitmap;
-    bitmap->active_iterators++;
-    return iter;
-}
-
-BdrvDirtyBitmapIter *bdrv_dirty_meta_iter_new(BdrvDirtyBitmap *bitmap)
-{
-    BdrvDirtyBitmapIter *iter = g_new(BdrvDirtyBitmapIter, 1);
-    hbitmap_iter_init(&iter->hbi, bitmap->meta, 0);
-    iter->bitmap = bitmap;
-    bitmap->active_iterators++;
-    return iter;
-}
-
-void bdrv_dirty_iter_free(BdrvDirtyBitmapIter *iter)
-{
-    if (!iter) {
-        return;
-    }
-    assert(iter->bitmap->active_iterators > 0);
-    iter->bitmap->active_iterators--;
-    g_free(iter);
-}
-
-int64_t bdrv_dirty_iter_next(BdrvDirtyBitmapIter *iter)
-{
-    return hbitmap_iter_next(&iter->hbi);
-}
-
-/* Called within bdrv_dirty_bitmap_lock..unlock */
-void bdrv_set_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap,
-                                  int64_t cur_sector, int64_t nr_sectors)
-{
-    assert(bdrv_dirty_bitmap_enabled(bitmap));
-    hbitmap_set(bitmap->bitmap, cur_sector, nr_sectors);
-}
-
-void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap,
-                           int64_t cur_sector, int64_t nr_sectors)
-{
-    bdrv_dirty_bitmap_lock(bitmap);
-    bdrv_set_dirty_bitmap_locked(bitmap, cur_sector, nr_sectors);
-    bdrv_dirty_bitmap_unlock(bitmap);
-}
-
-/* Called within bdrv_dirty_bitmap_lock..unlock */
-void bdrv_reset_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap,
-                                    int64_t cur_sector, int64_t nr_sectors)
-{
-    assert(bdrv_dirty_bitmap_enabled(bitmap));
-    hbitmap_reset(bitmap->bitmap, cur_sector, nr_sectors);
-}
-
-void bdrv_reset_dirty_bitmap(BdrvDirtyBitmap *bitmap,
-                             int64_t cur_sector, int64_t nr_sectors)
-{
-    bdrv_dirty_bitmap_lock(bitmap);
-    bdrv_reset_dirty_bitmap_locked(bitmap, cur_sector, nr_sectors);
-    bdrv_dirty_bitmap_unlock(bitmap);
-}
-
-void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out)
-{
-    assert(bdrv_dirty_bitmap_enabled(bitmap));
-    bdrv_dirty_bitmap_lock(bitmap);
-    if (!out) {
-        hbitmap_reset_all(bitmap->bitmap);
-    } else {
-        HBitmap *backup = bitmap->bitmap;
-        bitmap->bitmap = hbitmap_alloc(bitmap->size,
-                                       hbitmap_granularity(backup));
-        *out = backup;
-    }
-    bdrv_dirty_bitmap_unlock(bitmap);
-}
-
-void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in)
-{
-    HBitmap *tmp = bitmap->bitmap;
-    assert(bdrv_dirty_bitmap_enabled(bitmap));
-    bitmap->bitmap = in;
-    hbitmap_free(tmp);
-}
-
-uint64_t bdrv_dirty_bitmap_serialization_size(const BdrvDirtyBitmap *bitmap,
-                                              uint64_t start, uint64_t count)
-{
-    return hbitmap_serialization_size(bitmap->bitmap, start, count);
-}
-
-uint64_t bdrv_dirty_bitmap_serialization_align(const BdrvDirtyBitmap *bitmap)
-{
-    return hbitmap_serialization_granularity(bitmap->bitmap);
-}
-
-void bdrv_dirty_bitmap_serialize_part(const BdrvDirtyBitmap *bitmap,
-                                      uint8_t *buf, uint64_t start,
-                                      uint64_t count)
-{
-    hbitmap_serialize_part(bitmap->bitmap, buf, start, count);
-}
-
-void bdrv_dirty_bitmap_deserialize_part(BdrvDirtyBitmap *bitmap,
-                                        uint8_t *buf, uint64_t start,
-                                        uint64_t count, bool finish)
-{
-    hbitmap_deserialize_part(bitmap->bitmap, buf, start, count, finish);
-}
-
-void bdrv_dirty_bitmap_deserialize_zeroes(BdrvDirtyBitmap *bitmap,
-                                          uint64_t start, uint64_t count,
-                                          bool finish)
-{
-    hbitmap_deserialize_zeroes(bitmap->bitmap, start, count, finish);
-}
-
-void bdrv_dirty_bitmap_deserialize_finish(BdrvDirtyBitmap *bitmap)
-{
-    hbitmap_deserialize_finish(bitmap->bitmap);
-}
-
-void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector,
-                    int64_t nr_sectors)
-{
-    BdrvDirtyBitmap *bitmap;
-
-    if (QLIST_EMPTY(&bs->dirty_bitmaps)) {
-        return;
-    }
-
-    bdrv_dirty_bitmaps_lock(bs);
-    QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) {
-        if (!bdrv_dirty_bitmap_enabled(bitmap)) {
-            continue;
-        }
-        hbitmap_set(bitmap->bitmap, cur_sector, nr_sectors);
-    }
-    bdrv_dirty_bitmaps_unlock(bs);
-}
-
-/**
- * Advance a BdrvDirtyBitmapIter to an arbitrary offset.
- */
-void bdrv_set_dirty_iter(BdrvDirtyBitmapIter *iter, int64_t sector_num)
-{
-    hbitmap_iter_init(&iter->hbi, iter->hbi.hb, sector_num);
-}
-
-int64_t bdrv_get_dirty_count(BdrvDirtyBitmap *bitmap)
-{
-    return hbitmap_count(bitmap->bitmap);
-}
-
-int64_t bdrv_get_meta_dirty_count(BdrvDirtyBitmap *bitmap)
-{
-    return hbitmap_count(bitmap->meta);
-}

block/dmg-bz2.c

@@ -1,61 +0,0 @@
-/*
- * DMG bzip2 uncompression
- *
- * Copyright (c) 2004 Johannes E. Schindelin
- * Copyright (c) 2016 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 "qemu/osdep.h"
-#include "qemu-common.h"
-#include "dmg.h"
-#include <bzlib.h>
-
-static int dmg_uncompress_bz2_do(char *next_in, unsigned int avail_in,
-                                 char *next_out, unsigned int avail_out)
-{
-    int ret;
-    uint64_t total_out;
-    bz_stream bzstream = {};
-
-    ret = BZ2_bzDecompressInit(&bzstream, 0, 0);
-    if (ret != BZ_OK) {
-        return -1;
-    }
-    bzstream.next_in = next_in;
-    bzstream.avail_in = avail_in;
-    bzstream.next_out = next_out;
-    bzstream.avail_out = avail_out;
-    ret = BZ2_bzDecompress(&bzstream);
-    total_out = ((uint64_t)bzstream.total_out_hi32 << 32) +
-                bzstream.total_out_lo32;
-    BZ2_bzDecompressEnd(&bzstream);
-    if (ret != BZ_STREAM_END ||
-        total_out != avail_out) {
-        return -1;
-    }
-    return 0;
-}
-
-__attribute__((constructor))
-static void dmg_bz2_init(void)
-{
-    assert(!dmg_uncompress_bz2);
-    dmg_uncompress_bz2 = dmg_uncompress_bz2_do;
-}

block/dmg.c

@@ -21,17 +21,16 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
-#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "qemu/bswap.h"
 #include "qemu/error-report.h"
 #include "qemu/module.h"
-#include "dmg.h"
-
-int (*dmg_uncompress_bz2)(char *next_in, unsigned int avail_in,
-                          char *next_out, unsigned int avail_out);
+#include <zlib.h>
+#ifdef CONFIG_BZIP2
+#include <bzlib.h>
+#endif
+#include <glib.h>
 
 enum {
     /* Limit chunk sizes to prevent unreasonable amounts of memory being used
@@ -41,6 +40,31 @@ enum {
     DMG_SECTORCOUNTS_MAX = DMG_LENGTHS_MAX / 512,
 };
 
+typedef struct BDRVDMGState {
+    CoMutex lock;
+    /* each chunk contains a certain number of sectors,
+     * offsets[i] is the offset in the .dmg file,
+     * lengths[i] is the length of the compressed chunk,
+     * sectors[i] is the sector beginning at offsets[i],
+     * sectorcounts[i] is the number of sectors in that chunk,
+     * the sectors array is ordered
+     * 0<=i<n_chunks */
+
+    uint32_t n_chunks;
+    uint32_t* types;
+    uint64_t* offsets;
+    uint64_t* lengths;
+    uint64_t* sectors;
+    uint64_t* sectorcounts;
+    uint32_t current_chunk;
+    uint8_t *compressed_chunk;
+    uint8_t *uncompressed_chunk;
+    z_stream zstream;
+#ifdef CONFIG_BZIP2
+    bz_stream bzstream;
+#endif
+} BDRVDMGState;
+
 static int dmg_probe(const uint8_t *buf, int buf_size, const char *filename)
 {
     int len;
@@ -61,7 +85,7 @@ static int read_uint64(BlockDriverState *bs, int64_t offset, uint64_t *result)
     uint64_t buffer;
     int ret;
 
-    ret = bdrv_pread(bs->file, offset, &buffer, 8);
+    ret = bdrv_pread(bs->file->bs, offset, &buffer, 8);
     if (ret < 0) {
         return ret;
     }
@@ -75,7 +99,7 @@ static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result)
     uint32_t buffer;
     int ret;
 
-    ret = bdrv_pread(bs->file, offset, &buffer, 4);
+    ret = bdrv_pread(bs->file->bs, offset, &buffer, 4);
     if (ret < 0) {
         return ret;
     }
@@ -128,9 +152,8 @@ static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,
     }
 }
 
-static int64_t dmg_find_koly_offset(BdrvChild *file, Error **errp)
+static int64_t dmg_find_koly_offset(BlockDriverState *file_bs, Error **errp)
 {
-    BlockDriverState *file_bs = file->bs;
     int64_t length;
     int64_t offset = 0;
     uint8_t buffer[515];
@@ -154,7 +177,7 @@ static int64_t dmg_find_koly_offset(BdrvChild *file, Error **errp)
         offset = length - 511 - 512;
     }
     length = length < 515 ? length : 515;
-    ret = bdrv_pread(file, offset, buffer, length);
+    ret = bdrv_pread(file_bs, offset, buffer, length);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Failed while reading UDIF trailer");
         return ret;
@@ -185,9 +208,10 @@ static bool dmg_is_known_block_type(uint32_t entry_type)
     case 0x00000001:    /* uncompressed */
     case 0x00000002:    /* zeroes */
     case 0x80000005:    /* zlib */
-        return true;
+#ifdef CONFIG_BZIP2
     case 0x80000006:    /* bzip2 */
-        return !!dmg_uncompress_bz2;
+#endif
+        return true;
     default:
         return false;
     }
@@ -330,7 +354,7 @@ static int dmg_read_resource_fork(BlockDriverState *bs, DmgHeaderState *ds,
         offset += 4;
 
         buffer = g_realloc(buffer, count);
-        ret = bdrv_pread(bs->file, offset, buffer, count);
+        ret = bdrv_pread(bs->file->bs, offset, buffer, count);
         if (ret < 0) {
             goto fail;
         }
@@ -367,7 +391,7 @@ static int dmg_read_plist_xml(BlockDriverState *bs, DmgHeaderState *ds,
 
     buffer = g_malloc(info_length + 1);
     buffer[info_length] = '\0';
-    ret = bdrv_pread(bs->file, info_begin, buffer, info_length);
+    ret = bdrv_pread(bs->file->bs, info_begin, buffer, info_length);
     if (ret != info_length) {
         ret = -EINVAL;
         goto fail;
@@ -413,19 +437,7 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
     int64_t offset;
     int ret;
 
-    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
-                               false, errp);
-    if (!bs->file) {
-        return -EINVAL;
-    }
-
-    ret = bdrv_set_read_only(bs, true, errp);
-    if (ret < 0) {
-        return ret;
-    }
-
-    block_module_load_one("dmg-bz2");
-
+    bs->read_only = 1;
     s->n_chunks = 0;
     s->offsets = s->lengths = s->sectors = s->sectorcounts = NULL;
     /* used by dmg_read_mish_block to keep track of the current I/O position */
@@ -434,7 +446,7 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
     ds.max_sectors_per_chunk = 1;
 
     /* locate the UDIF trailer */
-    offset = dmg_find_koly_offset(bs->file, errp);
+    offset = dmg_find_koly_offset(bs->file->bs, errp);
     if (offset < 0) {
         ret = offset;
         goto fail;
@@ -532,11 +544,6 @@ fail:
     return ret;
 }
 
-static void dmg_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    bs->bl.request_alignment = BDRV_SECTOR_SIZE; /* No sub-sector I/O */
-}
-
 static inline int is_sector_in_chunk(BDRVDMGState* s,
                 uint32_t chunk_num, uint64_t sector_num)
 {
@@ -572,6 +579,9 @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
     if (!is_sector_in_chunk(s, s->current_chunk, sector_num)) {
         int ret;
         uint32_t chunk = search_chunk(s, sector_num);
+#ifdef CONFIG_BZIP2
+        uint64_t total_out;
+#endif
 
         if (chunk >= s->n_chunks) {
             return -1;
@@ -582,7 +592,7 @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
         case 0x80000005: { /* zlib compressed */
             /* we need to buffer, because only the chunk as whole can be
              * inflated. */
-            ret = bdrv_pread(bs->file, s->offsets[chunk],
+            ret = bdrv_pread(bs->file->bs, s->offsets[chunk],
                              s->compressed_chunk, s->lengths[chunk]);
             if (ret != s->lengths[chunk]) {
                 return -1;
@@ -602,29 +612,36 @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
                 return -1;
             }
             break; }
+#ifdef CONFIG_BZIP2
         case 0x80000006: /* bzip2 compressed */
-            if (!dmg_uncompress_bz2) {
-                break;
-            }
             /* we need to buffer, because only the chunk as whole can be
              * inflated. */
-            ret = bdrv_pread(bs->file, s->offsets[chunk],
+            ret = bdrv_pread(bs->file->bs, s->offsets[chunk],
                              s->compressed_chunk, s->lengths[chunk]);
             if (ret != s->lengths[chunk]) {
                 return -1;
             }
 
-            ret = dmg_uncompress_bz2((char *)s->compressed_chunk,
-                                     (unsigned int) s->lengths[chunk],
-                                     (char *)s->uncompressed_chunk,
-                                     (unsigned int)
-                                         (512 * s->sectorcounts[chunk]));
-            if (ret < 0) {
-                return ret;
+            ret = BZ2_bzDecompressInit(&s->bzstream, 0, 0);
+            if (ret != BZ_OK) {
+                return -1;
+            }
+            s->bzstream.next_in = (char *)s->compressed_chunk;
+            s->bzstream.avail_in = (unsigned int) s->lengths[chunk];
+            s->bzstream.next_out = (char *)s->uncompressed_chunk;
+            s->bzstream.avail_out = (unsigned int) 512 * s->sectorcounts[chunk];
+            ret = BZ2_bzDecompress(&s->bzstream);
+            total_out = ((uint64_t)s->bzstream.total_out_hi32 << 32) +
+                        s->bzstream.total_out_lo32;
+            BZ2_bzDecompressEnd(&s->bzstream);
+            if (ret != BZ_STREAM_END ||
+                total_out != 512 * s->sectorcounts[chunk]) {
+                return -1;
             }
             break;
+#endif /* CONFIG_BZIP2 */
         case 1: /* copy */
-            ret = bdrv_pread(bs->file, s->offsets[chunk],
+            ret = bdrv_pread(bs->file->bs, s->offsets[chunk],
                              s->uncompressed_chunk, s->lengths[chunk]);
             if (ret != s->lengths[chunk]) {
                 return -1;
@@ -640,42 +657,38 @@ static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
     return 0;
 }
 
-static int coroutine_fn
-dmg_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
-              QEMUIOVector *qiov, int flags)
+static int dmg_read(BlockDriverState *bs, int64_t sector_num,
+                    uint8_t *buf, int nb_sectors)
 {
     BDRVDMGState *s = bs->opaque;
-    uint64_t sector_num = offset >> BDRV_SECTOR_BITS;
-    int nb_sectors = bytes >> BDRV_SECTOR_BITS;
-    int ret, i;
-
-    assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
-    assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
-
-    qemu_co_mutex_lock(&s->lock);
+    int i;
 
     for (i = 0; i < nb_sectors; i++) {
         uint32_t sector_offset_in_chunk;
-        void *data;
-
         if (dmg_read_chunk(bs, sector_num + i) != 0) {
-            ret = -EIO;
-            goto fail;
+            return -1;
         }
         /* Special case: current chunk is all zeroes. Do not perform a memcpy as
          * s->uncompressed_chunk may be too small to cover the large all-zeroes
          * section. dmg_read_chunk is called to find s->current_chunk */
         if (s->types[s->current_chunk] == 2) { /* all zeroes block entry */
-            qemu_iovec_memset(qiov, i * 512, 0, 512);
+            memset(buf + i * 512, 0, 512);
             continue;
         }
         sector_offset_in_chunk = sector_num + i - s->sectors[s->current_chunk];
-        data = s->uncompressed_chunk + sector_offset_in_chunk * 512;
-        qemu_iovec_from_buf(qiov, i * 512, data, 512);
+        memcpy(buf + i * 512,
+               s->uncompressed_chunk + sector_offset_in_chunk * 512, 512);
     }
+    return 0;
+}
 
-    ret = 0;
-fail:
+static coroutine_fn int dmg_co_read(BlockDriverState *bs, int64_t sector_num,
+                                    uint8_t *buf, int nb_sectors)
+{
+    int ret;
+    BDRVDMGState *s = bs->opaque;
+    qemu_co_mutex_lock(&s->lock);
+    ret = dmg_read(bs, sector_num, buf, nb_sectors);
     qemu_co_mutex_unlock(&s->lock);
     return ret;
 }
@@ -700,9 +713,7 @@ static BlockDriver bdrv_dmg = {
     .instance_size  = sizeof(BDRVDMGState),
     .bdrv_probe     = dmg_probe,
     .bdrv_open      = dmg_open,
-    .bdrv_refresh_limits = dmg_refresh_limits,
-    .bdrv_child_perm     = bdrv_format_default_perms,
-    .bdrv_co_preadv = dmg_co_preadv,
+    .bdrv_read      = dmg_co_read,
     .bdrv_close     = dmg_close,
 };
 

block/dmg.h

@@ -1,59 +0,0 @@
-/*
- * Header for DMG driver
- *
- * Copyright (c) 2004-2006 Fabrice Bellard
- * Copyright (c) 2016 Red hat, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
- */
-
-#ifndef BLOCK_DMG_H
-#define BLOCK_DMG_H
-
-#include "qemu/osdep.h"
-#include "qemu-common.h"
-#include "block/block_int.h"
-#include <zlib.h>
-
-typedef struct BDRVDMGState {
-    CoMutex lock;
-    /* each chunk contains a certain number of sectors,
-     * offsets[i] is the offset in the .dmg file,
-     * lengths[i] is the length of the compressed chunk,
-     * sectors[i] is the sector beginning at offsets[i],
-     * sectorcounts[i] is the number of sectors in that chunk,
-     * the sectors array is ordered
-     * 0<=i<n_chunks */
-
-    uint32_t n_chunks;
-    uint32_t *types;
-    uint64_t *offsets;
-    uint64_t *lengths;
-    uint64_t *sectors;
-    uint64_t *sectorcounts;
-    uint32_t current_chunk;
-    uint8_t *compressed_chunk;
-    uint8_t *uncompressed_chunk;
-    z_stream zstream;
-} BDRVDMGState;
-
-extern int (*dmg_uncompress_bz2)(char *next_in, unsigned int avail_in,
-                                 char *next_out, unsigned int avail_out);
-
-#endif

block/iscsi-opts.c

@@ -1,69 +0,0 @@
-/*
- * QEMU Block driver for iSCSI images (static options)
- *
- * Copyright (c) 2017 Peter Lieven <pl@kamp.de>
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this software and associated documentation files (the "Software"), to deal
- * in the Software without restriction, including without limitation the rights
- * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
- * copies of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
- * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
- * THE SOFTWARE.
- */
-
-#include "qemu/osdep.h"
-#include "qemu-common.h"
-#include "qemu/config-file.h"
-
-static QemuOptsList qemu_iscsi_opts = {
-    .name = "iscsi",
-    .head = QTAILQ_HEAD_INITIALIZER(qemu_iscsi_opts.head),
-    .desc = {
-        {
-            .name = "user",
-            .type = QEMU_OPT_STRING,
-            .help = "username for CHAP authentication to target",
-        },{
-            .name = "password",
-            .type = QEMU_OPT_STRING,
-            .help = "password for CHAP authentication to target",
-        },{
-            .name = "password-secret",
-            .type = QEMU_OPT_STRING,
-            .help = "ID of the secret providing password for CHAP "
-                    "authentication to target",
-        },{
-            .name = "header-digest",
-            .type = QEMU_OPT_STRING,
-            .help = "HeaderDigest setting. "
-                    "{CRC32C|CRC32C-NONE|NONE-CRC32C|NONE}",
-        },{
-            .name = "initiator-name",
-            .type = QEMU_OPT_STRING,
-            .help = "Initiator iqn name to use when connecting",
-        },{
-            .name = "timeout",
-            .type = QEMU_OPT_NUMBER,
-            .help = "Request timeout in seconds (default 0 = no timeout)",
-        },
-        { /* end of list */ }
-    },
-};
-
-static void iscsi_block_opts_init(void)
-{
-    qemu_add_opts(&qemu_iscsi_opts);
-}
-
-block_init(iscsi_block_opts_init);

block/linux-aio.c

@@ -7,14 +7,11 @@
  * 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/osdep.h"
 #include "qemu-common.h"
 #include "block/aio.h"
 #include "qemu/queue.h"
-#include "block/block.h"
 #include "block/raw-aio.h"
 #include "qemu/event_notifier.h"
-#include "qemu/coroutine.h"
 
 #include <libaio.h>
 
@@ -28,10 +25,11 @@
  */
 #define MAX_EVENTS 128
 
+#define MAX_QUEUED_IO  128
+
 struct qemu_laiocb {
     BlockAIOCB common;
-    Coroutine *co;
-    LinuxAioState *ctx;
+    struct qemu_laio_state *ctx;
     struct iocb iocb;
     ssize_t ret;
     size_t nbytes;
@@ -42,28 +40,26 @@ struct qemu_laiocb {
 
 typedef struct {
     int plugged;
-    unsigned int in_queue;
-    unsigned int in_flight;
+    unsigned int n;
     bool blocked;
     QSIMPLEQ_HEAD(, qemu_laiocb) pending;
 } LaioQueue;
 
-struct LinuxAioState {
-    AioContext *aio_context;
-
+struct qemu_laio_state {
     io_context_t ctx;
     EventNotifier e;
 
-    /* io queue for submit at batch.  Protected by AioContext lock. */
+    /* io queue for submit at batch */
     LaioQueue io_q;
 
-    /* I/O completion processing.  Only runs in I/O thread.  */
+    /* I/O completion processing */
     QEMUBH *completion_bh;
+    struct io_event events[MAX_EVENTS];
     int event_idx;
     int event_max;
 };
 
-static void ioq_submit(LinuxAioState *s);
+static void ioq_submit(struct qemu_laio_state *s);
 
 static inline ssize_t io_event_ret(struct io_event *ev)
 {
@@ -73,7 +69,8 @@ static inline ssize_t io_event_ret(struct io_event *ev)
 /*
  * Completes an AIO request (calls the callback and frees the ACB).
  */
-static void qemu_laio_process_completion(struct qemu_laiocb *laiocb)
+static void qemu_laio_process_completion(struct qemu_laio_state *s,
+    struct qemu_laiocb *laiocb)
 {
     int ret;
 
@@ -87,191 +84,74 @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb)
                 qemu_iovec_memset(laiocb->qiov, ret, 0,
                     laiocb->qiov->size - ret);
             } else {
-                ret = -ENOSPC;
+                ret = -EINVAL;
             }
         }
     }
+    laiocb->common.cb(laiocb->common.opaque, ret);
 
-    laiocb->ret = ret;
-    if (laiocb->co) {
-        /* If the coroutine is already entered it must be in ioq_submit() and
-         * will notice laio->ret has been filled in when it eventually runs
-         * later.  Coroutines cannot be entered recursively so avoid doing
-         * that!
-         */
-        if (!qemu_coroutine_entered(laiocb->co)) {
-            aio_co_wake(laiocb->co);
-        }
-    } else {
-        laiocb->common.cb(laiocb->common.opaque, ret);
-        qemu_aio_unref(laiocb);
-    }
+    qemu_aio_unref(laiocb);
 }
 
-/**
- * aio_ring buffer which is shared between userspace and kernel.
- *
- * This copied from linux/fs/aio.c, common header does not exist
- * but AIO exists for ages so we assume ABI is stable.
- */
-struct aio_ring {
-    unsigned    id;    /* kernel internal index number */
-    unsigned    nr;    /* number of io_events */
-    unsigned    head;  /* Written to by userland or by kernel. */
-    unsigned    tail;
-
-    unsigned    magic;
-    unsigned    compat_features;
-    unsigned    incompat_features;
-    unsigned    header_length;  /* size of aio_ring */
-
-    struct io_event io_events[0];
-};
-
-/**
- * io_getevents_peek:
- * @ctx: AIO context
- * @events: pointer on events array, output value
-
- * Returns the number of completed events and sets a pointer
- * on events array.  This function does not update the internal
- * ring buffer, only reads head and tail.  When @events has been
- * processed io_getevents_commit() must be called.
- */
-static inline unsigned int io_getevents_peek(io_context_t ctx,
-                                             struct io_event **events)
-{
-    struct aio_ring *ring = (struct aio_ring *)ctx;
-    unsigned int head = ring->head, tail = ring->tail;
-    unsigned int nr;
-
-    nr = tail >= head ? tail - head : ring->nr - head;
-    *events = ring->io_events + head;
-    /* To avoid speculative loads of s->events[i] before observing tail.
-       Paired with smp_wmb() inside linux/fs/aio.c: aio_complete(). */
-    smp_rmb();
-
-    return nr;
-}
-
-/**
- * io_getevents_commit:
- * @ctx: AIO context
- * @nr: the number of events on which head should be advanced
- *
- * Advances head of a ring buffer.
- */
-static inline void io_getevents_commit(io_context_t ctx, unsigned int nr)
-{
-    struct aio_ring *ring = (struct aio_ring *)ctx;
-
-    if (nr) {
-        ring->head = (ring->head + nr) % ring->nr;
-    }
-}
-
-/**
- * io_getevents_advance_and_peek:
- * @ctx: AIO context
- * @events: pointer on events array, output value
- * @nr: the number of events on which head should be advanced
- *
- * Advances head of a ring buffer and returns number of elements left.
- */
-static inline unsigned int
-io_getevents_advance_and_peek(io_context_t ctx,
-                              struct io_event **events,
-                              unsigned int nr)
-{
-    io_getevents_commit(ctx, nr);
-    return io_getevents_peek(ctx, events);
-}
-
-/**
- * qemu_laio_process_completions:
- * @s: AIO state
- *
- * Fetches completed I/O requests and invokes their callbacks.
+/* The completion BH fetches completed I/O requests and invokes their
+ * callbacks.
  *
  * The function is somewhat tricky because it supports nested event loops, for
  * example when a request callback invokes aio_poll().  In order to do this,
- * indices are kept in LinuxAioState.  Function schedules BH completion so it
- * can be called again in a nested event loop.  When there are no events left
- * to complete the BH is being canceled.
+ * the completion events array and index are kept in qemu_laio_state.  The BH
+ * reschedules itself as long as there are completions pending so it will
+ * either be called again in a nested event loop or will be called after all
+ * events have been completed.  When there are no events left to complete, the
+ * BH returns without rescheduling.
  */
-static void qemu_laio_process_completions(LinuxAioState *s)
+static void qemu_laio_completion_bh(void *opaque)
 {
-    struct io_event *events;
+    struct qemu_laio_state *s = opaque;
+
+    /* Fetch more completion events when empty */
+    if (s->event_idx == s->event_max) {
+        do {
+            struct timespec ts = { 0 };
+            s->event_max = io_getevents(s->ctx, MAX_EVENTS, MAX_EVENTS,
+                                        s->events, &ts);
+        } while (s->event_max == -EINTR);
+
+        s->event_idx = 0;
+        if (s->event_max <= 0) {
+            s->event_max = 0;
+            return; /* no more events */
+        }
+    }
 
     /* Reschedule so nested event loops see currently pending completions */
     qemu_bh_schedule(s->completion_bh);
 
-    while ((s->event_max = io_getevents_advance_and_peek(s->ctx, &events,
-                                                         s->event_idx))) {
-        for (s->event_idx = 0; s->event_idx < s->event_max; ) {
-            struct iocb *iocb = events[s->event_idx].obj;
-            struct qemu_laiocb *laiocb =
+    /* Process completion events */
+    while (s->event_idx < s->event_max) {
+        struct iocb *iocb = s->events[s->event_idx].obj;
+        struct qemu_laiocb *laiocb =
                 container_of(iocb, struct qemu_laiocb, iocb);
 
-            laiocb->ret = io_event_ret(&events[s->event_idx]);
+        laiocb->ret = io_event_ret(&s->events[s->event_idx]);
+        s->event_idx++;
 
-            /* Change counters one-by-one because we can be nested. */
-            s->io_q.in_flight--;
-            s->event_idx++;
-            qemu_laio_process_completion(laiocb);
-        }
+        qemu_laio_process_completion(s, laiocb);
     }
 
-    qemu_bh_cancel(s->completion_bh);
-
-    /* If we are nested we have to notify the level above that we are done
-     * by setting event_max to zero, upper level will then jump out of it's
-     * own `for` loop.  If we are the last all counters droped to zero. */
-    s->event_max = 0;
-    s->event_idx = 0;
-}
-
-static void qemu_laio_process_completions_and_submit(LinuxAioState *s)
-{
-    qemu_laio_process_completions(s);
-
-    aio_context_acquire(s->aio_context);
     if (!s->io_q.plugged && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
         ioq_submit(s);
     }
-    aio_context_release(s->aio_context);
-}
-
-static void qemu_laio_completion_bh(void *opaque)
-{
-    LinuxAioState *s = opaque;
-
-    qemu_laio_process_completions_and_submit(s);
 }
 
 static void qemu_laio_completion_cb(EventNotifier *e)
 {
-    LinuxAioState *s = container_of(e, LinuxAioState, e);
+    struct qemu_laio_state *s = container_of(e, struct qemu_laio_state, e);
 
     if (event_notifier_test_and_clear(&s->e)) {
-        qemu_laio_process_completions_and_submit(s);
+        qemu_bh_schedule(s->completion_bh);
     }
 }
 
-static bool qemu_laio_poll_cb(void *opaque)
-{
-    EventNotifier *e = opaque;
-    LinuxAioState *s = container_of(e, LinuxAioState, e);
-    struct io_event *events;
-
-    if (!io_getevents_peek(s->ctx, &events)) {
-        return false;
-    }
-
-    qemu_laio_process_completions_and_submit(s);
-    return true;
-}
-
 static void laio_cancel(BlockAIOCB *blockacb)
 {
     struct qemu_laiocb *laiocb = (struct qemu_laiocb *)blockacb;
@@ -300,26 +180,22 @@ static void ioq_init(LaioQueue *io_q)
 {
     QSIMPLEQ_INIT(&io_q->pending);
     io_q->plugged = 0;
-    io_q->in_queue = 0;
-    io_q->in_flight = 0;
+    io_q->n = 0;
     io_q->blocked = false;
 }
 
-static void ioq_submit(LinuxAioState *s)
+static void ioq_submit(struct qemu_laio_state *s)
 {
     int ret, len;
     struct qemu_laiocb *aiocb;
-    struct iocb *iocbs[MAX_EVENTS];
+    struct iocb *iocbs[MAX_QUEUED_IO];
     QSIMPLEQ_HEAD(, qemu_laiocb) completed;
 
     do {
-        if (s->io_q.in_flight >= MAX_EVENTS) {
-            break;
-        }
         len = 0;
         QSIMPLEQ_FOREACH(aiocb, &s->io_q.pending, next) {
             iocbs[len++] = &aiocb->iocb;
-            if (s->io_q.in_flight + len >= MAX_EVENTS) {
+            if (len == MAX_QUEUED_IO) {
                 break;
             }
         }
@@ -329,56 +205,55 @@ static void ioq_submit(LinuxAioState *s)
             break;
         }
         if (ret < 0) {
-            /* Fail the first request, retry the rest */
-            aiocb = QSIMPLEQ_FIRST(&s->io_q.pending);
-            QSIMPLEQ_REMOVE_HEAD(&s->io_q.pending, next);
-            s->io_q.in_queue--;
-            aiocb->ret = ret;
-            qemu_laio_process_completion(aiocb);
-            continue;
+            abort();
         }
 
-        s->io_q.in_flight += ret;
-        s->io_q.in_queue  -= ret;
+        s->io_q.n -= ret;
         aiocb = container_of(iocbs[ret - 1], struct qemu_laiocb, iocb);
         QSIMPLEQ_SPLIT_AFTER(&s->io_q.pending, aiocb, next, &completed);
     } while (ret == len && !QSIMPLEQ_EMPTY(&s->io_q.pending));
-    s->io_q.blocked = (s->io_q.in_queue > 0);
-
-    if (s->io_q.in_flight) {
-        /* We can try to complete something just right away if there are
-         * still requests in-flight. */
-        qemu_laio_process_completions(s);
-        /*
-         * Even we have completed everything (in_flight == 0), the queue can
-         * have still pended requests (in_queue > 0).  We do not attempt to
-         * repeat submission to avoid IO hang.  The reason is simple: s->e is
-         * still set and completion callback will be called shortly and all
-         * pended requests will be submitted from there.
-         */
-    }
+    s->io_q.blocked = (s->io_q.n > 0);
 }
 
-void laio_io_plug(BlockDriverState *bs, LinuxAioState *s)
+void laio_io_plug(BlockDriverState *bs, void *aio_ctx)
 {
+    struct qemu_laio_state *s = aio_ctx;
+
     s->io_q.plugged++;
 }
 
-void laio_io_unplug(BlockDriverState *bs, LinuxAioState *s)
+void laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug)
 {
-    assert(s->io_q.plugged);
-    if (--s->io_q.plugged == 0 &&
-        !s->io_q.blocked && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
+    struct qemu_laio_state *s = aio_ctx;
+
+    assert(s->io_q.plugged > 0 || !unplug);
+
+    if (unplug && --s->io_q.plugged > 0) {
+        return;
+    }
+
+    if (!s->io_q.blocked && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
         ioq_submit(s);
     }
 }
 
-static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
-                          int type)
+BlockAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
+        BlockCompletionFunc *cb, void *opaque, int type)
 {
-    LinuxAioState *s = laiocb->ctx;
-    struct iocb *iocbs = &laiocb->iocb;
-    QEMUIOVector *qiov = laiocb->qiov;
+    struct qemu_laio_state *s = aio_ctx;
+    struct qemu_laiocb *laiocb;
+    struct iocb *iocbs;
+    off_t offset = sector_num * 512;
+
+    laiocb = qemu_aio_get(&laio_aiocb_info, bs, cb, opaque);
+    laiocb->nbytes = nb_sectors * 512;
+    laiocb->ctx = s;
+    laiocb->ret = -EINPROGRESS;
+    laiocb->is_read = (type == QEMU_AIO_READ);
+    laiocb->qiov = qiov;
+
+    iocbs = &laiocb->iocb;
 
     switch (type) {
     case QEMU_AIO_WRITE:
@@ -391,88 +266,43 @@ static int laio_do_submit(int fd, struct qemu_laiocb *laiocb, off_t offset,
     default:
         fprintf(stderr, "%s: invalid AIO request type 0x%x.\n",
                         __func__, type);
-        return -EIO;
+        goto out_free_aiocb;
     }
     io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));
 
     QSIMPLEQ_INSERT_TAIL(&s->io_q.pending, laiocb, next);
-    s->io_q.in_queue++;
+    s->io_q.n++;
     if (!s->io_q.blocked &&
-        (!s->io_q.plugged ||
-         s->io_q.in_flight + s->io_q.in_queue >= MAX_EVENTS)) {
+        (!s->io_q.plugged || s->io_q.n >= MAX_QUEUED_IO)) {
         ioq_submit(s);
     }
-
-    return 0;
-}
-
-int coroutine_fn laio_co_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
-                                uint64_t offset, QEMUIOVector *qiov, int type)
-{
-    int ret;
-    struct qemu_laiocb laiocb = {
-        .co         = qemu_coroutine_self(),
-        .nbytes     = qiov->size,
-        .ctx        = s,
-        .ret        = -EINPROGRESS,
-        .is_read    = (type == QEMU_AIO_READ),
-        .qiov       = qiov,
-    };
-
-    ret = laio_do_submit(fd, &laiocb, offset, type);
-    if (ret < 0) {
-        return ret;
-    }
-
-    if (laiocb.ret == -EINPROGRESS) {
-        qemu_coroutine_yield();
-    }
-    return laiocb.ret;
-}
-
-BlockAIOCB *laio_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
-        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
-        BlockCompletionFunc *cb, void *opaque, int type)
-{
-    struct qemu_laiocb *laiocb;
-    off_t offset = sector_num * BDRV_SECTOR_SIZE;
-    int ret;
-
-    laiocb = qemu_aio_get(&laio_aiocb_info, bs, cb, opaque);
-    laiocb->nbytes = nb_sectors * BDRV_SECTOR_SIZE;
-    laiocb->ctx = s;
-    laiocb->ret = -EINPROGRESS;
-    laiocb->is_read = (type == QEMU_AIO_READ);
-    laiocb->qiov = qiov;
-
-    ret = laio_do_submit(fd, laiocb, offset, type);
-    if (ret < 0) {
-        qemu_aio_unref(laiocb);
-        return NULL;
-    }
-
     return &laiocb->common;
+
+out_free_aiocb:
+    qemu_aio_unref(laiocb);
+    return NULL;
 }
 
-void laio_detach_aio_context(LinuxAioState *s, AioContext *old_context)
+void laio_detach_aio_context(void *s_, AioContext *old_context)
 {
-    aio_set_event_notifier(old_context, &s->e, false, NULL, NULL);
+    struct qemu_laio_state *s = s_;
+
+    aio_set_event_notifier(old_context, &s->e, false, NULL);
     qemu_bh_delete(s->completion_bh);
-    s->aio_context = NULL;
 }
 
-void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context)
+void laio_attach_aio_context(void *s_, AioContext *new_context)
 {
-    s->aio_context = new_context;
+    struct qemu_laio_state *s = s_;
+
     s->completion_bh = aio_bh_new(new_context, qemu_laio_completion_bh, s);
     aio_set_event_notifier(new_context, &s->e, false,
-                           qemu_laio_completion_cb,
-                           qemu_laio_poll_cb);
+                           qemu_laio_completion_cb);
 }
 
-LinuxAioState *laio_init(void)
+void *laio_init(void)
 {
-    LinuxAioState *s;
+    struct qemu_laio_state *s;
 
     s = g_malloc0(sizeof(*s));
     if (event_notifier_init(&s->e, false) < 0) {
@@ -494,8 +324,10 @@ out_free_state:
     return NULL;
 }
 
-void laio_cleanup(LinuxAioState *s)
+void laio_cleanup(void *s_)
 {
+    struct qemu_laio_state *s = s_;
+
     event_notifier_cleanup(&s->e);
 
     if (io_destroy(s->ctx) != 0) {

block/nbd-client.c

@@ -1,7 +1,6 @@
 /*
  * QEMU Block driver for  NBD
  *
- * Copyright (C) 2016 Red Hat, Inc.
  * Copyright (C) 2008 Bull S.A.S.
  *     Author: Laurent Vivier <Laurent.Vivier@bull.net>
  *
@@ -27,102 +26,91 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
-#include "qapi/error.h"
 #include "nbd-client.h"
+#include "qemu/sockets.h"
 
 #define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
 #define INDEX_TO_HANDLE(bs, index)  ((index)  ^ ((uint64_t)(intptr_t)bs))
 
-static void nbd_recv_coroutines_enter_all(NBDClientSession *s)
+static void nbd_recv_coroutines_enter_all(NbdClientSession *s)
 {
     int i;
 
     for (i = 0; i < MAX_NBD_REQUESTS; i++) {
         if (s->recv_coroutine[i]) {
-            aio_co_wake(s->recv_coroutine[i]);
+            qemu_coroutine_enter(s->recv_coroutine[i], NULL);
         }
     }
 }
 
 static void nbd_teardown_connection(BlockDriverState *bs)
 {
-    NBDClientSession *client = nbd_get_client_session(bs);
+    NbdClientSession *client = nbd_get_client_session(bs);
 
-    if (!client->ioc) { /* Already closed */
+    /* finish any pending coroutines */
+    shutdown(client->sock, 2);
+    nbd_recv_coroutines_enter_all(client);
+
+    nbd_client_detach_aio_context(bs);
+    closesocket(client->sock);
+    client->sock = -1;
+}
+
+static void nbd_reply_ready(void *opaque)
+{
+    BlockDriverState *bs = opaque;
+    NbdClientSession *s = nbd_get_client_session(bs);
+    uint64_t i;
+    int ret;
+
+    if (s->reply.handle == 0) {
+        /* No reply already in flight.  Fetch a header.  It is possible
+         * that another thread has done the same thing in parallel, so
+         * the socket is not readable anymore.
+         */
+        ret = nbd_receive_reply(s->sock, &s->reply);
+        if (ret == -EAGAIN) {
+            return;
+        }
+        if (ret < 0) {
+            s->reply.handle = 0;
+            goto fail;
+        }
+    }
+
+    /* There's no need for a mutex on the receive side, because the
+     * handler acts as a synchronization point and ensures that only
+     * one coroutine is called until the reply finishes.  */
+    i = HANDLE_TO_INDEX(s, s->reply.handle);
+    if (i >= MAX_NBD_REQUESTS) {
+        goto fail;
+    }
+
+    if (s->recv_coroutine[i]) {
+        qemu_coroutine_enter(s->recv_coroutine[i], NULL);
         return;
     }
 
-    /* finish any pending coroutines */
-    qio_channel_shutdown(client->ioc,
-                         QIO_CHANNEL_SHUTDOWN_BOTH,
-                         NULL);
-    BDRV_POLL_WHILE(bs, client->read_reply_co);
-
-    nbd_client_detach_aio_context(bs);
-    object_unref(OBJECT(client->sioc));
-    client->sioc = NULL;
-    object_unref(OBJECT(client->ioc));
-    client->ioc = NULL;
+fail:
+    nbd_teardown_connection(bs);
 }
 
-static coroutine_fn void nbd_read_reply_entry(void *opaque)
+static void nbd_restart_write(void *opaque)
 {
-    NBDClientSession *s = opaque;
-    uint64_t i;
-    int ret;
-    Error *local_err = NULL;
+    BlockDriverState *bs = opaque;
 
-    for (;;) {
-        assert(s->reply.handle == 0);
-        ret = nbd_receive_reply(s->ioc, &s->reply, &local_err);
-        if (ret < 0) {
-            error_report_err(local_err);
-        }
-        if (ret <= 0) {
-            break;
-        }
-
-        /* There's no need for a mutex on the receive side, because the
-         * handler acts as a synchronization point and ensures that only
-         * one coroutine is called until the reply finishes.
-         */
-        i = HANDLE_TO_INDEX(s, s->reply.handle);
-        if (i >= MAX_NBD_REQUESTS || !s->recv_coroutine[i]) {
-            break;
-        }
-
-        /* We're woken up by the recv_coroutine itself.  Note that there
-         * is no race between yielding and reentering read_reply_co.  This
-         * is because:
-         *
-         * - if recv_coroutine[i] runs on the same AioContext, it is only
-         *   entered after we yield
-         *
-         * - if recv_coroutine[i] runs on a different AioContext, reentering
-         *   read_reply_co happens through a bottom half, which can only
-         *   run after we yield.
-         */
-        aio_co_wake(s->recv_coroutine[i]);
-        qemu_coroutine_yield();
-    }
-
-    nbd_recv_coroutines_enter_all(s);
-    s->read_reply_co = NULL;
+    qemu_coroutine_enter(nbd_get_client_session(bs)->send_coroutine, NULL);
 }
 
 static int nbd_co_send_request(BlockDriverState *bs,
-                               NBDRequest *request,
-                               QEMUIOVector *qiov)
+                               struct nbd_request *request,
+                               QEMUIOVector *qiov, int offset)
 {
-    NBDClientSession *s = nbd_get_client_session(bs);
+    NbdClientSession *s = nbd_get_client_session(bs);
+    AioContext *aio_context;
     int rc, ret, i;
 
     qemu_co_mutex_lock(&s->send_mutex);
-    while (s->in_flight == MAX_NBD_REQUESTS) {
-        qemu_co_queue_wait(&s->free_sema, &s->send_mutex);
-    }
-    s->in_flight++;
 
     for (i = 0; i < MAX_NBD_REQUESTS; i++) {
         if (s->recv_coroutine[i] == NULL) {
@@ -131,50 +119,54 @@ static int nbd_co_send_request(BlockDriverState *bs,
         }
     }
 
-    g_assert(qemu_in_coroutine());
     assert(i < MAX_NBD_REQUESTS);
     request->handle = INDEX_TO_HANDLE(s, i);
+    s->send_coroutine = qemu_coroutine_self();
+    aio_context = bdrv_get_aio_context(bs);
 
-    if (!s->ioc) {
-        qemu_co_mutex_unlock(&s->send_mutex);
-        return -EPIPE;
-    }
-
+    aio_set_fd_handler(aio_context, s->sock, false,
+                       nbd_reply_ready, nbd_restart_write, bs);
     if (qiov) {
-        qio_channel_set_cork(s->ioc, true);
-        rc = nbd_send_request(s->ioc, request);
+        if (!s->is_unix) {
+            socket_set_cork(s->sock, 1);
+        }
+        rc = nbd_send_request(s->sock, request);
         if (rc >= 0) {
-            ret = nbd_rwv(s->ioc, qiov->iov, qiov->niov, request->len, false,
-                          NULL);
+            ret = qemu_co_sendv(s->sock, qiov->iov, qiov->niov,
+                                offset, request->len);
             if (ret != request->len) {
                 rc = -EIO;
             }
         }
-        qio_channel_set_cork(s->ioc, false);
+        if (!s->is_unix) {
+            socket_set_cork(s->sock, 0);
+        }
     } else {
-        rc = nbd_send_request(s->ioc, request);
+        rc = nbd_send_request(s->sock, request);
     }
+    aio_set_fd_handler(aio_context, s->sock, false,
+                       nbd_reply_ready, NULL, bs);
+    s->send_coroutine = NULL;
     qemu_co_mutex_unlock(&s->send_mutex);
     return rc;
 }
 
-static void nbd_co_receive_reply(NBDClientSession *s,
-                                 NBDRequest *request,
-                                 NBDReply *reply,
-                                 QEMUIOVector *qiov)
+static void nbd_co_receive_reply(NbdClientSession *s,
+    struct nbd_request *request, struct nbd_reply *reply,
+    QEMUIOVector *qiov, int offset)
 {
     int ret;
 
-    /* Wait until we're woken up by nbd_read_reply_entry.  */
+    /* Wait until we're woken up by the read handler.  TODO: perhaps
+     * peek at the next reply and avoid yielding if it's ours?  */
     qemu_coroutine_yield();
     *reply = s->reply;
-    if (reply->handle != request->handle ||
-        !s->ioc) {
+    if (reply->handle != request->handle) {
         reply->error = EIO;
     } else {
         if (qiov && reply->error == 0) {
-            ret = nbd_rwv(s->ioc, qiov->iov, qiov->niov, request->len, true,
-                          NULL);
+            ret = qemu_co_recvv(s->sock, qiov->iov, qiov->niov,
+                                offset, request->len);
             if (ret != request->len) {
                 reply->error = EIO;
             }
@@ -185,236 +177,231 @@ static void nbd_co_receive_reply(NBDClientSession *s,
     }
 }
 
-static void nbd_coroutine_end(BlockDriverState *bs,
-                              NBDRequest *request)
+static void nbd_coroutine_start(NbdClientSession *s,
+   struct nbd_request *request)
+{
+    /* Poor man semaphore.  The free_sema is locked when no other request
+     * can be accepted, and unlocked after receiving one reply.  */
+    if (s->in_flight >= MAX_NBD_REQUESTS - 1) {
+        qemu_co_mutex_lock(&s->free_sema);
+        assert(s->in_flight < MAX_NBD_REQUESTS);
+    }
+    s->in_flight++;
+
+    /* s->recv_coroutine[i] is set as soon as we get the send_lock.  */
+}
+
+static void nbd_coroutine_end(NbdClientSession *s,
+    struct nbd_request *request)
 {
-    NBDClientSession *s = nbd_get_client_session(bs);
     int i = HANDLE_TO_INDEX(s, request->handle);
-
     s->recv_coroutine[i] = NULL;
-
-    /* Kick the read_reply_co to get the next reply.  */
-    if (s->read_reply_co) {
-        aio_co_wake(s->read_reply_co);
+    if (s->in_flight-- == MAX_NBD_REQUESTS) {
+        qemu_co_mutex_unlock(&s->free_sema);
     }
-
-    qemu_co_mutex_lock(&s->send_mutex);
-    s->in_flight--;
-    qemu_co_queue_next(&s->free_sema);
-    qemu_co_mutex_unlock(&s->send_mutex);
 }
 
-int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset,
-                         uint64_t bytes, QEMUIOVector *qiov, int flags)
+static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
+                          int nb_sectors, QEMUIOVector *qiov,
+                          int offset)
 {
-    NBDClientSession *client = nbd_get_client_session(bs);
-    NBDRequest request = {
-        .type = NBD_CMD_READ,
-        .from = offset,
-        .len = bytes,
-    };
-    NBDReply reply;
+    NbdClientSession *client = nbd_get_client_session(bs);
+    struct nbd_request request = { .type = NBD_CMD_READ };
+    struct nbd_reply reply;
     ssize_t ret;
 
-    assert(bytes <= NBD_MAX_BUFFER_SIZE);
-    assert(!flags);
+    request.from = sector_num * 512;
+    request.len = nb_sectors * 512;
 
-    ret = nbd_co_send_request(bs, &request, NULL);
+    nbd_coroutine_start(client, &request);
+    ret = nbd_co_send_request(bs, &request, NULL, 0);
     if (ret < 0) {
         reply.error = -ret;
     } else {
-        nbd_co_receive_reply(client, &request, &reply, qiov);
+        nbd_co_receive_reply(client, &request, &reply, qiov, offset);
     }
-    nbd_coroutine_end(bs, &request);
+    nbd_coroutine_end(client, &request);
     return -reply.error;
+
 }
 
-int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset,
-                          uint64_t bytes, QEMUIOVector *qiov, int flags)
+static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
+                           int nb_sectors, QEMUIOVector *qiov,
+                           int offset)
 {
-    NBDClientSession *client = nbd_get_client_session(bs);
-    NBDRequest request = {
-        .type = NBD_CMD_WRITE,
-        .from = offset,
-        .len = bytes,
-    };
-    NBDReply reply;
+    NbdClientSession *client = nbd_get_client_session(bs);
+    struct nbd_request request = { .type = NBD_CMD_WRITE };
+    struct nbd_reply reply;
     ssize_t ret;
 
-    if (flags & BDRV_REQ_FUA) {
-        assert(client->nbdflags & NBD_FLAG_SEND_FUA);
-        request.flags |= NBD_CMD_FLAG_FUA;
+    if (!bdrv_enable_write_cache(bs) &&
+        (client->nbdflags & NBD_FLAG_SEND_FUA)) {
+        request.type |= NBD_CMD_FLAG_FUA;
     }
 
-    assert(bytes <= NBD_MAX_BUFFER_SIZE);
+    request.from = sector_num * 512;
+    request.len = nb_sectors * 512;
 
-    ret = nbd_co_send_request(bs, &request, qiov);
+    nbd_coroutine_start(client, &request);
+    ret = nbd_co_send_request(bs, &request, qiov, offset);
     if (ret < 0) {
         reply.error = -ret;
     } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL);
+        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
     }
-    nbd_coroutine_end(bs, &request);
+    nbd_coroutine_end(client, &request);
     return -reply.error;
 }
 
-int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
-                                int count, BdrvRequestFlags flags)
+/* qemu-nbd has a limit of slightly less than 1M per request.  Try to
+ * remain aligned to 4K. */
+#define NBD_MAX_SECTORS 2040
+
+int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
+                        int nb_sectors, QEMUIOVector *qiov)
 {
-    ssize_t ret;
-    NBDClientSession *client = nbd_get_client_session(bs);
-    NBDRequest request = {
-        .type = NBD_CMD_WRITE_ZEROES,
-        .from = offset,
-        .len = count,
-    };
-    NBDReply reply;
+    int offset = 0;
+    int ret;
+    while (nb_sectors > NBD_MAX_SECTORS) {
+        ret = nbd_co_readv_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
+        if (ret < 0) {
+            return ret;
+        }
+        offset += NBD_MAX_SECTORS * 512;
+        sector_num += NBD_MAX_SECTORS;
+        nb_sectors -= NBD_MAX_SECTORS;
+    }
+    return nbd_co_readv_1(bs, sector_num, nb_sectors, qiov, offset);
+}
 
-    if (!(client->nbdflags & NBD_FLAG_SEND_WRITE_ZEROES)) {
-        return -ENOTSUP;
+int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
+                         int nb_sectors, QEMUIOVector *qiov)
+{
+    int offset = 0;
+    int ret;
+    while (nb_sectors > NBD_MAX_SECTORS) {
+        ret = nbd_co_writev_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
+        if (ret < 0) {
+            return ret;
+        }
+        offset += NBD_MAX_SECTORS * 512;
+        sector_num += NBD_MAX_SECTORS;
+        nb_sectors -= NBD_MAX_SECTORS;
     }
-
-    if (flags & BDRV_REQ_FUA) {
-        assert(client->nbdflags & NBD_FLAG_SEND_FUA);
-        request.flags |= NBD_CMD_FLAG_FUA;
-    }
-    if (!(flags & BDRV_REQ_MAY_UNMAP)) {
-        request.flags |= NBD_CMD_FLAG_NO_HOLE;
-    }
-
-    ret = nbd_co_send_request(bs, &request, NULL);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL);
-    }
-    nbd_coroutine_end(bs, &request);
-    return -reply.error;
+    return nbd_co_writev_1(bs, sector_num, nb_sectors, qiov, offset);
 }
 
 int nbd_client_co_flush(BlockDriverState *bs)
 {
-    NBDClientSession *client = nbd_get_client_session(bs);
-    NBDRequest request = { .type = NBD_CMD_FLUSH };
-    NBDReply reply;
+    NbdClientSession *client = nbd_get_client_session(bs);
+    struct nbd_request request = { .type = NBD_CMD_FLUSH };
+    struct nbd_reply reply;
     ssize_t ret;
 
     if (!(client->nbdflags & NBD_FLAG_SEND_FLUSH)) {
         return 0;
     }
 
+    if (client->nbdflags & NBD_FLAG_SEND_FUA) {
+        request.type |= NBD_CMD_FLAG_FUA;
+    }
+
     request.from = 0;
     request.len = 0;
 
-    ret = nbd_co_send_request(bs, &request, NULL);
+    nbd_coroutine_start(client, &request);
+    ret = nbd_co_send_request(bs, &request, NULL, 0);
     if (ret < 0) {
         reply.error = -ret;
     } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL);
+        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
     }
-    nbd_coroutine_end(bs, &request);
+    nbd_coroutine_end(client, &request);
     return -reply.error;
 }
 
-int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int count)
+int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
+                          int nb_sectors)
 {
-    NBDClientSession *client = nbd_get_client_session(bs);
-    NBDRequest request = {
-        .type = NBD_CMD_TRIM,
-        .from = offset,
-        .len = count,
-    };
-    NBDReply reply;
+    NbdClientSession *client = nbd_get_client_session(bs);
+    struct nbd_request request = { .type = NBD_CMD_TRIM };
+    struct nbd_reply reply;
     ssize_t ret;
 
     if (!(client->nbdflags & NBD_FLAG_SEND_TRIM)) {
         return 0;
     }
+    request.from = sector_num * 512;
+    request.len = nb_sectors * 512;
 
-    ret = nbd_co_send_request(bs, &request, NULL);
+    nbd_coroutine_start(client, &request);
+    ret = nbd_co_send_request(bs, &request, NULL, 0);
     if (ret < 0) {
         reply.error = -ret;
     } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL);
+        nbd_co_receive_reply(client, &request, &reply, NULL, 0);
     }
-    nbd_coroutine_end(bs, &request);
+    nbd_coroutine_end(client, &request);
     return -reply.error;
 
 }
 
 void nbd_client_detach_aio_context(BlockDriverState *bs)
 {
-    NBDClientSession *client = nbd_get_client_session(bs);
-    qio_channel_detach_aio_context(QIO_CHANNEL(client->sioc));
+    aio_set_fd_handler(bdrv_get_aio_context(bs),
+                       nbd_get_client_session(bs)->sock,
+                       false, NULL, NULL, NULL);
 }
 
 void nbd_client_attach_aio_context(BlockDriverState *bs,
                                    AioContext *new_context)
 {
-    NBDClientSession *client = nbd_get_client_session(bs);
-    qio_channel_attach_aio_context(QIO_CHANNEL(client->sioc), new_context);
-    aio_co_schedule(new_context, client->read_reply_co);
+    aio_set_fd_handler(new_context, nbd_get_client_session(bs)->sock,
+                       false, nbd_reply_ready, NULL, bs);
 }
 
 void nbd_client_close(BlockDriverState *bs)
 {
-    NBDClientSession *client = nbd_get_client_session(bs);
-    NBDRequest request = { .type = NBD_CMD_DISC };
+    NbdClientSession *client = nbd_get_client_session(bs);
+    struct nbd_request request = {
+        .type = NBD_CMD_DISC,
+        .from = 0,
+        .len = 0
+    };
 
-    if (client->ioc == NULL) {
+    if (client->sock == -1) {
         return;
     }
 
-    nbd_send_request(client->ioc, &request);
+    nbd_send_request(client->sock, &request);
 
     nbd_teardown_connection(bs);
 }
 
-int nbd_client_init(BlockDriverState *bs,
-                    QIOChannelSocket *sioc,
-                    const char *export,
-                    QCryptoTLSCreds *tlscreds,
-                    const char *hostname,
+int nbd_client_init(BlockDriverState *bs, int sock, const char *export,
                     Error **errp)
 {
-    NBDClientSession *client = nbd_get_client_session(bs);
+    NbdClientSession *client = nbd_get_client_session(bs);
     int ret;
 
     /* NBD handshake */
     logout("session init %s\n", export);
-    qio_channel_set_blocking(QIO_CHANNEL(sioc), true, NULL);
-
-    ret = nbd_receive_negotiate(QIO_CHANNEL(sioc), export,
-                                &client->nbdflags,
-                                tlscreds, hostname,
-                                &client->ioc,
-                                &client->size, errp);
+    qemu_set_block(sock);
+    ret = nbd_receive_negotiate(sock, export,
+                                &client->nbdflags, &client->size, errp);
     if (ret < 0) {
         logout("Failed to negotiate with the NBD server\n");
+        closesocket(sock);
         return ret;
     }
-    if (client->nbdflags & NBD_FLAG_SEND_FUA) {
-        bs->supported_write_flags = BDRV_REQ_FUA;
-        bs->supported_zero_flags |= BDRV_REQ_FUA;
-    }
-    if (client->nbdflags & NBD_FLAG_SEND_WRITE_ZEROES) {
-        bs->supported_zero_flags |= BDRV_REQ_MAY_UNMAP;
-    }
 
     qemu_co_mutex_init(&client->send_mutex);
-    qemu_co_queue_init(&client->free_sema);
-    client->sioc = sioc;
-    object_ref(OBJECT(client->sioc));
-
-    if (!client->ioc) {
-        client->ioc = QIO_CHANNEL(sioc);
-        object_ref(OBJECT(client->ioc));
-    }
+    qemu_co_mutex_init(&client->free_sema);
+    client->sock = sock;
 
     /* Now that we're connected, set the socket to be non-blocking and
      * kick the reply mechanism.  */
-    qio_channel_set_blocking(QIO_CHANNEL(sioc), false, NULL);
-    client->read_reply_co = qemu_coroutine_create(nbd_read_reply_entry, client);
+    qemu_set_nonblock(sock);
     nbd_client_attach_aio_context(bs, bdrv_get_aio_context(bs));
 
     logout("Established connection with NBD server\n");

block/nbd-client.h

@@ -4,7 +4,6 @@
 #include "qemu-common.h"
 #include "block/nbd.h"
 #include "block/block_int.h"
-#include "io/channel-socket.h"
 
 /* #define DEBUG_NBD */
 
@@ -17,39 +16,35 @@
 
 #define MAX_NBD_REQUESTS    16
 
-typedef struct NBDClientSession {
-    QIOChannelSocket *sioc; /* The master data channel */
-    QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */
-    uint16_t nbdflags;
+typedef struct NbdClientSession {
+    int sock;
+    uint32_t nbdflags;
     off_t size;
 
     CoMutex send_mutex;
-    CoQueue free_sema;
-    Coroutine *read_reply_co;
+    CoMutex free_sema;
+    Coroutine *send_coroutine;
     int in_flight;
 
     Coroutine *recv_coroutine[MAX_NBD_REQUESTS];
-    NBDReply reply;
-} NBDClientSession;
+    struct nbd_reply reply;
 
-NBDClientSession *nbd_get_client_session(BlockDriverState *bs);
+    bool is_unix;
+} NbdClientSession;
 
-int nbd_client_init(BlockDriverState *bs,
-                    QIOChannelSocket *sock,
-                    const char *export_name,
-                    QCryptoTLSCreds *tlscreds,
-                    const char *hostname,
+NbdClientSession *nbd_get_client_session(BlockDriverState *bs);
+
+int nbd_client_init(BlockDriverState *bs, int sock, const char *export_name,
                     Error **errp);
 void nbd_client_close(BlockDriverState *bs);
 
-int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int count);
+int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
+                          int nb_sectors);
 int nbd_client_co_flush(BlockDriverState *bs);
-int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset,
-                          uint64_t bytes, QEMUIOVector *qiov, int flags);
-int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
-                                int count, BdrvRequestFlags flags);
-int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset,
-                         uint64_t bytes, QEMUIOVector *qiov, int flags);
+int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
+                         int nb_sectors, QEMUIOVector *qiov);
+int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
+                        int nb_sectors, QEMUIOVector *qiov);
 
 void nbd_client_detach_aio_context(BlockDriverState *bs);
 void nbd_client_attach_aio_context(BlockDriverState *bs,

block/nbd.c

@@ -26,28 +26,23 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
 #include "block/nbd-client.h"
-#include "qapi/error.h"
 #include "qemu/uri.h"
 #include "block/block_int.h"
 #include "qemu/module.h"
-#include "qapi-visit.h"
-#include "qapi/qobject-input-visitor.h"
-#include "qapi/qobject-output-visitor.h"
+#include "qemu/sockets.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qjson.h"
+#include "qapi/qmp/qint.h"
 #include "qapi/qmp/qstring.h"
-#include "qemu/cutils.h"
+
+#include <sys/types.h>
+#include <unistd.h>
 
 #define EN_OPTSTR ":exportname="
 
 typedef struct BDRVNBDState {
-    NBDClientSession client;
-
-    /* For nbd_refresh_filename() */
-    SocketAddress *saddr;
-    char *export, *tlscredsid;
+    NbdClientSession client;
 } BDRVNBDState;
 
 static int nbd_parse_uri(const char *filename, QDict *options)
@@ -78,7 +73,7 @@ static int nbd_parse_uri(const char *filename, QDict *options)
     p = uri->path ? uri->path : "/";
     p += strspn(p, "/");
     if (p[0]) {
-        qdict_put_str(options, "export", p);
+        qdict_put(options, "export", qstring_from_str(p));
     }
 
     qp = query_params_parse(uri->query);
@@ -93,12 +88,9 @@ static int nbd_parse_uri(const char *filename, QDict *options)
             ret = -EINVAL;
             goto out;
         }
-        qdict_put_str(options, "server.type", "unix");
-        qdict_put_str(options, "server.path", qp->p[0].value);
+        qdict_put(options, "path", qstring_from_str(qp->p[0].value));
     } else {
         QString *host;
-        char *port_str;
-
         /* nbd[+tcp]://host[:port]/export */
         if (!uri->server) {
             ret = -EINVAL;
@@ -113,12 +105,12 @@ static int nbd_parse_uri(const char *filename, QDict *options)
             host = qstring_from_str(uri->server);
         }
 
-        qdict_put_str(options, "server.type", "inet");
-        qdict_put(options, "server.host", host);
-
-        port_str = g_strdup_printf("%d", uri->port ?: NBD_DEFAULT_PORT);
-        qdict_put_str(options, "server.port", port_str);
-        g_free(port_str);
+        qdict_put(options, "host", host);
+        if (uri->port) {
+            char* port_str = g_strdup_printf("%d", uri->port);
+            qdict_put(options, "port", qstring_from_str(port_str));
+            g_free(port_str);
+        }
     }
 
 out:
@@ -129,26 +121,6 @@ out:
     return ret;
 }
 
-static bool nbd_has_filename_options_conflict(QDict *options, Error **errp)
-{
-    const QDictEntry *e;
-
-    for (e = qdict_first(options); e; e = qdict_next(options, e)) {
-        if (!strcmp(e->key, "host") ||
-            !strcmp(e->key, "port") ||
-            !strcmp(e->key, "path") ||
-            !strcmp(e->key, "export") ||
-            strstart(e->key, "server.", NULL))
-        {
-            error_setg(errp, "Option '%s' cannot be used with a file name",
-                       e->key);
-            return true;
-        }
-    }
-
-    return false;
-}
-
 static void nbd_parse_filename(const char *filename, QDict *options,
                                Error **errp)
 {
@@ -157,7 +129,12 @@ static void nbd_parse_filename(const char *filename, QDict *options,
     const char *host_spec;
     const char *unixpath;
 
-    if (nbd_has_filename_options_conflict(options, errp)) {
+    if (qdict_haskey(options, "host")
+        || qdict_haskey(options, "port")
+        || qdict_haskey(options, "path"))
+    {
+        error_setg(errp, "host/port/path and a file name may not be specified "
+                         "at the same time");
         return;
     }
 
@@ -179,7 +156,7 @@ static void nbd_parse_filename(const char *filename, QDict *options,
         export_name[0] = 0; /* truncate 'file' */
         export_name += strlen(EN_OPTSTR);
 
-        qdict_put_str(options, "export", export_name);
+        qdict_put(options, "export", qstring_from_str(export_name));
     }
 
     /* extract the host_spec - fail if it's not nbd:... */
@@ -194,19 +171,17 @@ static void nbd_parse_filename(const char *filename, QDict *options,
 
     /* are we a UNIX or TCP socket? */
     if (strstart(host_spec, "unix:", &unixpath)) {
-        qdict_put_str(options, "server.type", "unix");
-        qdict_put_str(options, "server.path", unixpath);
+        qdict_put(options, "path", qstring_from_str(unixpath));
     } else {
-        InetSocketAddress *addr = g_new(InetSocketAddress, 1);
+        InetSocketAddress *addr = NULL;
 
-        if (inet_parse(addr, host_spec, errp)) {
-            goto out_inet;
+        addr = inet_parse(host_spec, errp);
+        if (!addr) {
+            goto out;
         }
 
-        qdict_put_str(options, "server.type", "inet");
-        qdict_put_str(options, "server.host", addr->host);
-        qdict_put_str(options, "server.port", addr->port);
-    out_inet:
+        qdict_put(options, "host", qstring_from_str(addr->host));
+        qdict_put(options, "port", qstring_from_str(addr->port));
         qapi_free_InetSocketAddress(addr);
     }
 
@@ -214,255 +189,117 @@ out:
     g_free(file);
 }
 
-static bool nbd_process_legacy_socket_options(QDict *output_options,
-                                              QemuOpts *legacy_opts,
-                                              Error **errp)
-{
-    const char *path = qemu_opt_get(legacy_opts, "path");
-    const char *host = qemu_opt_get(legacy_opts, "host");
-    const char *port = qemu_opt_get(legacy_opts, "port");
-    const QDictEntry *e;
-
-    if (!path && !host && !port) {
-        return true;
-    }
-
-    for (e = qdict_first(output_options); e; e = qdict_next(output_options, e))
-    {
-        if (strstart(e->key, "server.", NULL)) {
-            error_setg(errp, "Cannot use 'server' and path/host/port at the "
-                       "same time");
-            return false;
-        }
-    }
-
-    if (path && host) {
-        error_setg(errp, "path and host may not be used at the same time");
-        return false;
-    } else if (path) {
-        if (port) {
-            error_setg(errp, "port may not be used without host");
-            return false;
-        }
-
-        qdict_put_str(output_options, "server.type", "unix");
-        qdict_put_str(output_options, "server.path", path);
-    } else if (host) {
-        qdict_put_str(output_options, "server.type", "inet");
-        qdict_put_str(output_options, "server.host", host);
-        qdict_put_str(output_options, "server.port",
-                      port ?: stringify(NBD_DEFAULT_PORT));
-    }
-
-    return true;
-}
-
-static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options,
+static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options, char **export,
                                  Error **errp)
 {
-    SocketAddress *saddr = NULL;
-    QDict *addr = NULL;
-    QObject *crumpled_addr = NULL;
-    Visitor *iv = NULL;
-    Error *local_err = NULL;
+    SocketAddress *saddr;
 
-    qdict_extract_subqdict(options, &addr, "server.");
-    if (!qdict_size(addr)) {
-        error_setg(errp, "NBD server address missing");
-        goto done;
+    if (qdict_haskey(options, "path") == qdict_haskey(options, "host")) {
+        if (qdict_haskey(options, "path")) {
+            error_setg(errp, "path and host may not be used at the same time.");
+        } else {
+            error_setg(errp, "one of path and host must be specified.");
+        }
+        return NULL;
     }
 
-    crumpled_addr = qdict_crumple(addr, errp);
-    if (!crumpled_addr) {
-        goto done;
+    saddr = g_new0(SocketAddress, 1);
+
+    if (qdict_haskey(options, "path")) {
+        saddr->type = SOCKET_ADDRESS_KIND_UNIX;
+        saddr->u.q_unix = g_new0(UnixSocketAddress, 1);
+        saddr->u.q_unix->path = g_strdup(qdict_get_str(options, "path"));
+        qdict_del(options, "path");
+    } else {
+        saddr->type = SOCKET_ADDRESS_KIND_INET;
+        saddr->u.inet = g_new0(InetSocketAddress, 1);
+        saddr->u.inet->host = g_strdup(qdict_get_str(options, "host"));
+        if (!qdict_get_try_str(options, "port")) {
+            saddr->u.inet->port = g_strdup_printf("%d", NBD_DEFAULT_PORT);
+        } else {
+            saddr->u.inet->port = g_strdup(qdict_get_str(options, "port"));
+        }
+        qdict_del(options, "host");
+        qdict_del(options, "port");
     }
 
-    /*
-     * FIXME .numeric, .to, .ipv4 or .ipv6 don't work with -drive
-     * server.type=inet.  .to doesn't matter, it's ignored anyway.
-     * That's because when @options come from -blockdev or
-     * blockdev_add, members are typed according to the QAPI schema,
-     * but when they come from -drive, they're all QString.  The
-     * visitor expects the former.
-     */
-    iv = qobject_input_visitor_new(crumpled_addr);
-    visit_type_SocketAddress(iv, NULL, &saddr, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        goto done;
+    s->client.is_unix = saddr->type == SOCKET_ADDRESS_KIND_UNIX;
+
+    *export = g_strdup(qdict_get_try_str(options, "export"));
+    if (*export) {
+        qdict_del(options, "export");
     }
 
-done:
-    QDECREF(addr);
-    qobject_decref(crumpled_addr);
-    visit_free(iv);
     return saddr;
 }
 
-NBDClientSession *nbd_get_client_session(BlockDriverState *bs)
+NbdClientSession *nbd_get_client_session(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
     return &s->client;
 }
 
-static QIOChannelSocket *nbd_establish_connection(SocketAddress *saddr,
-                                                  Error **errp)
+static int nbd_establish_connection(BlockDriverState *bs,
+                                    SocketAddress *saddr,
+                                    Error **errp)
 {
-    QIOChannelSocket *sioc;
-    Error *local_err = NULL;
+    BDRVNBDState *s = bs->opaque;
+    int sock;
 
-    sioc = qio_channel_socket_new();
-    qio_channel_set_name(QIO_CHANNEL(sioc), "nbd-client");
+    sock = socket_connect(saddr, errp, NULL, NULL);
 
-    qio_channel_socket_connect_sync(sioc,
-                                    saddr,
-                                    &local_err);
-    if (local_err) {
-        object_unref(OBJECT(sioc));
-        error_propagate(errp, local_err);
-        return NULL;
+    if (sock < 0) {
+        logout("Failed to establish connection to NBD server\n");
+        return -EIO;
     }
 
-    qio_channel_set_delay(QIO_CHANNEL(sioc), false);
+    if (!s->client.is_unix) {
+        socket_set_nodelay(sock);
+    }
 
-    return sioc;
+    return sock;
 }
 
-
-static QCryptoTLSCreds *nbd_get_tls_creds(const char *id, Error **errp)
-{
-    Object *obj;
-    QCryptoTLSCreds *creds;
-
-    obj = object_resolve_path_component(
-        object_get_objects_root(), id);
-    if (!obj) {
-        error_setg(errp, "No TLS credentials with id '%s'",
-                   id);
-        return NULL;
-    }
-    creds = (QCryptoTLSCreds *)
-        object_dynamic_cast(obj, TYPE_QCRYPTO_TLS_CREDS);
-    if (!creds) {
-        error_setg(errp, "Object with id '%s' is not TLS credentials",
-                   id);
-        return NULL;
-    }
-
-    if (creds->endpoint != QCRYPTO_TLS_CREDS_ENDPOINT_CLIENT) {
-        error_setg(errp,
-                   "Expecting TLS credentials with a client endpoint");
-        return NULL;
-    }
-    object_ref(obj);
-    return creds;
-}
-
-
-static QemuOptsList nbd_runtime_opts = {
-    .name = "nbd",
-    .head = QTAILQ_HEAD_INITIALIZER(nbd_runtime_opts.head),
-    .desc = {
-        {
-            .name = "host",
-            .type = QEMU_OPT_STRING,
-            .help = "TCP host to connect to",
-        },
-        {
-            .name = "port",
-            .type = QEMU_OPT_STRING,
-            .help = "TCP port to connect to",
-        },
-        {
-            .name = "path",
-            .type = QEMU_OPT_STRING,
-            .help = "Unix socket path to connect to",
-        },
-        {
-            .name = "export",
-            .type = QEMU_OPT_STRING,
-            .help = "Name of the NBD export to open",
-        },
-        {
-            .name = "tls-creds",
-            .type = QEMU_OPT_STRING,
-            .help = "ID of the TLS credentials to use",
-        },
-    },
-};
-
 static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
                     Error **errp)
 {
     BDRVNBDState *s = bs->opaque;
-    QemuOpts *opts = NULL;
-    Error *local_err = NULL;
-    QIOChannelSocket *sioc = NULL;
-    QCryptoTLSCreds *tlscreds = NULL;
-    const char *hostname = NULL;
-    int ret = -EINVAL;
-
-    opts = qemu_opts_create(&nbd_runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        goto error;
-    }
-
-    /* Translate @host, @port, and @path to a SocketAddress */
-    if (!nbd_process_legacy_socket_options(options, opts, errp)) {
-        goto error;
-    }
+    char *export = NULL;
+    int result, sock;
+    SocketAddress *saddr;
 
     /* Pop the config into our state object. Exit if invalid. */
-    s->saddr = nbd_config(s, options, errp);
-    if (!s->saddr) {
-        goto error;
-    }
-
-    s->export = g_strdup(qemu_opt_get(opts, "export"));
-
-    s->tlscredsid = g_strdup(qemu_opt_get(opts, "tls-creds"));
-    if (s->tlscredsid) {
-        tlscreds = nbd_get_tls_creds(s->tlscredsid, errp);
-        if (!tlscreds) {
-            goto error;
-        }
-
-        /* TODO SOCKET_ADDRESS_KIND_FD where fd has AF_INET or AF_INET6 */
-        if (s->saddr->type != SOCKET_ADDRESS_TYPE_INET) {
-            error_setg(errp, "TLS only supported over IP sockets");
-            goto error;
-        }
-        hostname = s->saddr->u.inet.host;
+    saddr = nbd_config(s, options, &export, errp);
+    if (!saddr) {
+        return -EINVAL;
     }
 
     /* establish TCP connection, return error if it fails
      * TODO: Configurable retry-until-timeout behaviour.
      */
-    sioc = nbd_establish_connection(s->saddr, errp);
-    if (!sioc) {
-        ret = -ECONNREFUSED;
-        goto error;
+    sock = nbd_establish_connection(bs, saddr, errp);
+    qapi_free_SocketAddress(saddr);
+    if (sock < 0) {
+        g_free(export);
+        return sock;
     }
 
     /* NBD handshake */
-    ret = nbd_client_init(bs, sioc, s->export,
-                          tlscreds, hostname, errp);
- error:
-    if (sioc) {
-        object_unref(OBJECT(sioc));
-    }
-    if (tlscreds) {
-        object_unref(OBJECT(tlscreds));
-    }
-    if (ret < 0) {
-        qapi_free_SocketAddress(s->saddr);
-        g_free(s->export);
-        g_free(s->tlscredsid);
-    }
-    qemu_opts_del(opts);
-    return ret;
+    result = nbd_client_init(bs, sock, export, errp);
+    g_free(export);
+    return result;
+}
+
+static int nbd_co_readv(BlockDriverState *bs, int64_t sector_num,
+                        int nb_sectors, QEMUIOVector *qiov)
+{
+    return nbd_client_co_readv(bs, sector_num, nb_sectors, qiov);
+}
+
+static int nbd_co_writev(BlockDriverState *bs, int64_t sector_num,
+                         int nb_sectors, QEMUIOVector *qiov)
+{
+    return nbd_client_co_writev(bs, sector_num, nb_sectors, qiov);
 }
 
 static int nbd_co_flush(BlockDriverState *bs)
@@ -472,20 +309,19 @@ static int nbd_co_flush(BlockDriverState *bs)
 
 static void nbd_refresh_limits(BlockDriverState *bs, Error **errp)
 {
-    bs->bl.max_pdiscard = NBD_MAX_BUFFER_SIZE;
-    bs->bl.max_pwrite_zeroes = NBD_MAX_BUFFER_SIZE;
-    bs->bl.max_transfer = NBD_MAX_BUFFER_SIZE;
+    bs->bl.max_discard = UINT32_MAX >> BDRV_SECTOR_BITS;
+    bs->bl.max_transfer_length = UINT32_MAX >> BDRV_SECTOR_BITS;
+}
+
+static int nbd_co_discard(BlockDriverState *bs, int64_t sector_num,
+                          int nb_sectors)
+{
+    return nbd_client_co_discard(bs, sector_num, nb_sectors);
 }
 
 static void nbd_close(BlockDriverState *bs)
 {
-    BDRVNBDState *s = bs->opaque;
-
     nbd_client_close(bs);
-
-    qapi_free_SocketAddress(s->saddr);
-    g_free(s->export);
-    g_free(s->tlscredsid);
 }
 
 static int64_t nbd_getlength(BlockDriverState *bs)
@@ -506,54 +342,48 @@ static void nbd_attach_aio_context(BlockDriverState *bs,
     nbd_client_attach_aio_context(bs, new_context);
 }
 
-static void nbd_refresh_filename(BlockDriverState *bs, QDict *options)
+static void nbd_refresh_filename(BlockDriverState *bs)
 {
-    BDRVNBDState *s = bs->opaque;
     QDict *opts = qdict_new();
-    QObject *saddr_qdict;
-    Visitor *ov;
-    const char *host = NULL, *port = NULL, *path = NULL;
+    const char *path   = qdict_get_try_str(bs->options, "path");
+    const char *host   = qdict_get_try_str(bs->options, "host");
+    const char *port   = qdict_get_try_str(bs->options, "port");
+    const char *export = qdict_get_try_str(bs->options, "export");
 
-    if (s->saddr->type == SOCKET_ADDRESS_TYPE_INET) {
-        const InetSocketAddress *inet = &s->saddr->u.inet;
-        if (!inet->has_ipv4 && !inet->has_ipv6 && !inet->has_to) {
-            host = inet->host;
-            port = inet->port;
-        }
-    } else if (s->saddr->type == SOCKET_ADDRESS_TYPE_UNIX) {
-        path = s->saddr->u.q_unix.path;
-    } /* else can't represent as pseudo-filename */
+    qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("nbd")));
 
-    qdict_put_str(opts, "driver", "nbd");
-
-    if (path && s->export) {
+    if (path && export) {
         snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "nbd+unix:///%s?socket=%s", s->export, path);
-    } else if (path && !s->export) {
+                 "nbd+unix:///%s?socket=%s", export, path);
+    } else if (path && !export) {
         snprintf(bs->exact_filename, sizeof(bs->exact_filename),
                  "nbd+unix://?socket=%s", path);
-    } else if (host && s->export) {
+    } else if (!path && export && port) {
         snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "nbd://%s:%s/%s", host, port, s->export);
-    } else if (host && !s->export) {
+                 "nbd://%s:%s/%s", host, port, export);
+    } else if (!path && export && !port) {
+        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
+                 "nbd://%s/%s", host, export);
+    } else if (!path && !export && port) {
         snprintf(bs->exact_filename, sizeof(bs->exact_filename),
                  "nbd://%s:%s", host, port);
+    } else if (!path && !export && !port) {
+        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
+                 "nbd://%s", host);
     }
 
-    ov = qobject_output_visitor_new(&saddr_qdict);
-    visit_type_SocketAddress(ov, NULL, &s->saddr, &error_abort);
-    visit_complete(ov, &saddr_qdict);
-    visit_free(ov);
-    qdict_put_obj(opts, "server", saddr_qdict);
-
-    if (s->export) {
-        qdict_put_str(opts, "export", s->export);
+    if (path) {
+        qdict_put_obj(opts, "path", QOBJECT(qstring_from_str(path)));
+    } else if (port) {
+        qdict_put_obj(opts, "host", QOBJECT(qstring_from_str(host)));
+        qdict_put_obj(opts, "port", QOBJECT(qstring_from_str(port)));
+    } else {
+        qdict_put_obj(opts, "host", QOBJECT(qstring_from_str(host)));
     }
-    if (s->tlscredsid) {
-        qdict_put_str(opts, "tls-creds", s->tlscredsid);
+    if (export) {
+        qdict_put_obj(opts, "export", QOBJECT(qstring_from_str(export)));
     }
 
-    qdict_flatten(opts);
     bs->full_open_options = opts;
 }
 
@@ -563,12 +393,11 @@ static BlockDriver bdrv_nbd = {
     .instance_size              = sizeof(BDRVNBDState),
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
-    .bdrv_co_preadv             = nbd_client_co_preadv,
-    .bdrv_co_pwritev            = nbd_client_co_pwritev,
-    .bdrv_co_pwrite_zeroes      = nbd_client_co_pwrite_zeroes,
+    .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_pdiscard           = nbd_client_co_pdiscard,
+    .bdrv_co_discard            = nbd_co_discard,
     .bdrv_refresh_limits        = nbd_refresh_limits,
     .bdrv_getlength             = nbd_getlength,
     .bdrv_detach_aio_context    = nbd_detach_aio_context,
@@ -582,12 +411,11 @@ static BlockDriver bdrv_nbd_tcp = {
     .instance_size              = sizeof(BDRVNBDState),
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
-    .bdrv_co_preadv             = nbd_client_co_preadv,
-    .bdrv_co_pwritev            = nbd_client_co_pwritev,
-    .bdrv_co_pwrite_zeroes      = nbd_client_co_pwrite_zeroes,
+    .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_pdiscard           = nbd_client_co_pdiscard,
+    .bdrv_co_discard            = nbd_co_discard,
     .bdrv_refresh_limits        = nbd_refresh_limits,
     .bdrv_getlength             = nbd_getlength,
     .bdrv_detach_aio_context    = nbd_detach_aio_context,
@@ -601,12 +429,11 @@ static BlockDriver bdrv_nbd_unix = {
     .instance_size              = sizeof(BDRVNBDState),
     .bdrv_parse_filename        = nbd_parse_filename,
     .bdrv_file_open             = nbd_open,
-    .bdrv_co_preadv             = nbd_client_co_preadv,
-    .bdrv_co_pwritev            = nbd_client_co_pwritev,
-    .bdrv_co_pwrite_zeroes      = nbd_client_co_pwrite_zeroes,
+    .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_pdiscard           = nbd_client_co_pdiscard,
+    .bdrv_co_discard            = nbd_co_discard,
     .bdrv_refresh_limits        = nbd_refresh_limits,
     .bdrv_getlength             = nbd_getlength,
     .bdrv_detach_aio_context    = nbd_detach_aio_context,

block/nfs.c

@@ -1,7 +1,7 @@
 /*
  * QEMU Block driver for native access to files on NFS shares
  *
- * Copyright (c) 2014-2016 Peter Lieven <pl@kamp.de>
+ * Copyright (c) 2014 Peter Lieven <pl@kamp.de>
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this software and associated documentation files (the "Software"), to deal
@@ -22,30 +22,20 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
+#include "config-host.h"
 
 #include <poll.h>
 #include "qemu-common.h"
 #include "qemu/config-file.h"
 #include "qemu/error-report.h"
-#include "qapi/error.h"
 #include "block/block_int.h"
 #include "trace.h"
 #include "qemu/iov.h"
 #include "qemu/uri.h"
-#include "qemu/cutils.h"
 #include "sysemu/sysemu.h"
-#include "qapi/qmp/qdict.h"
-#include "qapi/qmp/qstring.h"
-#include "qapi-visit.h"
-#include "qapi/qobject-input-visitor.h"
-#include "qapi/qobject-output-visitor.h"
 #include <nfsc/libnfs.h>
 
-
 #define QEMU_NFS_MAX_READAHEAD_SIZE 1048576
-#define QEMU_NFS_MAX_PAGECACHE_SIZE (8388608 / NFS_BLKSIZE)
-#define QEMU_NFS_MAX_DEBUG_LEVEL 2
 
 typedef struct NFSClient {
     struct nfs_context *context;
@@ -53,139 +43,22 @@ typedef struct NFSClient {
     int events;
     bool has_zero_init;
     AioContext *aio_context;
-    QemuMutex mutex;
     blkcnt_t st_blocks;
-    bool cache_used;
-    NFSServer *server;
-    char *path;
-    int64_t uid, gid, tcp_syncnt, readahead, pagecache, debug;
 } NFSClient;
 
 typedef struct NFSRPC {
-    BlockDriverState *bs;
     int ret;
     int complete;
     QEMUIOVector *iov;
     struct stat *st;
     Coroutine *co;
+    QEMUBH *bh;
     NFSClient *client;
 } NFSRPC;
 
-static int nfs_parse_uri(const char *filename, QDict *options, Error **errp)
-{
-    URI *uri = NULL;
-    QueryParams *qp = NULL;
-    int ret = -EINVAL, i;
-
-    uri = uri_parse(filename);
-    if (!uri) {
-        error_setg(errp, "Invalid URI specified");
-        goto out;
-    }
-    if (strcmp(uri->scheme, "nfs") != 0) {
-        error_setg(errp, "URI scheme must be 'nfs'");
-        goto out;
-    }
-
-    if (!uri->server) {
-        error_setg(errp, "missing hostname in URI");
-        goto out;
-    }
-
-    if (!uri->path) {
-        error_setg(errp, "missing file path in URI");
-        goto out;
-    }
-
-    qp = query_params_parse(uri->query);
-    if (!qp) {
-        error_setg(errp, "could not parse query parameters");
-        goto out;
-    }
-
-    qdict_put_str(options, "server.host", uri->server);
-    qdict_put_str(options, "server.type", "inet");
-    qdict_put_str(options, "path", uri->path);
-
-    for (i = 0; i < qp->n; i++) {
-        unsigned long long val;
-        if (!qp->p[i].value) {
-            error_setg(errp, "Value for NFS parameter expected: %s",
-                       qp->p[i].name);
-            goto out;
-        }
-        if (parse_uint_full(qp->p[i].value, &val, 0)) {
-            error_setg(errp, "Illegal value for NFS parameter: %s",
-                       qp->p[i].name);
-            goto out;
-        }
-        if (!strcmp(qp->p[i].name, "uid")) {
-            qdict_put_str(options, "user", qp->p[i].value);
-        } else if (!strcmp(qp->p[i].name, "gid")) {
-            qdict_put_str(options, "group", qp->p[i].value);
-        } else if (!strcmp(qp->p[i].name, "tcp-syncnt")) {
-            qdict_put_str(options, "tcp-syn-count", qp->p[i].value);
-        } else if (!strcmp(qp->p[i].name, "readahead")) {
-            qdict_put_str(options, "readahead-size", qp->p[i].value);
-        } else if (!strcmp(qp->p[i].name, "pagecache")) {
-            qdict_put_str(options, "page-cache-size", qp->p[i].value);
-        } else if (!strcmp(qp->p[i].name, "debug")) {
-            qdict_put_str(options, "debug", qp->p[i].value);
-        } else {
-            error_setg(errp, "Unknown NFS parameter name: %s",
-                       qp->p[i].name);
-            goto out;
-        }
-    }
-    ret = 0;
-out:
-    if (qp) {
-        query_params_free(qp);
-    }
-    if (uri) {
-        uri_free(uri);
-    }
-    return ret;
-}
-
-static bool nfs_has_filename_options_conflict(QDict *options, Error **errp)
-{
-    const QDictEntry *qe;
-
-    for (qe = qdict_first(options); qe; qe = qdict_next(options, qe)) {
-        if (!strcmp(qe->key, "host") ||
-            !strcmp(qe->key, "path") ||
-            !strcmp(qe->key, "user") ||
-            !strcmp(qe->key, "group") ||
-            !strcmp(qe->key, "tcp-syn-count") ||
-            !strcmp(qe->key, "readahead-size") ||
-            !strcmp(qe->key, "page-cache-size") ||
-            !strcmp(qe->key, "debug") ||
-            strstart(qe->key, "server.", NULL))
-        {
-            error_setg(errp, "Option %s cannot be used with a filename",
-                       qe->key);
-            return true;
-        }
-    }
-
-    return false;
-}
-
-static void nfs_parse_filename(const char *filename, QDict *options,
-                               Error **errp)
-{
-    if (nfs_has_filename_options_conflict(options, errp)) {
-        return;
-    }
-
-    nfs_parse_uri(filename, options, errp);
-}
-
 static void nfs_process_read(void *arg);
 static void nfs_process_write(void *arg);
 
-/* Called with QemuMutex held.  */
 static void nfs_set_events(NFSClient *client)
 {
     int ev = nfs_which_events(client->context);
@@ -193,8 +66,7 @@ static void nfs_set_events(NFSClient *client)
         aio_set_fd_handler(client->aio_context, nfs_get_fd(client->context),
                            false,
                            (ev & POLLIN) ? nfs_process_read : NULL,
-                           (ev & POLLOUT) ? nfs_process_write : NULL,
-                           NULL, client);
+                           (ev & POLLOUT) ? nfs_process_write : NULL, client);
 
     }
     client->events = ev;
@@ -203,48 +75,39 @@ static void nfs_set_events(NFSClient *client)
 static void nfs_process_read(void *arg)
 {
     NFSClient *client = arg;
-
-    qemu_mutex_lock(&client->mutex);
     nfs_service(client->context, POLLIN);
     nfs_set_events(client);
-    qemu_mutex_unlock(&client->mutex);
 }
 
 static void nfs_process_write(void *arg)
 {
     NFSClient *client = arg;
-
-    qemu_mutex_lock(&client->mutex);
     nfs_service(client->context, POLLOUT);
     nfs_set_events(client);
-    qemu_mutex_unlock(&client->mutex);
 }
 
-static void nfs_co_init_task(BlockDriverState *bs, NFSRPC *task)
+static void nfs_co_init_task(NFSClient *client, NFSRPC *task)
 {
     *task = (NFSRPC) {
         .co             = qemu_coroutine_self(),
-        .bs             = bs,
-        .client         = bs->opaque,
+        .client         = client,
     };
 }
 
 static void nfs_co_generic_bh_cb(void *opaque)
 {
     NFSRPC *task = opaque;
-
     task->complete = 1;
-    aio_co_wake(task->co);
+    qemu_bh_delete(task->bh);
+    qemu_coroutine_enter(task->co, NULL);
 }
 
-/* Called (via nfs_service) with QemuMutex held.  */
 static void
 nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
                   void *private_data)
 {
     NFSRPC *task = private_data;
     task->ret = ret;
-    assert(!task->st);
     if (task->ret > 0 && task->iov) {
         if (task->ret <= task->iov->size) {
             qemu_iovec_from_buf(task->iov, 0, data, task->ret);
@@ -252,33 +115,40 @@ nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
             task->ret = -EIO;
         }
     }
+    if (task->ret == 0 && task->st) {
+        memcpy(task->st, data, sizeof(struct stat));
+    }
     if (task->ret < 0) {
         error_report("NFS Error: %s", nfs_get_error(nfs));
     }
-    aio_bh_schedule_oneshot(task->client->aio_context,
-                            nfs_co_generic_bh_cb, task);
+    if (task->co) {
+        task->bh = aio_bh_new(task->client->aio_context,
+                              nfs_co_generic_bh_cb, task);
+        qemu_bh_schedule(task->bh);
+    } else {
+        task->complete = 1;
+    }
 }
 
-static int coroutine_fn nfs_co_preadv(BlockDriverState *bs, uint64_t offset,
-                                      uint64_t bytes, QEMUIOVector *iov,
-                                      int flags)
+static int coroutine_fn nfs_co_readv(BlockDriverState *bs,
+                                     int64_t sector_num, int nb_sectors,
+                                     QEMUIOVector *iov)
 {
     NFSClient *client = bs->opaque;
     NFSRPC task;
 
-    nfs_co_init_task(bs, &task);
+    nfs_co_init_task(client, &task);
     task.iov = iov;
 
-    qemu_mutex_lock(&client->mutex);
     if (nfs_pread_async(client->context, client->fh,
-                        offset, bytes, nfs_co_generic_cb, &task) != 0) {
-        qemu_mutex_unlock(&client->mutex);
+                        sector_num * BDRV_SECTOR_SIZE,
+                        nb_sectors * BDRV_SECTOR_SIZE,
+                        nfs_co_generic_cb, &task) != 0) {
         return -ENOMEM;
     }
 
-    nfs_set_events(client);
-    qemu_mutex_unlock(&client->mutex);
     while (!task.complete) {
+        nfs_set_events(client);
         qemu_coroutine_yield();
     }
 
@@ -294,50 +164,39 @@ static int coroutine_fn nfs_co_preadv(BlockDriverState *bs, uint64_t offset,
     return 0;
 }
 
-static int coroutine_fn nfs_co_pwritev(BlockDriverState *bs, uint64_t offset,
-                                       uint64_t bytes, QEMUIOVector *iov,
-                                       int flags)
+static int coroutine_fn nfs_co_writev(BlockDriverState *bs,
+                                        int64_t sector_num, int nb_sectors,
+                                        QEMUIOVector *iov)
 {
     NFSClient *client = bs->opaque;
     NFSRPC task;
     char *buf = NULL;
-    bool my_buffer = false;
 
-    nfs_co_init_task(bs, &task);
+    nfs_co_init_task(client, &task);
 
-    if (iov->niov != 1) {
-        buf = g_try_malloc(bytes);
-        if (bytes && buf == NULL) {
-            return -ENOMEM;
-        }
-        qemu_iovec_to_buf(iov, 0, buf, bytes);
-        my_buffer = true;
-    } else {
-        buf = iov->iov[0].iov_base;
-    }
-
-    qemu_mutex_lock(&client->mutex);
-    if (nfs_pwrite_async(client->context, client->fh,
-                         offset, bytes, buf,
-                         nfs_co_generic_cb, &task) != 0) {
-        qemu_mutex_unlock(&client->mutex);
-        if (my_buffer) {
-            g_free(buf);
-        }
+    buf = g_try_malloc(nb_sectors * BDRV_SECTOR_SIZE);
+    if (nb_sectors && buf == NULL) {
+        return -ENOMEM;
+    }
+
+    qemu_iovec_to_buf(iov, 0, buf, nb_sectors * BDRV_SECTOR_SIZE);
+
+    if (nfs_pwrite_async(client->context, client->fh,
+                         sector_num * BDRV_SECTOR_SIZE,
+                         nb_sectors * BDRV_SECTOR_SIZE,
+                         buf, nfs_co_generic_cb, &task) != 0) {
+        g_free(buf);
         return -ENOMEM;
     }
 
-    nfs_set_events(client);
-    qemu_mutex_unlock(&client->mutex);
     while (!task.complete) {
+        nfs_set_events(client);
         qemu_coroutine_yield();
     }
 
-    if (my_buffer) {
-        g_free(buf);
-    }
+    g_free(buf);
 
-    if (task.ret != bytes) {
+    if (task.ret != nb_sectors * BDRV_SECTOR_SIZE) {
         return task.ret < 0 ? task.ret : -EIO;
     }
 
@@ -349,62 +208,30 @@ static int coroutine_fn nfs_co_flush(BlockDriverState *bs)
     NFSClient *client = bs->opaque;
     NFSRPC task;
 
-    nfs_co_init_task(bs, &task);
+    nfs_co_init_task(client, &task);
 
-    qemu_mutex_lock(&client->mutex);
     if (nfs_fsync_async(client->context, client->fh, nfs_co_generic_cb,
                         &task) != 0) {
-        qemu_mutex_unlock(&client->mutex);
         return -ENOMEM;
     }
 
-    nfs_set_events(client);
-    qemu_mutex_unlock(&client->mutex);
     while (!task.complete) {
+        nfs_set_events(client);
         qemu_coroutine_yield();
     }
 
     return task.ret;
 }
 
+/* TODO Convert to fine grained options */
 static QemuOptsList runtime_opts = {
     .name = "nfs",
     .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
     .desc = {
         {
-            .name = "path",
+            .name = "filename",
             .type = QEMU_OPT_STRING,
-            .help = "Path of the image on the host",
-        },
-        {
-            .name = "user",
-            .type = QEMU_OPT_NUMBER,
-            .help = "UID value to use when talking to the server",
-        },
-        {
-            .name = "group",
-            .type = QEMU_OPT_NUMBER,
-            .help = "GID value to use when talking to the server",
-        },
-        {
-            .name = "tcp-syn-count",
-            .type = QEMU_OPT_NUMBER,
-            .help = "Number of SYNs to send during the session establish",
-        },
-        {
-            .name = "readahead-size",
-            .type = QEMU_OPT_NUMBER,
-            .help = "Set the readahead size in bytes",
-        },
-        {
-            .name = "page-cache-size",
-            .type = QEMU_OPT_NUMBER,
-            .help = "Set the pagecache size in bytes",
-        },
-        {
-            .name = "debug",
-            .type = QEMU_OPT_NUMBER,
-            .help = "Set the NFS debug level (max 2)",
+            .help = "URL to the NFS file",
         },
         { /* end of list */ }
     },
@@ -415,7 +242,7 @@ static void nfs_detach_aio_context(BlockDriverState *bs)
     NFSClient *client = bs->opaque;
 
     aio_set_fd_handler(client->aio_context, nfs_get_fd(client->context),
-                       false, NULL, NULL, NULL, NULL);
+                       false, NULL, NULL, NULL);
     client->events = 0;
 }
 
@@ -435,7 +262,7 @@ static void nfs_client_close(NFSClient *client)
             nfs_close(client->context, client->fh);
         }
         aio_set_fd_handler(client->aio_context, nfs_get_fd(client->context),
-                           false, NULL, NULL, NULL, NULL);
+                           false, NULL, NULL, NULL);
         nfs_destroy_context(client->context);
     }
     memset(client, 0, sizeof(NFSClient));
@@ -445,75 +272,27 @@ static void nfs_file_close(BlockDriverState *bs)
 {
     NFSClient *client = bs->opaque;
     nfs_client_close(client);
-    qemu_mutex_destroy(&client->mutex);
 }
 
-static NFSServer *nfs_config(QDict *options, Error **errp)
+static int64_t nfs_client_open(NFSClient *client, const char *filename,
+                               int flags, Error **errp)
 {
-    NFSServer *server = NULL;
-    QDict *addr = NULL;
-    QObject *crumpled_addr = NULL;
-    Visitor *iv = NULL;
-    Error *local_error = NULL;
-
-    qdict_extract_subqdict(options, &addr, "server.");
-    if (!qdict_size(addr)) {
-        error_setg(errp, "NFS server address missing");
-        goto out;
-    }
-
-    crumpled_addr = qdict_crumple(addr, errp);
-    if (!crumpled_addr) {
-        goto out;
-    }
-
-    /*
-     * Caution: this works only because all scalar members of
-     * NFSServer are QString in @crumpled_addr.  The visitor expects
-     * @crumpled_addr to be typed according to the QAPI schema.  It
-     * is when @options come from -blockdev or blockdev_add.  But when
-     * they come from -drive, they're all QString.
-     */
-    iv = qobject_input_visitor_new(crumpled_addr);
-    visit_type_NFSServer(iv, NULL, &server, &local_error);
-    if (local_error) {
-        error_propagate(errp, local_error);
-        goto out;
-    }
-
-out:
-    QDECREF(addr);
-    qobject_decref(crumpled_addr);
-    visit_free(iv);
-    return server;
-}
-
-
-static int64_t nfs_client_open(NFSClient *client, QDict *options,
-                               int flags, int open_flags, Error **errp)
-{
-    int ret = -EINVAL;
-    QemuOpts *opts = NULL;
-    Error *local_err = NULL;
+    int ret = -EINVAL, i;
     struct stat st;
+    URI *uri;
+    QueryParams *qp = NULL;
     char *file = NULL, *strp = NULL;
 
-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
+    uri = uri_parse(filename);
+    if (!uri) {
+        error_setg(errp, "Invalid URL specified");
         goto fail;
     }
-
-    client->path = g_strdup(qemu_opt_get(opts, "path"));
-    if (!client->path) {
-        ret = -EINVAL;
-        error_setg(errp, "No path was specified");
+    if (!uri->server) {
+        error_setg(errp, "Invalid URL specified");
         goto fail;
     }
-
-    strp = strrchr(client->path, '/');
+    strp = strrchr(uri->path, '/');
     if (strp == NULL) {
         error_setg(errp, "Invalid URL specified");
         goto fail;
@@ -521,89 +300,48 @@ static int64_t nfs_client_open(NFSClient *client, QDict *options,
     file = g_strdup(strp);
     *strp = 0;
 
-    /* Pop the config into our state object, Exit if invalid */
-    client->server = nfs_config(options, errp);
-    if (!client->server) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
     client->context = nfs_init_context();
     if (client->context == NULL) {
         error_setg(errp, "Failed to init NFS context");
         goto fail;
     }
 
-    if (qemu_opt_get(opts, "user")) {
-        client->uid = qemu_opt_get_number(opts, "user", 0);
-        nfs_set_uid(client->context, client->uid);
-    }
-
-    if (qemu_opt_get(opts, "group")) {
-        client->gid = qemu_opt_get_number(opts, "group", 0);
-        nfs_set_gid(client->context, client->gid);
-    }
-
-    if (qemu_opt_get(opts, "tcp-syn-count")) {
-        client->tcp_syncnt = qemu_opt_get_number(opts, "tcp-syn-count", 0);
-        nfs_set_tcp_syncnt(client->context, client->tcp_syncnt);
-    }
-
+    qp = query_params_parse(uri->query);
+    for (i = 0; i < qp->n; i++) {
+        unsigned long long val;
+        if (!qp->p[i].value) {
+            error_setg(errp, "Value for NFS parameter expected: %s",
+                       qp->p[i].name);
+            goto fail;
+        }
+        if (parse_uint_full(qp->p[i].value, &val, 0)) {
+            error_setg(errp, "Illegal value for NFS parameter: %s",
+                       qp->p[i].name);
+            goto fail;
+        }
+        if (!strcmp(qp->p[i].name, "uid")) {
+            nfs_set_uid(client->context, val);
+        } else if (!strcmp(qp->p[i].name, "gid")) {
+            nfs_set_gid(client->context, val);
+        } else if (!strcmp(qp->p[i].name, "tcp-syncnt")) {
+            nfs_set_tcp_syncnt(client->context, val);
 #ifdef LIBNFS_FEATURE_READAHEAD
-    if (qemu_opt_get(opts, "readahead-size")) {
-        if (open_flags & BDRV_O_NOCACHE) {
-            error_setg(errp, "Cannot enable NFS readahead "
-                             "if cache.direct = on");
+        } else if (!strcmp(qp->p[i].name, "readahead")) {
+            if (val > QEMU_NFS_MAX_READAHEAD_SIZE) {
+                error_report("NFS Warning: Truncating NFS readahead"
+                             " size to %d", QEMU_NFS_MAX_READAHEAD_SIZE);
+                val = QEMU_NFS_MAX_READAHEAD_SIZE;
+            }
+            nfs_set_readahead(client->context, val);
+#endif
+        } else {
+            error_setg(errp, "Unknown NFS parameter name: %s",
+                       qp->p[i].name);
             goto fail;
         }
-        client->readahead = qemu_opt_get_number(opts, "readahead-size", 0);
-        if (client->readahead > QEMU_NFS_MAX_READAHEAD_SIZE) {
-            error_report("NFS Warning: Truncating NFS readahead "
-                         "size to %d", QEMU_NFS_MAX_READAHEAD_SIZE);
-            client->readahead = QEMU_NFS_MAX_READAHEAD_SIZE;
-        }
-        nfs_set_readahead(client->context, client->readahead);
-#ifdef LIBNFS_FEATURE_PAGECACHE
-        nfs_set_pagecache_ttl(client->context, 0);
-#endif
-        client->cache_used = true;
     }
-#endif
 
-#ifdef LIBNFS_FEATURE_PAGECACHE
-    if (qemu_opt_get(opts, "page-cache-size")) {
-        if (open_flags & BDRV_O_NOCACHE) {
-            error_setg(errp, "Cannot enable NFS pagecache "
-                             "if cache.direct = on");
-            goto fail;
-        }
-        client->pagecache = qemu_opt_get_number(opts, "page-cache-size", 0);
-        if (client->pagecache > QEMU_NFS_MAX_PAGECACHE_SIZE) {
-            error_report("NFS Warning: Truncating NFS pagecache "
-                         "size to %d pages", QEMU_NFS_MAX_PAGECACHE_SIZE);
-            client->pagecache = QEMU_NFS_MAX_PAGECACHE_SIZE;
-        }
-        nfs_set_pagecache(client->context, client->pagecache);
-        nfs_set_pagecache_ttl(client->context, 0);
-        client->cache_used = true;
-    }
-#endif
-
-#ifdef LIBNFS_FEATURE_DEBUG
-    if (qemu_opt_get(opts, "debug")) {
-        client->debug = qemu_opt_get_number(opts, "debug", 0);
-        /* limit the maximum debug level to avoid potential flooding
-         * of our log files. */
-        if (client->debug > QEMU_NFS_MAX_DEBUG_LEVEL) {
-            error_report("NFS Warning: Limiting NFS debug level "
-                         "to %d", QEMU_NFS_MAX_DEBUG_LEVEL);
-            client->debug = QEMU_NFS_MAX_DEBUG_LEVEL;
-        }
-        nfs_set_debug(client->context, client->debug);
-    }
-#endif
-
-    ret = nfs_mount(client->context, client->server->host, client->path);
+    ret = nfs_mount(client->context, uri->server, uri->path);
     if (ret < 0) {
         error_setg(errp, "Failed to mount nfs share: %s",
                    nfs_get_error(client->context));
@@ -636,13 +374,14 @@ static int64_t nfs_client_open(NFSClient *client, QDict *options,
     ret = DIV_ROUND_UP(st.st_size, BDRV_SECTOR_SIZE);
     client->st_blocks = st.st_blocks;
     client->has_zero_init = S_ISREG(st.st_mode);
-    *strp = '/';
     goto out;
-
 fail:
     nfs_client_close(client);
 out:
-    qemu_opts_del(opts);
+    if (qp) {
+        query_params_free(qp);
+    }
+    uri_free(uri);
     g_free(file);
     return ret;
 }
@@ -651,18 +390,28 @@ static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
                          Error **errp) {
     NFSClient *client = bs->opaque;
     int64_t ret;
+    QemuOpts *opts;
+    Error *local_err = NULL;
 
     client->aio_context = bdrv_get_aio_context(bs);
 
-    ret = nfs_client_open(client, options,
-                          (flags & BDRV_O_RDWR) ? O_RDWR : O_RDONLY,
-                          bs->open_flags, errp);
-    if (ret < 0) {
-        return ret;
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    qemu_opts_absorb_qdict(opts, options, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto out;
+    }
+    ret = nfs_client_open(client, qemu_opt_get(opts, "filename"),
+                          (flags & BDRV_O_RDWR) ? O_RDWR : O_RDONLY,
+                          errp);
+    if (ret < 0) {
+        goto out;
     }
-    qemu_mutex_init(&client->mutex);
     bs->total_sectors = ret;
     ret = 0;
+out:
+    qemu_opts_del(opts);
     return ret;
 }
 
@@ -684,7 +433,6 @@ static int nfs_file_create(const char *url, QemuOpts *opts, Error **errp)
     int ret = 0;
     int64_t total_size = 0;
     NFSClient *client = g_new0(NFSClient, 1);
-    QDict *options = NULL;
 
     client->aio_context = qemu_get_aio_context();
 
@@ -692,20 +440,13 @@ static int nfs_file_create(const char *url, QemuOpts *opts, Error **errp)
     total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
                           BDRV_SECTOR_SIZE);
 
-    options = qdict_new();
-    ret = nfs_parse_uri(url, options, errp);
-    if (ret < 0) {
-        goto out;
-    }
-
-    ret = nfs_client_open(client, options, O_CREAT, 0, errp);
+    ret = nfs_client_open(client, url, O_CREAT, errp);
     if (ret < 0) {
         goto out;
     }
     ret = nfs_ftruncate(client->context, client->fh, total_size);
     nfs_client_close(client);
 out:
-    QDECREF(options);
     g_free(client);
     return ret;
 }
@@ -716,25 +457,6 @@ static int nfs_has_zero_init(BlockDriverState *bs)
     return client->has_zero_init;
 }
 
-/* Called (via nfs_service) with QemuMutex held.  */
-static void
-nfs_get_allocated_file_size_cb(int ret, struct nfs_context *nfs, void *data,
-                               void *private_data)
-{
-    NFSRPC *task = private_data;
-    task->ret = ret;
-    if (task->ret == 0) {
-        memcpy(task->st, data, sizeof(struct stat));
-    }
-    if (task->ret < 0) {
-        error_report("NFS Error: %s", nfs_get_error(nfs));
-    }
-
-    /* Set task->complete before reading bs->wakeup.  */
-    atomic_mb_set(&task->complete, 1);
-    bdrv_wakeup(task->bs);
-}
-
 static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
 {
     NFSClient *client = bs->opaque;
@@ -746,31 +468,24 @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
         return client->st_blocks * 512;
     }
 
-    task.bs = bs;
     task.st = &st;
-    if (nfs_fstat_async(client->context, client->fh, nfs_get_allocated_file_size_cb,
+    if (nfs_fstat_async(client->context, client->fh, nfs_co_generic_cb,
                         &task) != 0) {
         return -ENOMEM;
     }
 
-    nfs_set_events(client);
-    BDRV_POLL_WHILE(bs, !task.complete);
+    while (!task.complete) {
+        nfs_set_events(client);
+        aio_poll(client->aio_context, true);
+    }
 
     return (task.ret < 0 ? task.ret : st.st_blocks * 512);
 }
 
-static int nfs_file_truncate(BlockDriverState *bs, int64_t offset, Error **errp)
+static int nfs_file_truncate(BlockDriverState *bs, int64_t offset)
 {
     NFSClient *client = bs->opaque;
-    int ret;
-
-    ret = nfs_ftruncate(client->context, client->fh, offset);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Failed to truncate file");
-        return ret;
-    }
-
-    return 0;
+    return nfs_ftruncate(client->context, client->fh, offset);
 }
 
 /* Note that this will not re-establish a connection with the NFS server
@@ -787,12 +502,6 @@ static int nfs_reopen_prepare(BDRVReopenState *state,
         return -EACCES;
     }
 
-    if ((state->flags & BDRV_O_NOCACHE) && client->cache_used) {
-        error_setg(errp, "Cannot disable cache if libnfs readahead or"
-                         " pagecache is enabled");
-        return -EINVAL;
-    }
-
     /* Update cache for read-only reopens */
     if (!(state->flags & BDRV_O_RDWR)) {
         ret = nfs_fstat(client->context, client->fh, &st);
@@ -807,77 +516,12 @@ static int nfs_reopen_prepare(BDRVReopenState *state,
     return 0;
 }
 
-static void nfs_refresh_filename(BlockDriverState *bs, QDict *options)
-{
-    NFSClient *client = bs->opaque;
-    QDict *opts = qdict_new();
-    QObject *server_qdict;
-    Visitor *ov;
-
-    qdict_put_str(opts, "driver", "nfs");
-
-    if (client->uid && !client->gid) {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "nfs://%s%s?uid=%" PRId64, client->server->host, client->path,
-                 client->uid);
-    } else if (!client->uid && client->gid) {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "nfs://%s%s?gid=%" PRId64, client->server->host, client->path,
-                 client->gid);
-    } else if (client->uid && client->gid) {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "nfs://%s%s?uid=%" PRId64 "&gid=%" PRId64,
-                 client->server->host, client->path, client->uid, client->gid);
-    } else {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename),
-                 "nfs://%s%s", client->server->host, client->path);
-    }
-
-    ov = qobject_output_visitor_new(&server_qdict);
-    visit_type_NFSServer(ov, NULL, &client->server, &error_abort);
-    visit_complete(ov, &server_qdict);
-    qdict_put_obj(opts, "server", server_qdict);
-    qdict_put_str(opts, "path", client->path);
-
-    if (client->uid) {
-        qdict_put_int(opts, "user", client->uid);
-    }
-    if (client->gid) {
-        qdict_put_int(opts, "group", client->gid);
-    }
-    if (client->tcp_syncnt) {
-        qdict_put_int(opts, "tcp-syn-cnt", client->tcp_syncnt);
-    }
-    if (client->readahead) {
-        qdict_put_int(opts, "readahead-size", client->readahead);
-    }
-    if (client->pagecache) {
-        qdict_put_int(opts, "page-cache-size", client->pagecache);
-    }
-    if (client->debug) {
-        qdict_put_int(opts, "debug", client->debug);
-    }
-
-    visit_free(ov);
-    qdict_flatten(opts);
-    bs->full_open_options = opts;
-}
-
-#ifdef LIBNFS_FEATURE_PAGECACHE
-static void nfs_invalidate_cache(BlockDriverState *bs,
-                                 Error **errp)
-{
-    NFSClient *client = bs->opaque;
-    nfs_pagecache_invalidate(client->context, client->fh);
-}
-#endif
-
 static BlockDriver bdrv_nfs = {
     .format_name                    = "nfs",
     .protocol_name                  = "nfs",
 
     .instance_size                  = sizeof(NFSClient),
-    .bdrv_parse_filename            = nfs_parse_filename,
+    .bdrv_needs_filename            = true,
     .create_opts                    = &nfs_create_opts,
 
     .bdrv_has_zero_init             = nfs_has_zero_init,
@@ -889,17 +533,12 @@ static BlockDriver bdrv_nfs = {
     .bdrv_create                    = nfs_file_create,
     .bdrv_reopen_prepare            = nfs_reopen_prepare,
 
-    .bdrv_co_preadv                 = nfs_co_preadv,
-    .bdrv_co_pwritev                = nfs_co_pwritev,
+    .bdrv_co_readv                  = nfs_co_readv,
+    .bdrv_co_writev                 = nfs_co_writev,
     .bdrv_co_flush_to_disk          = nfs_co_flush,
 
     .bdrv_detach_aio_context        = nfs_detach_aio_context,
     .bdrv_attach_aio_context        = nfs_attach_aio_context,
-    .bdrv_refresh_filename          = nfs_refresh_filename,
-
-#ifdef LIBNFS_FEATURE_PAGECACHE
-    .bdrv_invalidate_cache          = nfs_invalidate_cache,
-#endif
 };
 
 static void nfs_block_init(void)

block/null.c

@@ -10,19 +10,13 @@
  * See the COPYING file in the top-level directory.
  */
 
-#include "qemu/osdep.h"
-#include "qapi/error.h"
-#include "qapi/qmp/qdict.h"
-#include "qapi/qmp/qstring.h"
 #include "block/block_int.h"
 
 #define NULL_OPT_LATENCY "latency-ns"
-#define NULL_OPT_ZEROES  "read-zeroes"
 
 typedef struct {
     int64_t length;
     int64_t latency_ns;
-    bool read_zeroes;
 } BDRVNullState;
 
 static QemuOptsList runtime_opts = {
@@ -45,11 +39,6 @@ static QemuOptsList runtime_opts = {
             .help = "nanoseconds (approximated) to wait "
                     "before completing request",
         },
-        {
-            .name = NULL_OPT_ZEROES,
-            .type = QEMU_OPT_BOOL,
-            .help = "return zeroes when read",
-        },
         { /* end of list */ }
     },
 };
@@ -71,7 +60,6 @@ static int null_file_open(BlockDriverState *bs, QDict *options, int flags,
         error_setg(errp, "latency-ns is invalid");
         ret = -EINVAL;
     }
-    s->read_zeroes = qemu_opt_get_bool(opts, NULL_OPT_ZEROES, false);
     qemu_opts_del(opts);
     return ret;
 }
@@ -101,12 +89,6 @@ static coroutine_fn int null_co_readv(BlockDriverState *bs,
                                       int64_t sector_num, int nb_sectors,
                                       QEMUIOVector *qiov)
 {
-    BDRVNullState *s = bs->opaque;
-
-    if (s->read_zeroes) {
-        qemu_iovec_memset(qiov, 0, 0, nb_sectors * BDRV_SECTOR_SIZE);
-    }
-
     return null_co_common(bs);
 }
 
@@ -124,6 +106,7 @@ static coroutine_fn int null_co_flush(BlockDriverState *bs)
 
 typedef struct {
     BlockAIOCB common;
+    QEMUBH *bh;
     QEMUTimer timer;
 } NullAIOCB;
 
@@ -135,6 +118,7 @@ static void null_bh_cb(void *opaque)
 {
     NullAIOCB *acb = opaque;
     acb->common.cb(acb->common.opaque, 0);
+    qemu_bh_delete(acb->bh);
     qemu_aio_unref(acb);
 }
 
@@ -162,7 +146,8 @@ static inline BlockAIOCB *null_aio_common(BlockDriverState *bs,
         timer_mod_ns(&acb->timer,
                      qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + s->latency_ns);
     } else {
-        aio_bh_schedule_oneshot(bdrv_get_aio_context(bs), null_bh_cb, acb);
+        acb->bh = aio_bh_new(bdrv_get_aio_context(bs), null_bh_cb, acb);
+        qemu_bh_schedule(acb->bh);
     }
     return &acb->common;
 }
@@ -173,12 +158,6 @@ static BlockAIOCB *null_aio_readv(BlockDriverState *bs,
                                   BlockCompletionFunc *cb,
                                   void *opaque)
 {
-    BDRVNullState *s = bs->opaque;
-
-    if (s->read_zeroes) {
-        qemu_iovec_memset(qiov, 0, 0, nb_sectors * BDRV_SECTOR_SIZE);
-    }
-
     return null_aio_common(bs, cb, opaque);
 }
 
@@ -204,38 +183,6 @@ static int null_reopen_prepare(BDRVReopenState *reopen_state,
     return 0;
 }
 
-static int64_t coroutine_fn null_co_get_block_status(BlockDriverState *bs,
-                                                     int64_t sector_num,
-                                                     int nb_sectors, int *pnum,
-                                                     BlockDriverState **file)
-{
-    BDRVNullState *s = bs->opaque;
-    off_t start = sector_num * BDRV_SECTOR_SIZE;
-
-    *pnum = nb_sectors;
-    *file = bs;
-
-    if (s->read_zeroes) {
-        return BDRV_BLOCK_OFFSET_VALID | start | BDRV_BLOCK_ZERO;
-    } else {
-        return BDRV_BLOCK_OFFSET_VALID | start;
-    }
-}
-
-static void null_refresh_filename(BlockDriverState *bs, QDict *opts)
-{
-    QINCREF(opts);
-    qdict_del(opts, "filename");
-
-    if (!qdict_size(opts)) {
-        snprintf(bs->exact_filename, sizeof(bs->exact_filename), "%s://",
-                 bs->drv->format_name);
-    }
-
-    qdict_put_str(opts, "driver", bs->drv->format_name);
-    bs->full_open_options = opts;
-}
-
 static BlockDriver bdrv_null_co = {
     .format_name            = "null-co",
     .protocol_name          = "null-co",
@@ -249,10 +196,6 @@ static BlockDriver bdrv_null_co = {
     .bdrv_co_writev         = null_co_writev,
     .bdrv_co_flush_to_disk  = null_co_flush,
     .bdrv_reopen_prepare    = null_reopen_prepare,
-
-    .bdrv_co_get_block_status   = null_co_get_block_status,
-
-    .bdrv_refresh_filename  = null_refresh_filename,
 };
 
 static BlockDriver bdrv_null_aio = {
@@ -268,10 +211,6 @@ static BlockDriver bdrv_null_aio = {
     .bdrv_aio_writev        = null_aio_writev,
     .bdrv_aio_flush         = null_aio_flush,
     .bdrv_reopen_prepare    = null_reopen_prepare,
-
-    .bdrv_co_get_block_status   = null_co_get_block_status,
-
-    .bdrv_refresh_filename  = null_refresh_filename,
 };
 
 static void bdrv_null_init(void)

block/parallels.c

@@ -27,13 +27,9 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
-#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
-#include "sysemu/block-backend.h"
 #include "qemu/module.h"
-#include "qemu/bswap.h"
 #include "qemu/bitmap.h"
 #include "qapi/util.h"
 
@@ -43,7 +39,6 @@
 #define HEADER_MAGIC2 "WithouFreSpacExt"
 #define HEADER_VERSION 2
 #define HEADER_INUSE_MAGIC  (0x746F6E59)
-#define MAX_PARALLELS_IMAGE_FACTOR (1ull << 32)
 
 #define DEFAULT_CLUSTER_SIZE 1048576        /* 1 MiB */
 
@@ -66,7 +61,7 @@ typedef struct ParallelsHeader {
 typedef enum ParallelsPreallocMode {
     PRL_PREALLOC_MODE_FALLOCATE = 0,
     PRL_PREALLOC_MODE_TRUNCATE = 1,
-    PRL_PREALLOC_MODE__MAX = 2,
+    PRL_PREALLOC_MODE_MAX = 2,
 } ParallelsPreallocMode;
 
 static const char *prealloc_mode_lookup[] = {
@@ -114,7 +109,7 @@ static QemuOptsList parallels_runtime_opts = {
             .name = PARALLELS_OPT_PREALLOC_SIZE,
             .type = QEMU_OPT_SIZE,
             .help = "Preallocation size on image expansion",
-            .def_value_str = "128M",
+            .def_value_str = "128MiB",
         },
         {
             .name = PARALLELS_OPT_PREALLOC_MODE,
@@ -192,7 +187,8 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
                                  int nb_sectors, int *pnum)
 {
     BDRVParallelsState *s = bs->opaque;
-    int64_t pos, space, idx, to_allocate, i;
+    uint32_t idx, to_allocate, i;
+    int64_t pos, space;
 
     pos = block_status(s, sector_num, nb_sectors, pnum);
     if (pos > 0) {
@@ -200,31 +196,20 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
     }
 
     idx = sector_num / s->tracks;
-    to_allocate = DIV_ROUND_UP(sector_num + *pnum, s->tracks) - idx;
-
-    /* This function is called only by parallels_co_writev(), which will never
-     * pass a sector_num at or beyond the end of the image (because the block
-     * layer never passes such a sector_num to that function). Therefore, idx
-     * is always below s->bat_size.
-     * block_status() will limit *pnum so that sector_num + *pnum will not
-     * exceed the image end. Therefore, idx + to_allocate cannot exceed
-     * s->bat_size.
-     * Note that s->bat_size is an unsigned int, therefore idx + to_allocate
-     * will always fit into a uint32_t. */
-    assert(idx < s->bat_size && idx + to_allocate <= s->bat_size);
+    if (idx >= s->bat_size) {
+        return -EINVAL;
+    }
 
+    to_allocate = (sector_num + *pnum + s->tracks - 1) / s->tracks - idx;
     space = to_allocate * s->tracks;
     if (s->data_end + space > bdrv_getlength(bs->file->bs) >> BDRV_SECTOR_BITS) {
         int ret;
         space += s->prealloc_size;
         if (s->prealloc_mode == PRL_PREALLOC_MODE_FALLOCATE) {
-            ret = bdrv_pwrite_zeroes(bs->file,
-                                     s->data_end << BDRV_SECTOR_BITS,
-                                     space << BDRV_SECTOR_BITS, 0);
+            ret = bdrv_write_zeroes(bs->file->bs, s->data_end, space, 0);
         } else {
-            ret = bdrv_truncate(bs->file,
-                                (s->data_end + space) << BDRV_SECTOR_BITS,
-                                NULL);
+            ret = bdrv_truncate(bs->file->bs,
+                                (s->data_end + space) << BDRV_SECTOR_BITS);
         }
         if (ret < 0) {
             return ret;
@@ -259,7 +244,7 @@ static coroutine_fn int parallels_co_flush_to_os(BlockDriverState *bs)
         if (off + to_write > s->header_size) {
             to_write = s->header_size - off;
         }
-        ret = bdrv_pwrite(bs->file, off, (uint8_t *)s->header + off,
+        ret = bdrv_pwrite(bs->file->bs, off, (uint8_t *)s->header + off,
                           to_write);
         if (ret < 0) {
             qemu_co_mutex_unlock(&s->lock);
@@ -275,7 +260,7 @@ static coroutine_fn int parallels_co_flush_to_os(BlockDriverState *bs)
 
 
 static int64_t coroutine_fn parallels_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
+        int64_t sector_num, int nb_sectors, int *pnum)
 {
     BDRVParallelsState *s = bs->opaque;
     int64_t offset;
@@ -288,7 +273,6 @@ static int64_t coroutine_fn parallels_co_get_block_status(BlockDriverState *bs,
         return 0;
     }
 
-    *file = bs->file->bs;
     return (offset << BDRV_SECTOR_BITS) |
         BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
 }
@@ -320,7 +304,7 @@ static coroutine_fn int parallels_co_writev(BlockDriverState *bs,
         qemu_iovec_reset(&hd_qiov);
         qemu_iovec_concat(&hd_qiov, qiov, bytes_done, nbytes);
 
-        ret = bdrv_co_writev(bs->file, position, n, &hd_qiov);
+        ret = bdrv_co_writev(bs->file->bs, position, n, &hd_qiov);
         if (ret < 0) {
             break;
         }
@@ -360,7 +344,7 @@ static coroutine_fn int parallels_co_readv(BlockDriverState *bs,
             qemu_iovec_reset(&hd_qiov);
             qemu_iovec_concat(&hd_qiov, qiov, bytes_done, nbytes);
 
-            ret = bdrv_co_readv(bs->file, position, n, &hd_qiov);
+            ret = bdrv_co_readv(bs->file->bs, position, n, &hd_qiov);
             if (ret < 0) {
                 break;
             }
@@ -441,7 +425,7 @@ static int parallels_check(BlockDriverState *bs, BdrvCheckResult *res,
     }
 
     if (flush_bat) {
-        ret = bdrv_pwrite_sync(bs->file, 0, s->header, s->header_size);
+        ret = bdrv_pwrite_sync(bs->file->bs, 0, s->header, s->header_size);
         if (ret < 0) {
             res->check_errors++;
             return ret;
@@ -457,10 +441,8 @@ static int parallels_check(BlockDriverState *bs, BdrvCheckResult *res,
                 size - res->image_end_offset);
         res->leaks += count;
         if (fix & BDRV_FIX_LEAKS) {
-            Error *local_err = NULL;
-            ret = bdrv_truncate(bs->file, res->image_end_offset, &local_err);
+            ret = bdrv_truncate(bs->file->bs, res->image_end_offset);
             if (ret < 0) {
-                error_report_err(local_err);
                 res->check_errors++;
                 return ret;
             }
@@ -477,7 +459,7 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
     int64_t total_size, cl_size;
     uint8_t tmp[BDRV_SECTOR_SIZE];
     Error *local_err = NULL;
-    BlockBackend *file;
+    BlockDriverState *file;
     uint32_t bat_entries, bat_sectors;
     ParallelsHeader header;
     int ret;
@@ -486,10 +468,6 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
                           BDRV_SECTOR_SIZE);
     cl_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE,
                           DEFAULT_CLUSTER_SIZE), BDRV_SECTOR_SIZE);
-    if (total_size >= MAX_PARALLELS_IMAGE_FACTOR * cl_size) {
-        error_propagate(errp, local_err);
-        return -E2BIG;
-    }
 
     ret = bdrv_create_file(filename, opts, &local_err);
     if (ret < 0) {
@@ -497,17 +475,14 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
         return ret;
     }
 
-    file = blk_new_open(filename, NULL, NULL,
-                        BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
-                        &local_err);
-    if (file == NULL) {
+    file = NULL;
+    ret = bdrv_open(&file, filename, NULL, NULL,
+                    BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+    if (ret < 0) {
         error_propagate(errp, local_err);
-        return -EIO;
+        return ret;
     }
-
-    blk_set_allow_write_beyond_eof(file, true);
-
-    ret = blk_truncate(file, 0, errp);
+    ret = bdrv_truncate(file, 0);
     if (ret < 0) {
         goto exit;
     }
@@ -531,19 +506,18 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
     memset(tmp, 0, sizeof(tmp));
     memcpy(tmp, &header, sizeof(header));
 
-    ret = blk_pwrite(file, 0, tmp, BDRV_SECTOR_SIZE, 0);
+    ret = bdrv_pwrite(file, 0, tmp, BDRV_SECTOR_SIZE);
     if (ret < 0) {
         goto exit;
     }
-    ret = blk_pwrite_zeroes(file, BDRV_SECTOR_SIZE,
-                            (bat_sectors - 1) << BDRV_SECTOR_BITS, 0);
+    ret = bdrv_write_zeroes(file, 1, bat_sectors - 1, 0);
     if (ret < 0) {
         goto exit;
     }
     ret = 0;
 
 done:
-    blk_unref(file);
+    bdrv_unref(file);
     return ret;
 
 exit:
@@ -579,7 +553,7 @@ static int parallels_update_header(BlockDriverState *bs)
     if (size > s->header_size) {
         size = s->header_size;
     }
-    return bdrv_pwrite_sync(bs->file, 0, s->header, size);
+    return bdrv_pwrite_sync(bs->file->bs, 0, s->header, size);
 }
 
 static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
@@ -592,13 +566,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
     Error *local_err = NULL;
     char *buf;
 
-    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
-                               false, errp);
-    if (!bs->file) {
-        return -EINVAL;
-    }
-
-    ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph));
+    ret = bdrv_pread(bs->file->bs, 0, &ph, sizeof(ph));
     if (ret < 0) {
         goto fail;
     }
@@ -653,7 +621,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
         s->header_size = size;
     }
 
-    ret = bdrv_pread(bs->file, 0, s->header, s->header_size);
+    ret = bdrv_pread(bs->file->bs, 0, s->header, s->header_size);
     if (ret < 0) {
         goto fail;
     }
@@ -692,14 +660,13 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
     s->prealloc_size = MAX(s->tracks, s->prealloc_size >> BDRV_SECTOR_BITS);
     buf = qemu_opt_get_del(opts, PARALLELS_OPT_PREALLOC_MODE);
     s->prealloc_mode = qapi_enum_parse(prealloc_mode_lookup, buf,
-            PRL_PREALLOC_MODE__MAX, PRL_PREALLOC_MODE_FALLOCATE, &local_err);
+            PRL_PREALLOC_MODE_MAX, PRL_PREALLOC_MODE_FALLOCATE, &local_err);
     g_free(buf);
     if (local_err != NULL) {
         goto fail_options;
     }
-
-    if (!(flags & BDRV_O_RESIZE) || !bdrv_has_zero_init(bs->file->bs) ||
-            bdrv_truncate(bs->file, bdrv_getlength(bs->file->bs), NULL) != 0) {
+    if (!bdrv_has_zero_init(bs->file->bs) ||
+            bdrv_truncate(bs->file->bs, bdrv_getlength(bs->file->bs)) != 0) {
         s->prealloc_mode = PRL_PREALLOC_MODE_FALLOCATE;
     }
 
@@ -742,7 +709,7 @@ static void parallels_close(BlockDriverState *bs)
     }
 
     if (bs->open_flags & BDRV_O_RDWR) {
-        bdrv_truncate(bs->file, s->data_end << BDRV_SECTOR_BITS, NULL);
+        bdrv_truncate(bs->file->bs, s->data_end << BDRV_SECTOR_BITS);
     }
 
     g_free(s->bat_dirty_bmap);
@@ -774,7 +741,6 @@ static BlockDriver bdrv_parallels = {
     .bdrv_probe		= parallels_probe,
     .bdrv_open		= parallels_open,
     .bdrv_close		= parallels_close,
-    .bdrv_child_perm          = bdrv_format_default_perms,
     .bdrv_co_get_block_status = parallels_co_get_block_status,
     .bdrv_has_zero_init       = bdrv_has_zero_init_1,
     .bdrv_co_flush_to_os      = parallels_co_flush_to_os,

block/qapi.c

@@ -22,20 +22,17 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
 #include "block/qapi.h"
 #include "block/block_int.h"
 #include "block/throttle-groups.h"
 #include "block/write-threshold.h"
 #include "qmp-commands.h"
 #include "qapi-visit.h"
-#include "qapi/qobject-output-visitor.h"
+#include "qapi/qmp-output-visitor.h"
 #include "qapi/qmp/types.h"
 #include "sysemu/block-backend.h"
-#include "qemu/cutils.h"
 
-BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
-                                        BlockDriverState *bs, Error **errp)
+BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs, Error **errp)
 {
     ImageInfo **p_image_info;
     BlockDriverState *bs0;
@@ -49,7 +46,7 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
 
     info->cache = g_new(BlockdevCacheInfo, 1);
     *info->cache = (BlockdevCacheInfo) {
-        .writeback      = blk ? blk_enable_write_cache(blk) : true,
+        .writeback      = bdrv_enable_write_cache(bs),
         .direct         = !!(bs->open_flags & BDRV_O_NOCACHE),
         .no_flush       = !!(bs->open_flags & BDRV_O_NO_FLUSH),
     };
@@ -67,10 +64,10 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
     info->backing_file_depth = bdrv_get_backing_file_depth(bs);
     info->detect_zeroes = bs->detect_zeroes;
 
-    if (blk && blk_get_public(blk)->throttle_state) {
+    if (bs->throttle_state) {
         ThrottleConfig cfg;
 
-        throttle_group_get_config(blk, &cfg);
+        throttle_group_get_config(bs, &cfg);
 
         info->bps     = cfg.buckets[THROTTLE_BPS_TOTAL].avg;
         info->bps_rd  = cfg.buckets[THROTTLE_BPS_READ].avg;
@@ -94,31 +91,11 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
         info->has_iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
         info->iops_wr_max     = cfg.buckets[THROTTLE_OPS_WRITE].max;
 
-        info->has_bps_max_length     = info->has_bps_max;
-        info->bps_max_length         =
-            cfg.buckets[THROTTLE_BPS_TOTAL].burst_length;
-        info->has_bps_rd_max_length  = info->has_bps_rd_max;
-        info->bps_rd_max_length      =
-            cfg.buckets[THROTTLE_BPS_READ].burst_length;
-        info->has_bps_wr_max_length  = info->has_bps_wr_max;
-        info->bps_wr_max_length      =
-            cfg.buckets[THROTTLE_BPS_WRITE].burst_length;
-
-        info->has_iops_max_length    = info->has_iops_max;
-        info->iops_max_length        =
-            cfg.buckets[THROTTLE_OPS_TOTAL].burst_length;
-        info->has_iops_rd_max_length = info->has_iops_rd_max;
-        info->iops_rd_max_length     =
-            cfg.buckets[THROTTLE_OPS_READ].burst_length;
-        info->has_iops_wr_max_length = info->has_iops_wr_max;
-        info->iops_wr_max_length     =
-            cfg.buckets[THROTTLE_OPS_WRITE].burst_length;
-
         info->has_iops_size = cfg.op_size;
         info->iops_size = cfg.op_size;
 
         info->has_group = true;
-        info->group = g_strdup(throttle_group_get_name(blk));
+        info->group = g_strdup(throttle_group_get_name(bs));
     }
 
     info->write_threshold = bdrv_write_threshold_get(bs);
@@ -233,13 +210,11 @@ void bdrv_query_image_info(BlockDriverState *bs,
     Error *err = NULL;
     ImageInfo *info;
 
-    aio_context_acquire(bdrv_get_aio_context(bs));
-
     size = bdrv_getlength(bs);
     if (size < 0) {
-        error_setg_errno(errp, -size, "Can't get image size '%s'",
-                         bs->exact_filename);
-        goto out;
+        error_setg_errno(errp, -size, "Can't get size of device '%s'",
+                         bdrv_get_device_name(bs));
+        return;
     }
 
     info = g_new0(ImageInfo, 1);
@@ -270,18 +245,15 @@ void bdrv_query_image_info(BlockDriverState *bs,
         info->has_backing_filename = true;
         bdrv_get_full_backing_filename(bs, backing_filename2, PATH_MAX, &err);
         if (err) {
-            /* Can't reconstruct the full backing filename, so we must omit
-             * this field and apply a Best Effort to this query. */
+            error_propagate(errp, err);
+            qapi_free_ImageInfo(info);
             g_free(backing_filename2);
-            backing_filename2 = NULL;
-            error_free(err);
-            err = NULL;
+            return;
         }
 
-        /* Always report the full_backing_filename if present, even if it's the
-         * same as backing_filename. That they are same is useful info. */
-        if (backing_filename2) {
-            info->full_backing_filename = g_strdup(backing_filename2);
+        if (strcmp(backing_filename, backing_filename2) != 0) {
+            info->full_backing_filename =
+                        g_strdup(backing_filename2);
             info->has_full_backing_filename = true;
         }
 
@@ -307,13 +279,10 @@ void bdrv_query_image_info(BlockDriverState *bs,
     default:
         error_propagate(errp, err);
         qapi_free_ImageInfo(info);
-        goto out;
+        return;
     }
 
     *p_info = info;
-
-out:
-    aio_context_release(bdrv_get_aio_context(bs));
 }
 
 /* @p_info will be set only on success. */
@@ -327,7 +296,7 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
     info->locked = blk_dev_is_medium_locked(blk);
     info->removable = blk_dev_has_removable_media(blk);
 
-    if (blk_dev_has_tray(blk)) {
+    if (blk_dev_has_removable_media(blk)) {
         info->has_tray_open = true;
         info->tray_open = blk_dev_is_tray_open(blk);
     }
@@ -344,7 +313,7 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
 
     if (bs && bs->drv) {
         info->has_inserted = true;
-        info->inserted = bdrv_block_device_info(blk, bs, errp);
+        info->inserted = bdrv_block_device_info(bs, errp);
         if (info->inserted == NULL) {
             goto err;
         }
@@ -357,83 +326,16 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
     qapi_free_BlockInfo(info);
 }
 
-static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
+static BlockStats *bdrv_query_stats(const BlockDriverState *bs,
+                                    bool query_backing)
 {
-    BlockAcctStats *stats = blk_get_stats(blk);
-    BlockAcctTimedStats *ts = NULL;
-
-    ds->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
-    ds->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
-    ds->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
-    ds->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
-
-    ds->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
-    ds->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
-    ds->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
-
-    ds->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
-    ds->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
-    ds->invalid_flush_operations =
-        stats->invalid_ops[BLOCK_ACCT_FLUSH];
-
-    ds->rd_merged = stats->merged[BLOCK_ACCT_READ];
-    ds->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
-    ds->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
-    ds->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
-    ds->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
-    ds->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
-
-    ds->has_idle_time_ns = stats->last_access_time_ns > 0;
-    if (ds->has_idle_time_ns) {
-        ds->idle_time_ns = block_acct_idle_time_ns(stats);
-    }
-
-    ds->account_invalid = stats->account_invalid;
-    ds->account_failed = stats->account_failed;
-
-    while ((ts = block_acct_interval_next(stats, ts))) {
-        BlockDeviceTimedStatsList *timed_stats =
-            g_malloc0(sizeof(*timed_stats));
-        BlockDeviceTimedStats *dev_stats = g_malloc0(sizeof(*dev_stats));
-        timed_stats->next = ds->timed_stats;
-        timed_stats->value = dev_stats;
-        ds->timed_stats = timed_stats;
-
-        TimedAverage *rd = &ts->latency[BLOCK_ACCT_READ];
-        TimedAverage *wr = &ts->latency[BLOCK_ACCT_WRITE];
-        TimedAverage *fl = &ts->latency[BLOCK_ACCT_FLUSH];
-
-        dev_stats->interval_length = ts->interval_length;
-
-        dev_stats->min_rd_latency_ns = timed_average_min(rd);
-        dev_stats->max_rd_latency_ns = timed_average_max(rd);
-        dev_stats->avg_rd_latency_ns = timed_average_avg(rd);
-
-        dev_stats->min_wr_latency_ns = timed_average_min(wr);
-        dev_stats->max_wr_latency_ns = timed_average_max(wr);
-        dev_stats->avg_wr_latency_ns = timed_average_avg(wr);
-
-        dev_stats->min_flush_latency_ns = timed_average_min(fl);
-        dev_stats->max_flush_latency_ns = timed_average_max(fl);
-        dev_stats->avg_flush_latency_ns = timed_average_avg(fl);
-
-        dev_stats->avg_rd_queue_depth =
-            block_acct_queue_depth(ts, BLOCK_ACCT_READ);
-        dev_stats->avg_wr_queue_depth =
-            block_acct_queue_depth(ts, BLOCK_ACCT_WRITE);
-    }
-}
-
-static BlockStats *bdrv_query_bds_stats(const BlockDriverState *bs,
-                                 bool query_backing)
-{
-    BlockStats *s = NULL;
+    BlockStats *s;
 
     s = g_malloc0(sizeof(*s));
-    s->stats = g_malloc0(sizeof(*s->stats));
 
-    if (!bs) {
-        return s;
+    if (bdrv_get_device_name(bs)[0]) {
+        s->has_device = true;
+        s->device = g_strdup(bdrv_get_device_name(bs));
     }
 
     if (bdrv_get_node_name(bs)[0]) {
@@ -441,16 +343,83 @@ static BlockStats *bdrv_query_bds_stats(const BlockDriverState *bs,
         s->node_name = g_strdup(bdrv_get_node_name(bs));
     }
 
-    s->stats->wr_highest_offset = stat64_get(&bs->wr_highest_offset);
+    s->stats = g_malloc0(sizeof(*s->stats));
+    if (bs->blk) {
+        BlockAcctStats *stats = blk_get_stats(bs->blk);
+        BlockAcctTimedStats *ts = NULL;
+
+        s->stats->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
+        s->stats->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
+        s->stats->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
+        s->stats->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
+
+        s->stats->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
+        s->stats->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
+        s->stats->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
+
+        s->stats->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
+        s->stats->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
+        s->stats->invalid_flush_operations =
+            stats->invalid_ops[BLOCK_ACCT_FLUSH];
+
+        s->stats->rd_merged = stats->merged[BLOCK_ACCT_READ];
+        s->stats->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
+        s->stats->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
+        s->stats->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
+        s->stats->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
+        s->stats->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
+
+        s->stats->has_idle_time_ns = stats->last_access_time_ns > 0;
+        if (s->stats->has_idle_time_ns) {
+            s->stats->idle_time_ns = block_acct_idle_time_ns(stats);
+        }
+
+        s->stats->account_invalid = stats->account_invalid;
+        s->stats->account_failed = stats->account_failed;
+
+        while ((ts = block_acct_interval_next(stats, ts))) {
+            BlockDeviceTimedStatsList *timed_stats =
+                g_malloc0(sizeof(*timed_stats));
+            BlockDeviceTimedStats *dev_stats = g_malloc0(sizeof(*dev_stats));
+            timed_stats->next = s->stats->timed_stats;
+            timed_stats->value = dev_stats;
+            s->stats->timed_stats = timed_stats;
+
+            TimedAverage *rd = &ts->latency[BLOCK_ACCT_READ];
+            TimedAverage *wr = &ts->latency[BLOCK_ACCT_WRITE];
+            TimedAverage *fl = &ts->latency[BLOCK_ACCT_FLUSH];
+
+            dev_stats->interval_length = ts->interval_length;
+
+            dev_stats->min_rd_latency_ns = timed_average_min(rd);
+            dev_stats->max_rd_latency_ns = timed_average_max(rd);
+            dev_stats->avg_rd_latency_ns = timed_average_avg(rd);
+
+            dev_stats->min_wr_latency_ns = timed_average_min(wr);
+            dev_stats->max_wr_latency_ns = timed_average_max(wr);
+            dev_stats->avg_wr_latency_ns = timed_average_avg(wr);
+
+            dev_stats->min_flush_latency_ns = timed_average_min(fl);
+            dev_stats->max_flush_latency_ns = timed_average_max(fl);
+            dev_stats->avg_flush_latency_ns = timed_average_avg(fl);
+
+            dev_stats->avg_rd_queue_depth =
+                block_acct_queue_depth(ts, BLOCK_ACCT_READ);
+            dev_stats->avg_wr_queue_depth =
+                block_acct_queue_depth(ts, BLOCK_ACCT_WRITE);
+        }
+    }
+
+    s->stats->wr_highest_offset = bs->wr_highest_offset;
 
     if (bs->file) {
         s->has_parent = true;
-        s->parent = bdrv_query_bds_stats(bs->file->bs, query_backing);
+        s->parent = bdrv_query_stats(bs->file->bs, query_backing);
     }
 
     if (query_backing && bs->backing) {
         s->has_backing = true;
-        s->backing = bdrv_query_bds_stats(bs->backing->bs, query_backing);
+        s->backing = bdrv_query_stats(bs->backing->bs, query_backing);
     }
 
     return s;
@@ -484,39 +453,21 @@ BlockStatsList *qmp_query_blockstats(bool has_query_nodes,
                                      Error **errp)
 {
     BlockStatsList *head = NULL, **p_next = &head;
-    BlockBackend *blk;
-    BlockDriverState *bs;
+    BlockDriverState *bs = NULL;
 
     /* Just to be safe if query_nodes is not always initialized */
-    if (has_query_nodes && query_nodes) {
-        for (bs = bdrv_next_node(NULL); bs; bs = bdrv_next_node(bs)) {
-            BlockStatsList *info = g_malloc0(sizeof(*info));
-            AioContext *ctx = bdrv_get_aio_context(bs);
+    query_nodes = has_query_nodes && query_nodes;
 
-            aio_context_acquire(ctx);
-            info->value = bdrv_query_bds_stats(bs, false);
-            aio_context_release(ctx);
+    while ((bs = query_nodes ? bdrv_next_node(bs) : bdrv_next(bs))) {
+        BlockStatsList *info = g_malloc0(sizeof(*info));
+        AioContext *ctx = bdrv_get_aio_context(bs);
 
-            *p_next = info;
-            p_next = &info->next;
-        }
-    } else {
-        for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
-            BlockStatsList *info = g_malloc0(sizeof(*info));
-            AioContext *ctx = blk_get_aio_context(blk);
-            BlockStats *s;
+        aio_context_acquire(ctx);
+        info->value = bdrv_query_stats(bs, !query_nodes);
+        aio_context_release(ctx);
 
-            aio_context_acquire(ctx);
-            s = bdrv_query_bds_stats(blk_bs(blk), true);
-            s->has_device = true;
-            s->device = g_strdup(blk_name(blk));
-            bdrv_query_blk_stats(s->stats, blk);
-            aio_context_release(ctx);
-
-            info->value = s;
-            *p_next = info;
-            p_next = &info->next;
-        }
+        *p_next = info;
+        p_next = &info->next;
     }
 
     return head;
@@ -595,11 +546,9 @@ static void dump_qobject(fprintf_function func_fprintf, void *f,
                          int comp_indent, QObject *obj)
 {
     switch (qobject_type(obj)) {
-        case QTYPE_QNUM: {
-            QNum *value = qobject_to_qnum(obj);
-            char *tmp = qnum_to_string(value);
-            func_fprintf(f, "%s", tmp);
-            g_free(tmp);
+        case QTYPE_QINT: {
+            QInt *value = qobject_to_qint(obj);
+            func_fprintf(f, "%" PRId64, qint_get_int(value));
             break;
         }
         case QTYPE_QSTRING: {
@@ -617,6 +566,11 @@ static void dump_qobject(fprintf_function func_fprintf, void *f,
             dump_qlist(func_fprintf, f, comp_indent, value);
             break;
         }
+        case QTYPE_QFLOAT: {
+            QFloat *value = qobject_to_qfloat(obj);
+            func_fprintf(f, "%g", qfloat_get_double(value));
+            break;
+        }
         case QTYPE_QBOOL: {
             QBool *value = qobject_to_qbool(obj);
             func_fprintf(f, "%s", qbool_get_bool(value) ? "true" : "false");
@@ -634,10 +588,11 @@ static void dump_qlist(fprintf_function func_fprintf, void *f, int indentation,
     int i = 0;
 
     for (entry = qlist_first(list); entry; entry = qlist_next(entry), i++) {
-        QType type = qobject_type(entry->value);
+        qtype_code type = qobject_type(entry->value);
         bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
-        func_fprintf(f, "%*s[%i]:%c", indentation * 4, "", i,
-                     composite ? '\n' : ' ');
+        const char *format = composite ? "%*s[%i]:\n" : "%*s[%i]: ";
+
+        func_fprintf(f, format, indentation * 4, "", i);
         dump_qobject(func_fprintf, f, indentation + 1, entry->value);
         if (!composite) {
             func_fprintf(f, "\n");
@@ -651,9 +606,10 @@ static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
     const QDictEntry *entry;
 
     for (entry = qdict_first(dict); entry; entry = qdict_next(dict, entry)) {
-        QType type = qobject_type(entry->value);
+        qtype_code type = qobject_type(entry->value);
         bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
-        char *key = g_malloc(strlen(entry->key) + 1);
+        const char *format = composite ? "%*s%s:\n" : "%*s%s: ";
+        char key[strlen(entry->key) + 1];
         int i;
 
         /* replace dashes with spaces in key (variable) names */
@@ -661,28 +617,28 @@ static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
             key[i] = entry->key[i] == '-' ? ' ' : entry->key[i];
         }
         key[i] = 0;
-        func_fprintf(f, "%*s%s:%c", indentation * 4, "", key,
-                     composite ? '\n' : ' ');
+
+        func_fprintf(f, format, indentation * 4, "", key);
         dump_qobject(func_fprintf, f, indentation + 1, entry->value);
         if (!composite) {
             func_fprintf(f, "\n");
         }
-        g_free(key);
     }
 }
 
 void bdrv_image_info_specific_dump(fprintf_function func_fprintf, void *f,
                                    ImageInfoSpecific *info_spec)
 {
+    QmpOutputVisitor *ov = qmp_output_visitor_new();
     QObject *obj, *data;
-    Visitor *v = qobject_output_visitor_new(&obj);
 
-    visit_type_ImageInfoSpecific(v, NULL, &info_spec, &error_abort);
-    visit_complete(v, &obj);
+    visit_type_ImageInfoSpecific(qmp_output_get_visitor(ov), &info_spec, NULL,
+                                 &error_abort);
+    obj = qmp_output_get_qobject(ov);
+    assert(qobject_type(obj) == QTYPE_QDICT);
     data = qdict_get(qobject_to_qdict(obj), "data");
     dump_qobject(func_fprintf, f, 1, data);
-    qobject_decref(obj);
-    visit_free(v);
+    qmp_output_visitor_cleanup(ov);
 }
 
 void bdrv_image_info_dump(fprintf_function func_fprintf, void *f,
@@ -720,10 +676,7 @@ void bdrv_image_info_dump(fprintf_function func_fprintf, void *f,
 
     if (info->has_backing_filename) {
         func_fprintf(f, "backing file: %s", info->backing_filename);
-        if (!info->has_full_backing_filename) {
-            func_fprintf(f, " (cannot determine actual path)");
-        } else if (strcmp(info->backing_filename,
-                          info->full_backing_filename) != 0) {
+        if (info->has_full_backing_filename) {
             func_fprintf(f, " (actual path: %s)", info->full_backing_filename);
         }
         func_fprintf(f, "\n");

block/qcow.c

@@ -21,18 +21,13 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  * THE SOFTWARE.
  */
-#include "qemu/osdep.h"
-#include "qapi/error.h"
 #include "qemu-common.h"
-#include "qemu/error-report.h"
 #include "block/block_int.h"
-#include "sysemu/block-backend.h"
 #include "qemu/module.h"
-#include "qemu/bswap.h"
 #include <zlib.h>
 #include "qapi/qmp/qerror.h"
 #include "crypto/cipher.h"
-#include "migration/blocker.h"
+#include "migration/migration.h"
 
 /**************************************************************/
 /* QEMU COW block driver with compression and encryption support */
@@ -104,15 +99,8 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     unsigned int len, i, shift;
     int ret;
     QCowHeader header;
-    Error *local_err = NULL;
 
-    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
-                               false, errp);
-    if (!bs->file) {
-        return -EINVAL;
-    }
-
-    ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
+    ret = bdrv_pread(bs->file->bs, 0, &header, sizeof(header));
     if (ret < 0) {
         goto fail;
     }
@@ -131,7 +119,11 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
     if (header.version != QCOW_VERSION) {
-        error_setg(errp, "Unsupported qcow version %" PRIu32, header.version);
+        char version[64];
+        snprintf(version, sizeof(version), "QCOW version %" PRIu32,
+                 header.version);
+        error_setg(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+                   bdrv_get_device_or_node_name(bs), "qcow", version);
         ret = -ENOTSUP;
         goto fail;
     }
@@ -160,29 +152,14 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
         ret = -EINVAL;
         goto fail;
     }
-    if (!qcrypto_cipher_supports(QCRYPTO_CIPHER_ALG_AES_128,
-                                 QCRYPTO_CIPHER_MODE_CBC)) {
+    if (!qcrypto_cipher_supports(QCRYPTO_CIPHER_ALG_AES_128)) {
         error_setg(errp, "AES cipher not available");
         ret = -EINVAL;
         goto fail;
     }
     s->crypt_method_header = header.crypt_method;
     if (s->crypt_method_header) {
-        if (bdrv_uses_whitelist() &&
-            s->crypt_method_header == QCOW_CRYPT_AES) {
-            error_setg(errp,
-                       "Use of AES-CBC encrypted qcow images is no longer "
-                       "supported in system emulators");
-            error_append_hint(errp,
-                              "You can use 'qemu-img convert' to convert your "
-                              "image to an alternative supported format, such "
-                              "as unencrypted qcow, or raw with the LUKS "
-                              "format instead.\n");
-            ret = -ENOSYS;
-            goto fail;
-        }
-
-        bs->encrypted = true;
+        bs->encrypted = 1;
     }
     s->cluster_bits = header.cluster_bits;
     s->cluster_size = 1 << s->cluster_bits;
@@ -216,7 +193,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table,
+    ret = bdrv_pread(bs->file->bs, s->l1_table_offset, s->l1_table,
                s->l1_size * sizeof(uint64_t));
     if (ret < 0) {
         goto fail;
@@ -247,7 +224,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
             ret = -EINVAL;
             goto fail;
         }
-        ret = bdrv_pread(bs->file, header.backing_file_offset,
+        ret = bdrv_pread(bs->file->bs, header.backing_file_offset,
                    bs->backing_file, len);
         if (ret < 0) {
             goto fail;
@@ -259,12 +236,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     error_setg(&s->migration_blocker, "The qcow format used by node '%s' "
                "does not support live migration",
                bdrv_get_device_or_node_name(bs));
-    ret = migrate_add_blocker(s->migration_blocker, &local_err);
-    if (local_err) {
-        error_propagate(errp, local_err);
-        error_free(s->migration_blocker);
-        goto fail;
-    }
+    migrate_add_blocker(s->migration_blocker);
 
     qemu_co_mutex_init(&s->lock);
     return 0;
@@ -403,7 +375,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
         /* update the L1 entry */
         s->l1_table[l1_index] = l2_offset;
         tmp = cpu_to_be64(l2_offset);
-        if (bdrv_pwrite_sync(bs->file,
+        if (bdrv_pwrite_sync(bs->file->bs,
                 s->l1_table_offset + l1_index * sizeof(tmp),
                 &tmp, sizeof(tmp)) < 0)
             return 0;
@@ -433,11 +405,11 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
     l2_table = s->l2_cache + (min_index << s->l2_bits);
     if (new_l2_table) {
         memset(l2_table, 0, s->l2_size * sizeof(uint64_t));
-        if (bdrv_pwrite_sync(bs->file, l2_offset, l2_table,
+        if (bdrv_pwrite_sync(bs->file->bs, l2_offset, l2_table,
                 s->l2_size * sizeof(uint64_t)) < 0)
             return 0;
     } else {
-        if (bdrv_pread(bs->file, l2_offset, l2_table,
+        if (bdrv_pread(bs->file->bs, l2_offset, l2_table,
                        s->l2_size * sizeof(uint64_t)) !=
             s->l2_size * sizeof(uint64_t))
             return 0;
@@ -463,7 +435,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
             cluster_offset = (cluster_offset + s->cluster_size - 1) &
                 ~(s->cluster_size - 1);
             /* write the cluster content */
-            if (bdrv_pwrite(bs->file, cluster_offset, s->cluster_cache,
+            if (bdrv_pwrite(bs->file->bs, cluster_offset, s->cluster_cache,
                             s->cluster_size) !=
                 s->cluster_size)
                 return -1;
@@ -473,7 +445,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
                 /* round to cluster size */
                 cluster_offset = (cluster_offset + s->cluster_size - 1) &
                     ~(s->cluster_size - 1);
-                bdrv_truncate(bs->file, cluster_offset + s->cluster_size, NULL);
+                bdrv_truncate(bs->file->bs, cluster_offset + s->cluster_size);
                 /* if encrypted, we must initialize the cluster
                    content which won't be written */
                 if (bs->encrypted &&
@@ -493,7 +465,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
                                 errno = EIO;
                                 return -1;
                             }
-                            if (bdrv_pwrite(bs->file,
+                            if (bdrv_pwrite(bs->file->bs,
                                             cluster_offset + i * 512,
                                             s->cluster_data, 512) != 512)
                                 return -1;
@@ -508,7 +480,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
         /* update L2 table */
         tmp = cpu_to_be64(cluster_offset);
         l2_table[l2_index] = tmp;
-        if (bdrv_pwrite_sync(bs->file, l2_offset + l2_index * sizeof(tmp),
+        if (bdrv_pwrite_sync(bs->file->bs, l2_offset + l2_index * sizeof(tmp),
                 &tmp, sizeof(tmp)) < 0)
             return 0;
     }
@@ -516,7 +488,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
 }
 
 static int64_t coroutine_fn qcow_co_get_block_status(BlockDriverState *bs,
-        int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
+        int64_t sector_num, int nb_sectors, int *pnum)
 {
     BDRVQcowState *s = bs->opaque;
     int index_in_cluster, n;
@@ -537,7 +509,6 @@ static int64_t coroutine_fn qcow_co_get_block_status(BlockDriverState *bs,
         return BDRV_BLOCK_DATA;
     }
     cluster_offset |= (index_in_cluster << BDRV_SECTOR_BITS);
-    *file = bs->file->bs;
     return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | cluster_offset;
 }
 
@@ -578,7 +549,7 @@ static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
     if (s->cluster_cache_offset != coffset) {
         csize = cluster_offset >> (63 - s->cluster_bits);
         csize &= (s->cluster_size - 1);
-        ret = bdrv_pread(bs->file, coffset, s->cluster_data, csize);
+        ret = bdrv_pread(bs->file->bs, coffset, s->cluster_data, csize);
         if (ret != csize)
             return -1;
         if (decompress_buffer(s->cluster_cache, s->cluster_size,
@@ -632,7 +603,8 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
                 hd_iov.iov_len = n * 512;
                 qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
                 qemu_co_mutex_unlock(&s->lock);
-                ret = bdrv_co_readv(bs->backing, sector_num, n, &hd_qiov);
+                ret = bdrv_co_readv(bs->backing->bs, sector_num,
+                                    n, &hd_qiov);
                 qemu_co_mutex_lock(&s->lock);
                 if (ret < 0) {
                     goto fail;
@@ -656,7 +628,7 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
             hd_iov.iov_len = n * 512;
             qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
             qemu_co_mutex_unlock(&s->lock);
-            ret = bdrv_co_readv(bs->file,
+            ret = bdrv_co_readv(bs->file->bs,
                                 (cluster_offset >> 9) + index_in_cluster,
                                 n, &hd_qiov);
             qemu_co_mutex_lock(&s->lock);
@@ -758,7 +730,7 @@ static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
         hd_iov.iov_len = n * 512;
         qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
         qemu_co_mutex_unlock(&s->lock);
-        ret = bdrv_co_writev(bs->file,
+        ret = bdrv_co_writev(bs->file->bs,
                              (cluster_offset >> 9) + index_in_cluster,
                              n, &hd_qiov);
         qemu_co_mutex_lock(&s->lock);
@@ -806,7 +778,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     int flags = 0;
     Error *local_err = NULL;
     int ret;
-    BlockBackend *qcow_blk;
+    BlockDriverState *qcow_bs;
 
     /* Read out options */
     total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
@@ -822,18 +794,15 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
         goto cleanup;
     }
 
-    qcow_blk = blk_new_open(filename, NULL, NULL,
-                            BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
-                            &local_err);
-    if (qcow_blk == NULL) {
+    qcow_bs = NULL;
+    ret = bdrv_open(&qcow_bs, filename, NULL, NULL,
+                    BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+    if (ret < 0) {
         error_propagate(errp, local_err);
-        ret = -EIO;
         goto cleanup;
     }
 
-    blk_set_allow_write_beyond_eof(qcow_blk, true);
-
-    ret = blk_truncate(qcow_blk, 0, errp);
+    ret = bdrv_truncate(qcow_bs, 0);
     if (ret < 0) {
         goto exit;
     }
@@ -852,7 +821,6 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
             header_size += backing_filename_len;
         } else {
             /* special backing file for vvfat */
-            g_free(backing_file);
             backing_file = NULL;
         }
         header.cluster_bits = 9; /* 512 byte cluster to avoid copying
@@ -874,24 +842,24 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     /* write all the data */
-    ret = blk_pwrite(qcow_blk, 0, &header, sizeof(header), 0);
+    ret = bdrv_pwrite(qcow_bs, 0, &header, sizeof(header));
     if (ret != sizeof(header)) {
         goto exit;
     }
 
     if (backing_file) {
-        ret = blk_pwrite(qcow_blk, sizeof(header),
-                         backing_file, backing_filename_len, 0);
+        ret = bdrv_pwrite(qcow_bs, sizeof(header),
+            backing_file, backing_filename_len);
         if (ret != backing_filename_len) {
             goto exit;
         }
     }
 
     tmp = g_malloc0(BDRV_SECTOR_SIZE);
-    for (i = 0; i < DIV_ROUND_UP(sizeof(uint64_t) * l1_size, BDRV_SECTOR_SIZE);
-         i++) {
-        ret = blk_pwrite(qcow_blk, header_size + BDRV_SECTOR_SIZE * i,
-                         tmp, BDRV_SECTOR_SIZE, 0);
+    for (i = 0; i < ((sizeof(uint64_t)*l1_size + BDRV_SECTOR_SIZE - 1)/
+        BDRV_SECTOR_SIZE); i++) {
+        ret = bdrv_pwrite(qcow_bs, header_size +
+            BDRV_SECTOR_SIZE*i, tmp, BDRV_SECTOR_SIZE);
         if (ret != BDRV_SECTOR_SIZE) {
             g_free(tmp);
             goto exit;
@@ -901,7 +869,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     g_free(tmp);
     ret = 0;
 exit:
-    blk_unref(qcow_blk);
+    bdrv_unref(qcow_bs);
 cleanup:
     g_free(backing_file);
     return ret;
@@ -914,10 +882,10 @@ static int qcow_make_empty(BlockDriverState *bs)
     int ret;
 
     memset(s->l1_table, 0, l1_length);
-    if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table,
+    if (bdrv_pwrite_sync(bs->file->bs, s->l1_table_offset, s->l1_table,
             l1_length) < 0)
         return -1;
-    ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length, NULL);
+    ret = bdrv_truncate(bs->file->bs, s->l1_table_offset + l1_length);
     if (ret < 0)
         return ret;
 
@@ -930,32 +898,32 @@ static int qcow_make_empty(BlockDriverState *bs)
 
 /* XXX: put compressed sectors first, then all the cluster aligned
    tables to avoid losing bytes in alignment */
-static coroutine_fn int
-qcow_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
-                           uint64_t bytes, QEMUIOVector *qiov)
+static int qcow_write_compressed(BlockDriverState *bs, int64_t sector_num,
+                                 const uint8_t *buf, int nb_sectors)
 {
     BDRVQcowState *s = bs->opaque;
-    QEMUIOVector hd_qiov;
-    struct iovec iov;
     z_stream strm;
     int ret, out_len;
-    uint8_t *buf, *out_buf;
+    uint8_t *out_buf;
     uint64_t cluster_offset;
 
-    buf = qemu_blockalign(bs, s->cluster_size);
-    if (bytes != s->cluster_size) {
-        if (bytes > s->cluster_size ||
-            offset + bytes != bs->total_sectors << BDRV_SECTOR_BITS)
-        {
-            qemu_vfree(buf);
-            return -EINVAL;
-        }
-        /* Zero-pad last write if image size is not cluster aligned */
-        memset(buf + bytes, 0, s->cluster_size - bytes);
-    }
-    qemu_iovec_to_buf(qiov, 0, buf, qiov->size);
+    if (nb_sectors != s->cluster_sectors) {
+        ret = -EINVAL;
 
-    out_buf = g_malloc(s->cluster_size);
+        /* Zero-pad last write if image size is not cluster aligned */
+        if (sector_num + nb_sectors == bs->total_sectors &&
+            nb_sectors < s->cluster_sectors) {
+            uint8_t *pad_buf = qemu_blockalign(bs, s->cluster_size);
+            memset(pad_buf, 0, s->cluster_size);
+            memcpy(pad_buf, buf, nb_sectors * BDRV_SECTOR_SIZE);
+            ret = qcow_write_compressed(bs, sector_num,
+                                        pad_buf, s->cluster_sectors);
+            qemu_vfree(pad_buf);
+        }
+        return ret;
+    }
+
+    out_buf = g_malloc(s->cluster_size + (s->cluster_size / 1000) + 128);
 
     /* best compression, small window, no zlib header */
     memset(&strm, 0, sizeof(strm));
@@ -984,35 +952,27 @@ qcow_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
 
     if (ret != Z_STREAM_END || out_len >= s->cluster_size) {
         /* could not compress: write normal cluster */
-        ret = qcow_co_writev(bs, offset >> BDRV_SECTOR_BITS,
-                             bytes >> BDRV_SECTOR_BITS, qiov);
+        ret = bdrv_write(bs, sector_num, buf, s->cluster_sectors);
         if (ret < 0) {
             goto fail;
         }
-        goto success;
-    }
-    qemu_co_mutex_lock(&s->lock);
-    cluster_offset = get_cluster_offset(bs, offset, 2, out_len, 0, 0);
-    qemu_co_mutex_unlock(&s->lock);
-    if (cluster_offset == 0) {
-        ret = -EIO;
-        goto fail;
-    }
-    cluster_offset &= s->cluster_offset_mask;
+    } else {
+        cluster_offset = get_cluster_offset(bs, sector_num << 9, 2,
+                                            out_len, 0, 0);
+        if (cluster_offset == 0) {
+            ret = -EIO;
+            goto fail;
+        }
 
-    iov = (struct iovec) {
-        .iov_base   = out_buf,
-        .iov_len    = out_len,
-    };
-    qemu_iovec_init_external(&hd_qiov, &iov, 1);
-    ret = bdrv_co_pwritev(bs->file, cluster_offset, out_len, &hd_qiov, 0);
-    if (ret < 0) {
-        goto fail;
+        cluster_offset &= s->cluster_offset_mask;
+        ret = bdrv_pwrite(bs->file->bs, cluster_offset, out_buf, out_len);
+        if (ret < 0) {
+            goto fail;
+        }
     }
-success:
+
     ret = 0;
 fail:
-    qemu_vfree(buf);
     g_free(out_buf);
     return ret;
 }
@@ -1054,7 +1014,6 @@ static BlockDriver bdrv_qcow = {
     .bdrv_probe		= qcow_probe,
     .bdrv_open		= qcow_open,
     .bdrv_close		= qcow_close,
-    .bdrv_child_perm        = bdrv_format_default_perms,
     .bdrv_reopen_prepare    = qcow_reopen_prepare,
     .bdrv_create            = qcow_create,
     .bdrv_has_zero_init     = bdrv_has_zero_init_1,
@@ -1066,7 +1025,7 @@ static BlockDriver bdrv_qcow = {
 
     .bdrv_set_key           = qcow_set_key,
     .bdrv_make_empty        = qcow_make_empty,
-    .bdrv_co_pwritev_compressed = qcow_co_pwritev_compressed,
+    .bdrv_write_compressed  = qcow_write_compressed,
     .bdrv_get_info          = qcow_get_info,
 
     .create_opts            = &qcow_create_opts,

block/qcow2-cache.c

@@ -22,9 +22,16 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
+/* Needed for CONFIG_MADVISE */
+#include "config-host.h"
+
+#if defined(CONFIG_MADVISE) || defined(CONFIG_POSIX_MADVISE)
+#include <sys/mman.h>
+#endif
+
 #include "block/block_int.h"
 #include "qemu-common.h"
+#include "qemu/osdep.h"
 #include "qcow2.h"
 #include "trace.h"
 
@@ -65,8 +72,7 @@ static inline int qcow2_cache_get_table_idx(BlockDriverState *bs,
 static void qcow2_cache_table_release(BlockDriverState *bs, Qcow2Cache *c,
                                       int i, int num_tables)
 {
-/* Using MADV_DONTNEED to discard memory is a Linux-specific feature */
-#ifdef CONFIG_LINUX
+#if QEMU_MADV_DONTNEED != QEMU_MADV_INVALID
     BDRVQcow2State *s = bs->opaque;
     void *t = qcow2_cache_get_table_addr(bs, c, i);
     int align = getpagesize();
@@ -74,7 +80,7 @@ static void qcow2_cache_table_release(BlockDriverState *bs, Qcow2Cache *c,
     size_t offset = QEMU_ALIGN_UP((uintptr_t) t, align) - (uintptr_t) t;
     size_t length = QEMU_ALIGN_DOWN(mem_size - offset, align);
     if (length > 0) {
-        madvise((uint8_t *) t + offset, length, MADV_DONTNEED);
+        qemu_madvise((uint8_t *) t + offset, length, QEMU_MADV_DONTNEED);
     }
 #endif
 }
@@ -210,7 +216,7 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
         BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE);
     }
 
-    ret = bdrv_pwrite(bs->file, c->entries[i].offset,
+    ret = bdrv_pwrite(bs->file->bs, c->entries[i].offset,
                       qcow2_cache_get_table_addr(bs, c, i), s->cluster_size);
     if (ret < 0) {
         return ret;
@@ -221,7 +227,7 @@ static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i)
     return 0;
 }
 
-int qcow2_cache_write(BlockDriverState *bs, Qcow2Cache *c)
+int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
 {
     BDRVQcow2State *s = bs->opaque;
     int result = 0;
@@ -237,15 +243,8 @@ int qcow2_cache_write(BlockDriverState *bs, Qcow2Cache *c)
         }
     }
 
-    return result;
-}
-
-int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c)
-{
-    int result = qcow2_cache_write(bs, c);
-
     if (result == 0) {
-        int ret = bdrv_flush(bs->file->bs);
+        ret = bdrv_flush(bs->file->bs);
         if (ret < 0) {
             result = ret;
         }
@@ -357,7 +356,7 @@ static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c,
             BLKDBG_EVENT(bs->file, BLKDBG_L2_LOAD);
         }
 
-        ret = bdrv_pread(bs->file, offset,
+        ret = bdrv_pread(bs->file->bs, offset,
                          qcow2_cache_get_table_addr(bs, c, i),
                          s->cluster_size);
         if (ret < 0) {

block/qcow2-cluster.c

@@ -22,14 +22,11 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
 #include <zlib.h>
 
-#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "block/qcow2.h"
-#include "qemu/bswap.h"
 #include "trace.h"
 
 int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
@@ -65,8 +62,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
         }
     }
 
-    QEMU_BUILD_BUG_ON(QCOW_MAX_L1_SIZE > INT_MAX);
-    if (new_l1_size > QCOW_MAX_L1_SIZE / sizeof(uint64_t)) {
+    if (new_l1_size > INT_MAX / sizeof(uint64_t)) {
         return -EFBIG;
     }
 
@@ -83,9 +79,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
     }
     memset(new_l1_table, 0, align_offset(new_l1_size2, 512));
 
-    if (s->l1_size) {
-        memcpy(new_l1_table, s->l1_table, s->l1_size * sizeof(uint64_t));
-    }
+    memcpy(new_l1_table, s->l1_table, s->l1_size * sizeof(uint64_t));
 
     /* write new table (align to cluster) */
     BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ALLOC_TABLE);
@@ -111,7 +105,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
     BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_WRITE_TABLE);
     for(i = 0; i < s->l1_size; i++)
         new_l1_table[i] = cpu_to_be64(new_l1_table[i]);
-    ret = bdrv_pwrite_sync(bs->file, new_l1_table_offset,
+    ret = bdrv_pwrite_sync(bs->file->bs, new_l1_table_offset,
                            new_l1_table, new_l1_size2);
     if (ret < 0)
         goto fail;
@@ -120,9 +114,9 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
 
     /* set new table */
     BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ACTIVATE_TABLE);
-    stl_be_p(data, new_l1_size);
+    cpu_to_be32w((uint32_t*)data, new_l1_size);
     stq_be_p(data + 4, new_l1_table_offset);
-    ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, l1_size),
+    ret = bdrv_pwrite_sync(bs->file->bs, offsetof(QCowHeader, l1_size),
                            data, sizeof(data));
     if (ret < 0) {
         goto fail;
@@ -157,9 +151,11 @@ static int l2_load(BlockDriverState *bs, uint64_t l2_offset,
     uint64_t **l2_table)
 {
     BDRVQcow2State *s = bs->opaque;
+    int ret;
 
-    return qcow2_cache_get(bs, s->l2_table_cache, l2_offset,
-                           (void **)l2_table);
+    ret = qcow2_cache_get(bs, s->l2_table_cache, l2_offset, (void**) l2_table);
+
+    return ret;
 }
 
 /*
@@ -188,7 +184,7 @@ int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index)
     }
 
     BLKDBG_EVENT(bs->file, BLKDBG_L1_UPDATE);
-    ret = bdrv_pwrite_sync(bs->file,
+    ret = bdrv_pwrite_sync(bs->file->bs,
                            s->l1_table_offset + 8 * l1_start_index,
                            buf, sizeof(buf));
     if (ret < 0) {
@@ -309,19 +305,14 @@ static int count_contiguous_clusters(int nb_clusters, int cluster_size,
         uint64_t *l2_table, uint64_t stop_flags)
 {
     int i;
-    QCow2ClusterType first_cluster_type;
     uint64_t mask = stop_flags | L2E_OFFSET_MASK | QCOW_OFLAG_COMPRESSED;
     uint64_t first_entry = be64_to_cpu(l2_table[0]);
     uint64_t offset = first_entry & mask;
 
-    if (!offset) {
+    if (!offset)
         return 0;
-    }
 
-    /* must be allocated */
-    first_cluster_type = qcow2_get_cluster_type(first_entry);
-    assert(first_cluster_type == QCOW2_CLUSTER_NORMAL ||
-           first_cluster_type == QCOW2_CLUSTER_ZERO_ALLOC);
+    assert(qcow2_get_cluster_type(first_entry) == QCOW2_CLUSTER_NORMAL);
 
     for (i = 0; i < nb_clusters; i++) {
         uint64_t l2_entry = be64_to_cpu(l2_table[i]) & mask;
@@ -333,21 +324,14 @@ static int count_contiguous_clusters(int nb_clusters, int cluster_size,
 	return i;
 }
 
-/*
- * Checks how many consecutive unallocated clusters in a given L2
- * table have the same cluster type.
- */
-static int count_contiguous_clusters_unallocated(int nb_clusters,
-                                                 uint64_t *l2_table,
-                                                 QCow2ClusterType wanted_type)
+static int count_contiguous_clusters_by_type(int nb_clusters,
+                                             uint64_t *l2_table,
+                                             int wanted_type)
 {
     int i;
 
-    assert(wanted_type == QCOW2_CLUSTER_ZERO_PLAIN ||
-           wanted_type == QCOW2_CLUSTER_UNALLOCATED);
     for (i = 0; i < nb_clusters; i++) {
-        uint64_t entry = be64_to_cpu(l2_table[i]);
-        QCow2ClusterType type = qcow2_get_cluster_type(entry);
+        int type = qcow2_get_cluster_type(be64_to_cpu(l2_table[i]));
 
         if (type != wanted_type) {
             break;
@@ -403,18 +387,22 @@ int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num,
     return 0;
 }
 
-static int coroutine_fn do_perform_cow(BlockDriverState *bs,
-                                       uint64_t src_cluster_offset,
-                                       uint64_t cluster_offset,
-                                       int offset_in_cluster,
-                                       int bytes)
+static int coroutine_fn copy_sectors(BlockDriverState *bs,
+                                     uint64_t start_sect,
+                                     uint64_t cluster_offset,
+                                     int n_start, int n_end)
 {
     BDRVQcow2State *s = bs->opaque;
     QEMUIOVector qiov;
     struct iovec iov;
-    int ret;
+    int n, ret;
 
-    iov.iov_len = bytes;
+    n = n_end - n_start;
+    if (n <= 0) {
+        return 0;
+    }
+
+    iov.iov_len = n * BDRV_SECTOR_SIZE;
     iov.iov_base = qemu_try_blockalign(bs, iov.iov_len);
     if (iov.iov_base == NULL) {
         return -ENOMEM;
@@ -433,21 +421,17 @@ static int coroutine_fn do_perform_cow(BlockDriverState *bs,
      * interface.  This avoids double I/O throttling and request tracking,
      * which can lead to deadlock when block layer copy-on-read is enabled.
      */
-    ret = bs->drv->bdrv_co_preadv(bs, src_cluster_offset + offset_in_cluster,
-                                  bytes, &qiov, 0);
+    ret = bs->drv->bdrv_co_readv(bs, start_sect + n_start, n, &qiov);
     if (ret < 0) {
         goto out;
     }
 
     if (bs->encrypted) {
         Error *err = NULL;
-        int64_t sector = (src_cluster_offset + offset_in_cluster)
-                         >> BDRV_SECTOR_BITS;
         assert(s->cipher);
-        assert((offset_in_cluster & ~BDRV_SECTOR_MASK) == 0);
-        assert((bytes & ~BDRV_SECTOR_MASK) == 0);
-        if (qcow2_encrypt_sectors(s, sector, iov.iov_base, iov.iov_base,
-                                  bytes >> BDRV_SECTOR_BITS, true, &err) < 0) {
+        if (qcow2_encrypt_sectors(s, start_sect + n_start,
+                                  iov.iov_base, iov.iov_base, n,
+                                  true, &err) < 0) {
             ret = -EIO;
             error_free(err);
             goto out;
@@ -455,14 +439,14 @@ static int coroutine_fn do_perform_cow(BlockDriverState *bs,
     }
 
     ret = qcow2_pre_write_overlap_check(bs, 0,
-            cluster_offset + offset_in_cluster, bytes);
+            cluster_offset + n_start * BDRV_SECTOR_SIZE, n * BDRV_SECTOR_SIZE);
     if (ret < 0) {
         goto out;
     }
 
     BLKDBG_EVENT(bs->file, BLKDBG_COW_WRITE);
-    ret = bdrv_co_pwritev(bs->file, cluster_offset + offset_in_cluster,
-                          bytes, &qiov, 0);
+    ret = bdrv_co_writev(bs->file->bs, (cluster_offset >> 9) + n_start, n,
+                         &qiov);
     if (ret < 0) {
         goto out;
     }
@@ -477,44 +461,47 @@ out:
 /*
  * get_cluster_offset
  *
- * For a given offset of the virtual disk, find the cluster type and offset in
- * the qcow2 file. The offset is stored in *cluster_offset.
+ * For a given offset of the disk image, find the cluster offset in
+ * qcow2 file. The offset is stored in *cluster_offset.
  *
- * On entry, *bytes is the maximum number of contiguous bytes starting at
- * offset that we are interested in.
+ * on entry, *num is the number of contiguous sectors we'd like to
+ * access following offset.
  *
- * On exit, *bytes is the number of bytes starting at offset that have the same
- * cluster type and (if applicable) are stored contiguously in the image file.
- * Compressed clusters are always returned one by one.
+ * on exit, *num is the number of contiguous sectors we can read.
  *
  * Returns the cluster type (QCOW2_CLUSTER_*) on success, -errno in error
  * cases.
  */
 int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
-                             unsigned int *bytes, uint64_t *cluster_offset)
+    int *num, uint64_t *cluster_offset)
 {
     BDRVQcow2State *s = bs->opaque;
     unsigned int l2_index;
     uint64_t l1_index, l2_offset, *l2_table;
     int l1_bits, c;
-    unsigned int offset_in_cluster;
-    uint64_t bytes_available, bytes_needed, nb_clusters;
-    QCow2ClusterType type;
+    unsigned int index_in_cluster, nb_clusters;
+    uint64_t nb_available, nb_needed;
     int ret;
 
-    offset_in_cluster = offset_into_cluster(s, offset);
-    bytes_needed = (uint64_t) *bytes + offset_in_cluster;
+    index_in_cluster = (offset >> 9) & (s->cluster_sectors - 1);
+    nb_needed = *num + index_in_cluster;
 
     l1_bits = s->l2_bits + s->cluster_bits;
 
-    /* compute how many bytes there are between the start of the cluster
-     * containing offset and the end of the l1 entry */
-    bytes_available = (1ULL << l1_bits) - (offset & ((1ULL << l1_bits) - 1))
-                    + offset_in_cluster;
+    /* compute how many bytes there are between the offset and
+     * the end of the l1 entry
+     */
 
-    if (bytes_needed > bytes_available) {
-        bytes_needed = bytes_available;
+    nb_available = (1ULL << l1_bits) - (offset & ((1ULL << l1_bits) - 1));
+
+    /* compute the number of available sectors */
+
+    nb_available = (nb_available >> 9) + index_in_cluster;
+
+    if (nb_needed > nb_available) {
+        nb_needed = nb_available;
     }
+    assert(nb_needed <= INT_MAX);
 
     *cluster_offset = 0;
 
@@ -522,13 +509,13 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
 
     l1_index = offset >> l1_bits;
     if (l1_index >= s->l1_size) {
-        type = QCOW2_CLUSTER_UNALLOCATED;
+        ret = QCOW2_CLUSTER_UNALLOCATED;
         goto out;
     }
 
     l2_offset = s->l1_table[l1_index] & L1E_OFFSET_MASK;
     if (!l2_offset) {
-        type = QCOW2_CLUSTER_UNALLOCATED;
+        ret = QCOW2_CLUSTER_UNALLOCATED;
         goto out;
     }
 
@@ -551,43 +538,41 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
     l2_index = (offset >> s->cluster_bits) & (s->l2_size - 1);
     *cluster_offset = be64_to_cpu(l2_table[l2_index]);
 
-    nb_clusters = size_to_clusters(s, bytes_needed);
-    /* bytes_needed <= *bytes + offset_in_cluster, both of which are unsigned
-     * integers; the minimum cluster size is 512, so this assertion is always
-     * true */
-    assert(nb_clusters <= INT_MAX);
+    /* nb_needed <= INT_MAX, thus nb_clusters <= INT_MAX, too */
+    nb_clusters = size_to_clusters(s, nb_needed << 9);
 
-    type = qcow2_get_cluster_type(*cluster_offset);
-    if (s->qcow_version < 3 && (type == QCOW2_CLUSTER_ZERO_PLAIN ||
-                                type == QCOW2_CLUSTER_ZERO_ALLOC)) {
-        qcow2_signal_corruption(bs, true, -1, -1, "Zero cluster entry found"
-                                " in pre-v3 image (L2 offset: %#" PRIx64
-                                ", L2 index: %#x)", l2_offset, l2_index);
-        ret = -EIO;
-        goto fail;
-    }
-    switch (type) {
+    ret = qcow2_get_cluster_type(*cluster_offset);
+    switch (ret) {
     case QCOW2_CLUSTER_COMPRESSED:
         /* Compressed clusters can only be processed one by one */
         c = 1;
         *cluster_offset &= L2E_COMPRESSED_OFFSET_SIZE_MASK;
         break;
-    case QCOW2_CLUSTER_ZERO_PLAIN:
-    case QCOW2_CLUSTER_UNALLOCATED:
-        /* how many empty clusters ? */
-        c = count_contiguous_clusters_unallocated(nb_clusters,
-                                                  &l2_table[l2_index], type);
+    case QCOW2_CLUSTER_ZERO:
+        if (s->qcow_version < 3) {
+            qcow2_signal_corruption(bs, true, -1, -1, "Zero cluster entry found"
+                                    " in pre-v3 image (L2 offset: %#" PRIx64
+                                    ", L2 index: %#x)", l2_offset, l2_index);
+            ret = -EIO;
+            goto fail;
+        }
+        c = count_contiguous_clusters_by_type(nb_clusters, &l2_table[l2_index],
+                                              QCOW2_CLUSTER_ZERO);
+        *cluster_offset = 0;
+        break;
+    case QCOW2_CLUSTER_UNALLOCATED:
+        /* how many empty clusters ? */
+        c = count_contiguous_clusters_by_type(nb_clusters, &l2_table[l2_index],
+                                              QCOW2_CLUSTER_UNALLOCATED);
         *cluster_offset = 0;
         break;
-    case QCOW2_CLUSTER_ZERO_ALLOC:
     case QCOW2_CLUSTER_NORMAL:
         /* how many allocated clusters ? */
         c = count_contiguous_clusters(nb_clusters, s->cluster_size,
-                                      &l2_table[l2_index], QCOW_OFLAG_ZERO);
+                &l2_table[l2_index], QCOW_OFLAG_ZERO);
         *cluster_offset &= L2E_OFFSET_MASK;
         if (offset_into_cluster(s, *cluster_offset)) {
-            qcow2_signal_corruption(bs, true, -1, -1,
-                                    "Cluster allocation offset %#"
+            qcow2_signal_corruption(bs, true, -1, -1, "Data cluster offset %#"
                                     PRIx64 " unaligned (L2 offset: %#" PRIx64
                                     ", L2 index: %#x)", *cluster_offset,
                                     l2_offset, l2_index);
@@ -601,20 +586,15 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
 
     qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
 
-    bytes_available = (int64_t)c * s->cluster_size;
+    nb_available = (c * s->cluster_sectors);
 
 out:
-    if (bytes_available > bytes_needed) {
-        bytes_available = bytes_needed;
-    }
+    if (nb_available > nb_needed)
+        nb_available = nb_needed;
 
-    /* bytes_available <= bytes_needed <= *bytes + offset_in_cluster;
-     * subtracting offset_in_cluster will therefore definitely yield something
-     * not exceeding UINT_MAX */
-    assert(bytes_available - offset_in_cluster <= UINT_MAX);
-    *bytes = bytes_available - offset_in_cluster;
+    *num = nb_available - index_in_cluster;
 
-    return type;
+    return ret;
 
 fail:
     qcow2_cache_put(bs, s->l2_table_cache, (void **)&l2_table);
@@ -758,12 +738,14 @@ static int perform_cow(BlockDriverState *bs, QCowL2Meta *m, Qcow2COWRegion *r)
     BDRVQcow2State *s = bs->opaque;
     int ret;
 
-    if (r->nb_bytes == 0) {
+    if (r->nb_sectors == 0) {
         return 0;
     }
 
     qemu_co_mutex_unlock(&s->lock);
-    ret = do_perform_cow(bs, m->offset, m->alloc_offset, r->offset, r->nb_bytes);
+    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) {
@@ -825,14 +807,13 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
     assert(l2_index + m->nb_clusters <= s->l2_size);
     for (i = 0; i < m->nb_clusters; i++) {
         /* if two concurrent writes happen to the same unallocated cluster
-         * each write allocates separate cluster and writes data concurrently.
-         * The first one to complete updates l2 table with pointer to its
-         * cluster the second one has to do RMW (which is done above by
-         * perform_cow()), update l2 table with its cluster pointer and free
-         * old cluster. This is what this loop does */
-        if (l2_table[l2_index + i] != 0) {
+	 * each write allocates separate cluster and writes data concurrently.
+	 * The first one to complete updates l2 table with pointer to its
+	 * cluster the second one has to do RMW (which is done above by
+	 * copy_sectors()), update l2 table with its cluster pointer and free
+	 * old cluster. This is what this loop does */
+        if(l2_table[l2_index + i] != 0)
             old_cluster[j++] = l2_table[l2_index + i];
-        }
 
         l2_table[l2_index + i] = cpu_to_be64((cluster_offset +
                     (i << s->cluster_bits)) | QCOW_OFLAG_COPIED);
@@ -847,7 +828,7 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
      * Don't discard clusters that reach a refcount of 0 (e.g. compressed
      * clusters), the next write will reuse them anyway.
      */
-    if (!m->keep_old_clusters && j != 0) {
+    if (j != 0) {
         for (i = 0; i < j; i++) {
             qcow2_free_any_clusters(bs, be64_to_cpu(old_cluster[i]), 1,
                                     QCOW2_DISCARD_NEVER);
@@ -872,7 +853,7 @@ static int count_cow_clusters(BDRVQcow2State *s, int nb_clusters,
 
     for (i = 0; i < nb_clusters; i++) {
         uint64_t l2_entry = be64_to_cpu(l2_table[l2_index + i]);
-        QCow2ClusterType cluster_type = qcow2_get_cluster_type(l2_entry);
+        int cluster_type = qcow2_get_cluster_type(l2_entry);
 
         switch(cluster_type) {
         case QCOW2_CLUSTER_NORMAL:
@@ -882,8 +863,7 @@ static int count_cow_clusters(BDRVQcow2State *s, int nb_clusters,
             break;
         case QCOW2_CLUSTER_UNALLOCATED:
         case QCOW2_CLUSTER_COMPRESSED:
-        case QCOW2_CLUSTER_ZERO_PLAIN:
-        case QCOW2_CLUSTER_ZERO_ALLOC:
+        case QCOW2_CLUSTER_ZERO:
             break;
         default:
             abort();
@@ -945,7 +925,9 @@ static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset,
             if (bytes == 0) {
                 /* Wait for the dependency to complete. We need to recheck
                  * the free/allocated clusters when we continue. */
-                qemu_co_queue_wait(&old_alloc->dependent_requests, &s->lock);
+                qemu_co_mutex_unlock(&s->lock);
+                qemu_co_queue_wait(&old_alloc->dependent_requests);
+                qemu_co_mutex_lock(&s->lock);
                 return -EAGAIN;
             }
         }
@@ -1145,9 +1127,8 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
     uint64_t entry;
     uint64_t nb_clusters;
     int ret;
-    bool keep_old_clusters = false;
 
-    uint64_t alloc_cluster_offset = 0;
+    uint64_t alloc_cluster_offset;
 
     trace_qcow2_handle_alloc(qemu_coroutine_self(), guest_offset, *host_offset,
                              *bytes);
@@ -1184,73 +1165,55 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
      * wrong with our code. */
     assert(nb_clusters > 0);
 
-    if (qcow2_get_cluster_type(entry) == QCOW2_CLUSTER_ZERO_ALLOC &&
-        (entry & QCOW_OFLAG_COPIED) &&
-        (!*host_offset ||
-         start_of_cluster(s, *host_offset) == (entry & L2E_OFFSET_MASK)))
-    {
-        /* Try to reuse preallocated zero clusters; contiguous normal clusters
-         * would be fine, too, but count_cow_clusters() above has limited
-         * nb_clusters already to a range of COW clusters */
-        int preallocated_nb_clusters =
-            count_contiguous_clusters(nb_clusters, s->cluster_size,
-                                      &l2_table[l2_index], QCOW_OFLAG_COPIED);
-        assert(preallocated_nb_clusters > 0);
-
-        nb_clusters = preallocated_nb_clusters;
-        alloc_cluster_offset = entry & L2E_OFFSET_MASK;
-
-        /* We want to reuse these clusters, so qcow2_alloc_cluster_link_l2()
-         * should not free them. */
-        keep_old_clusters = true;
-    }
-
     qcow2_cache_put(bs, s->l2_table_cache, (void **) &l2_table);
 
+    /* Allocate, if necessary at a given offset in the image file */
+    alloc_cluster_offset = start_of_cluster(s, *host_offset);
+    ret = do_alloc_cluster_offset(bs, guest_offset, &alloc_cluster_offset,
+                                  &nb_clusters);
+    if (ret < 0) {
+        goto fail;
+    }
+
+    /* Can't extend contiguous allocation */
+    if (nb_clusters == 0) {
+        *bytes = 0;
+        return 0;
+    }
+
+    /* !*host_offset would overwrite the image header and is reserved for "no
+     * host offset preferred". If 0 was a valid host offset, it'd trigger the
+     * following overlap check; do that now to avoid having an invalid value in
+     * *host_offset. */
     if (!alloc_cluster_offset) {
-        /* Allocate, if necessary at a given offset in the image file */
-        alloc_cluster_offset = start_of_cluster(s, *host_offset);
-        ret = do_alloc_cluster_offset(bs, guest_offset, &alloc_cluster_offset,
-                                      &nb_clusters);
-        if (ret < 0) {
-            goto fail;
-        }
-
-        /* Can't extend contiguous allocation */
-        if (nb_clusters == 0) {
-            *bytes = 0;
-            return 0;
-        }
-
-        /* !*host_offset would overwrite the image header and is reserved for
-         * "no host offset preferred". If 0 was a valid host offset, it'd
-         * trigger the following overlap check; do that now to avoid having an
-         * invalid value in *host_offset. */
-        if (!alloc_cluster_offset) {
-            ret = qcow2_pre_write_overlap_check(bs, 0, alloc_cluster_offset,
-                                                nb_clusters * s->cluster_size);
-            assert(ret < 0);
-            goto fail;
-        }
+        ret = qcow2_pre_write_overlap_check(bs, 0, alloc_cluster_offset,
+                                            nb_clusters * s->cluster_size);
+        assert(ret < 0);
+        goto fail;
     }
 
     /*
      * Save info needed for meta data update.
      *
-     * requested_bytes: Number of bytes from the start of the first
+     * requested_sectors: Number of sectors from the start of the first
      * newly allocated cluster to the end of the (possibly shortened
      * before) write request.
      *
-     * avail_bytes: Number of bytes from the start of the first
+     * avail_sectors: Number of sectors from the start of the first
      * newly allocated to the end of the last newly allocated cluster.
      *
-     * nb_bytes: The number of bytes from the start of the first
+     * nb_sectors: The number of sectors from the start of the first
      * newly allocated cluster to the end of the area that the write
      * request actually writes to (excluding COW at the end)
      */
-    uint64_t requested_bytes = *bytes + offset_into_cluster(s, guest_offset);
-    int avail_bytes = MIN(INT_MAX, nb_clusters << s->cluster_bits);
-    int nb_bytes = MIN(requested_bytes, avail_bytes);
+    int requested_sectors =
+        (*bytes + offset_into_cluster(s, guest_offset))
+        >> BDRV_SECTOR_BITS;
+    int avail_sectors = nb_clusters
+                        << (s->cluster_bits - BDRV_SECTOR_BITS);
+    int alloc_n_start = offset_into_cluster(s, guest_offset)
+                        >> BDRV_SECTOR_BITS;
+    int nb_sectors = MIN(requested_sectors, avail_sectors);
     QCowL2Meta *old_m = *m;
 
     *m = g_malloc0(sizeof(**m));
@@ -1261,23 +1224,23 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
         .alloc_offset   = alloc_cluster_offset,
         .offset         = start_of_cluster(s, guest_offset),
         .nb_clusters    = nb_clusters,
-
-        .keep_old_clusters  = keep_old_clusters,
+        .nb_available   = nb_sectors,
 
         .cow_start = {
             .offset     = 0,
-            .nb_bytes   = offset_into_cluster(s, guest_offset),
+            .nb_sectors = alloc_n_start,
         },
         .cow_end = {
-            .offset     = nb_bytes,
-            .nb_bytes   = avail_bytes - nb_bytes,
+            .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);
 
     *host_offset = alloc_cluster_offset + offset_into_cluster(s, guest_offset);
-    *bytes = MIN(*bytes, nb_bytes - offset_into_cluster(s, guest_offset));
+    *bytes = MIN(*bytes, (nb_sectors * BDRV_SECTOR_SIZE)
+                         - offset_into_cluster(s, guest_offset));
     assert(*bytes != 0);
 
     return 1;
@@ -1309,8 +1272,7 @@ fail:
  * Return 0 on success and -errno in error cases
  */
 int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
-                               unsigned int *bytes, uint64_t *host_offset,
-                               QCowL2Meta **m)
+    int *num, uint64_t *host_offset, QCowL2Meta **m)
 {
     BDRVQcow2State *s = bs->opaque;
     uint64_t start, remaining;
@@ -1318,11 +1280,13 @@ int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
     uint64_t cur_bytes;
     int ret;
 
-    trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset, *bytes);
+    trace_qcow2_alloc_clusters_offset(qemu_coroutine_self(), offset, *num);
+
+    assert((offset & ~BDRV_SECTOR_MASK) == 0);
 
 again:
     start = offset;
-    remaining = *bytes;
+    remaining = (uint64_t)*num << BDRV_SECTOR_BITS;
     cluster_offset = 0;
     *host_offset = 0;
     cur_bytes = 0;
@@ -1408,8 +1372,8 @@ again:
         }
     }
 
-    *bytes -= remaining;
-    assert(*bytes > 0);
+    *num -= remaining >> BDRV_SECTOR_BITS;
+    assert(*num > 0);
     assert(*host_offset != 0);
 
     return 0;
@@ -1454,7 +1418,7 @@ int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
         sector_offset = coffset & 511;
         csize = nb_csectors * 512 - sector_offset;
         BLKDBG_EVENT(bs->file, BLKDBG_READ_COMPRESSED);
-        ret = bdrv_read(bs->file, coffset >> 9, s->cluster_data,
+        ret = bdrv_read(bs->file->bs, coffset >> 9, s->cluster_data,
                         nb_csectors);
         if (ret < 0) {
             return ret;
@@ -1511,25 +1475,24 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
          * but rather fall through to the backing file.
          */
         switch (qcow2_get_cluster_type(old_l2_entry)) {
-        case QCOW2_CLUSTER_UNALLOCATED:
-            if (full_discard || !bs->backing) {
-                continue;
-            }
-            break;
+            case QCOW2_CLUSTER_UNALLOCATED:
+                if (full_discard || !bs->backing) {
+                    continue;
+                }
+                break;
 
-        case QCOW2_CLUSTER_ZERO_PLAIN:
-            if (!full_discard) {
-                continue;
-            }
-            break;
+            case QCOW2_CLUSTER_ZERO:
+                if (!full_discard) {
+                    continue;
+                }
+                break;
 
-        case QCOW2_CLUSTER_ZERO_ALLOC:
-        case QCOW2_CLUSTER_NORMAL:
-        case QCOW2_CLUSTER_COMPRESSED:
-            break;
+            case QCOW2_CLUSTER_NORMAL:
+            case QCOW2_CLUSTER_COMPRESSED:
+                break;
 
-        default:
-            abort();
+            default:
+                abort();
         }
 
         /* First remove L2 entries */
@@ -1549,36 +1512,37 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
     return nb_clusters;
 }
 
-int qcow2_cluster_discard(BlockDriverState *bs, uint64_t offset,
-                          uint64_t bytes, enum qcow2_discard_type type,
-                          bool full_discard)
+int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
+    int nb_sectors, enum qcow2_discard_type type, bool full_discard)
 {
     BDRVQcow2State *s = bs->opaque;
-    uint64_t end_offset = offset + bytes;
+    uint64_t end_offset;
     uint64_t nb_clusters;
-    int64_t cleared;
     int ret;
 
-    /* Caller must pass aligned values, except at image end */
-    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
-    assert(QEMU_IS_ALIGNED(end_offset, s->cluster_size) ||
-           end_offset == bs->total_sectors << BDRV_SECTOR_BITS);
+    end_offset = offset + (nb_sectors << BDRV_SECTOR_BITS);
 
-    nb_clusters = size_to_clusters(s, bytes);
+    /* Round start up and end down */
+    offset = align_offset(offset, s->cluster_size);
+    end_offset = start_of_cluster(s, end_offset);
+
+    if (offset > end_offset) {
+        return 0;
+    }
+
+    nb_clusters = size_to_clusters(s, end_offset - offset);
 
     s->cache_discards = true;
 
     /* Each L2 table is handled by its own loop iteration */
     while (nb_clusters > 0) {
-        cleared = discard_single_l2(bs, offset, nb_clusters, type,
-                                    full_discard);
-        if (cleared < 0) {
-            ret = cleared;
+        ret = discard_single_l2(bs, offset, nb_clusters, type, full_discard);
+        if (ret < 0) {
             goto fail;
         }
 
-        nb_clusters -= cleared;
-        offset += (cleared * s->cluster_size);
+        nb_clusters -= ret;
+        offset += (ret * s->cluster_size);
     }
 
     ret = 0;
@@ -1595,14 +1559,13 @@ fail:
  * clusters.
  */
 static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
-                          uint64_t nb_clusters, int flags)
+                          uint64_t nb_clusters)
 {
     BDRVQcow2State *s = bs->opaque;
     uint64_t *l2_table;
     int l2_index;
     int ret;
     int i;
-    bool unmap = !!(flags & BDRV_REQ_MAY_UNMAP);
 
     ret = get_cluster_table(bs, offset, &l2_table, &l2_index);
     if (ret < 0) {
@@ -1615,22 +1578,12 @@ static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
 
     for (i = 0; i < nb_clusters; i++) {
         uint64_t old_offset;
-        QCow2ClusterType cluster_type;
 
         old_offset = be64_to_cpu(l2_table[l2_index + i]);
 
-        /*
-         * Minimize L2 changes if the cluster already reads back as
-         * zeroes with correct allocation.
-         */
-        cluster_type = qcow2_get_cluster_type(old_offset);
-        if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN ||
-            (cluster_type == QCOW2_CLUSTER_ZERO_ALLOC && !unmap)) {
-            continue;
-        }
-
+        /* Update L2 entries */
         qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache, l2_table);
-        if (cluster_type == QCOW2_CLUSTER_COMPRESSED || unmap) {
+        if (old_offset & QCOW_OFLAG_COMPRESSED) {
             l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
             qcow2_free_any_clusters(bs, old_offset, 1, QCOW2_DISCARD_REQUEST);
         } else {
@@ -1643,39 +1596,30 @@ static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
     return nb_clusters;
 }
 
-int qcow2_cluster_zeroize(BlockDriverState *bs, uint64_t offset,
-                          uint64_t bytes, int flags)
+int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors)
 {
     BDRVQcow2State *s = bs->opaque;
-    uint64_t end_offset = offset + bytes;
     uint64_t nb_clusters;
-    int64_t cleared;
     int ret;
 
-    /* Caller must pass aligned values, except at image end */
-    assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
-    assert(QEMU_IS_ALIGNED(end_offset, s->cluster_size) ||
-           end_offset == bs->total_sectors << BDRV_SECTOR_BITS);
-
     /* The zero flag is only supported by version 3 and newer */
     if (s->qcow_version < 3) {
         return -ENOTSUP;
     }
 
     /* Each L2 table is handled by its own loop iteration */
-    nb_clusters = size_to_clusters(s, bytes);
+    nb_clusters = size_to_clusters(s, nb_sectors << BDRV_SECTOR_BITS);
 
     s->cache_discards = true;
 
     while (nb_clusters > 0) {
-        cleared = zero_single_l2(bs, offset, nb_clusters, flags);
-        if (cleared < 0) {
-            ret = cleared;
+        ret = zero_single_l2(bs, offset, nb_clusters);
+        if (ret < 0) {
             goto fail;
         }
 
-        nb_clusters -= cleared;
-        offset += (cleared * s->cluster_size);
+        nb_clusters -= ret;
+        offset += (ret * s->cluster_size);
     }
 
     ret = 0;
@@ -1697,8 +1641,7 @@ fail:
 static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
                                       int l1_size, int64_t *visited_l1_entries,
                                       int64_t l1_entries,
-                                      BlockDriverAmendStatusCB *status_cb,
-                                      void *cb_opaque)
+                                      BlockDriverAmendStatusCB *status_cb)
 {
     BDRVQcow2State *s = bs->opaque;
     bool is_active_l1 = (l1_table == s->l1_table);
@@ -1724,7 +1667,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
             /* unallocated */
             (*visited_l1_entries)++;
             if (status_cb) {
-                status_cb(bs, *visited_l1_entries, l1_entries, cb_opaque);
+                status_cb(bs, *visited_l1_entries, l1_entries);
             }
             continue;
         }
@@ -1743,7 +1686,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
                     (void **)&l2_table);
         } else {
             /* load inactive L2 tables from disk */
-            ret = bdrv_read(bs->file, l2_offset / BDRV_SECTOR_SIZE,
+            ret = bdrv_read(bs->file->bs, l2_offset / BDRV_SECTOR_SIZE,
                             (void *)l2_table, s->cluster_sectors);
         }
         if (ret < 0) {
@@ -1759,14 +1702,14 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
         for (j = 0; j < s->l2_size; j++) {
             uint64_t l2_entry = be64_to_cpu(l2_table[j]);
             int64_t offset = l2_entry & L2E_OFFSET_MASK;
-            QCow2ClusterType cluster_type = qcow2_get_cluster_type(l2_entry);
+            int cluster_type = qcow2_get_cluster_type(l2_entry);
+            bool preallocated = offset != 0;
 
-            if (cluster_type != QCOW2_CLUSTER_ZERO_PLAIN &&
-                cluster_type != QCOW2_CLUSTER_ZERO_ALLOC) {
+            if (cluster_type != QCOW2_CLUSTER_ZERO) {
                 continue;
             }
 
-            if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) {
+            if (!preallocated) {
                 if (!bs->backing) {
                     /* not backed; therefore we can simply deallocate the
                      * cluster */
@@ -1797,12 +1740,11 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
             }
 
             if (offset_into_cluster(s, offset)) {
-                qcow2_signal_corruption(bs, true, -1, -1,
-                                        "Cluster allocation offset "
+                qcow2_signal_corruption(bs, true, -1, -1, "Data cluster offset "
                                         "%#" PRIx64 " unaligned (L2 offset: %#"
                                         PRIx64 ", L2 index: %#x)", offset,
                                         l2_offset, j);
-                if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) {
+                if (!preallocated) {
                     qcow2_free_clusters(bs, offset, s->cluster_size,
                                         QCOW2_DISCARD_ALWAYS);
                 }
@@ -1812,16 +1754,17 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
 
             ret = qcow2_pre_write_overlap_check(bs, 0, offset, s->cluster_size);
             if (ret < 0) {
-                if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) {
+                if (!preallocated) {
                     qcow2_free_clusters(bs, offset, s->cluster_size,
                                         QCOW2_DISCARD_ALWAYS);
                 }
                 goto fail;
             }
 
-            ret = bdrv_pwrite_zeroes(bs->file, offset, s->cluster_size, 0);
+            ret = bdrv_write_zeroes(bs->file->bs, offset / BDRV_SECTOR_SIZE,
+                                    s->cluster_sectors, 0);
             if (ret < 0) {
-                if (cluster_type == QCOW2_CLUSTER_ZERO_PLAIN) {
+                if (!preallocated) {
                     qcow2_free_clusters(bs, offset, s->cluster_size,
                                         QCOW2_DISCARD_ALWAYS);
                 }
@@ -1851,7 +1794,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
                     goto fail;
                 }
 
-                ret = bdrv_write(bs->file, l2_offset / BDRV_SECTOR_SIZE,
+                ret = bdrv_write(bs->file->bs, l2_offset / BDRV_SECTOR_SIZE,
                                  (void *)l2_table, s->cluster_sectors);
                 if (ret < 0) {
                     goto fail;
@@ -1861,7 +1804,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
 
         (*visited_l1_entries)++;
         if (status_cb) {
-            status_cb(bs, *visited_l1_entries, l1_entries, cb_opaque);
+            status_cb(bs, *visited_l1_entries, l1_entries);
         }
     }
 
@@ -1885,8 +1828,7 @@ fail:
  * qcow2 version which doesn't yet support metadata zero clusters.
  */
 int qcow2_expand_zero_clusters(BlockDriverState *bs,
-                               BlockDriverAmendStatusCB *status_cb,
-                               void *cb_opaque)
+                               BlockDriverAmendStatusCB *status_cb)
 {
     BDRVQcow2State *s = bs->opaque;
     uint64_t *l1_table = NULL;
@@ -1903,7 +1845,7 @@ int qcow2_expand_zero_clusters(BlockDriverState *bs,
 
     ret = expand_zero_clusters_in_l1(bs, s->l1_table, s->l1_size,
                                      &visited_l1_entries, l1_entries,
-                                     status_cb, cb_opaque);
+                                     status_cb);
     if (ret < 0) {
         goto fail;
     }
@@ -1921,12 +1863,12 @@ int qcow2_expand_zero_clusters(BlockDriverState *bs,
     }
 
     for (i = 0; i < s->nb_snapshots; i++) {
-        int l1_sectors = DIV_ROUND_UP(s->snapshots[i].l1_size *
-                                      sizeof(uint64_t), BDRV_SECTOR_SIZE);
+        int l1_sectors = (s->snapshots[i].l1_size * sizeof(uint64_t) +
+                BDRV_SECTOR_SIZE - 1) / BDRV_SECTOR_SIZE;
 
         l1_table = g_realloc(l1_table, l1_sectors * BDRV_SECTOR_SIZE);
 
-        ret = bdrv_read(bs->file,
+        ret = bdrv_read(bs->file->bs,
                         s->snapshots[i].l1_table_offset / BDRV_SECTOR_SIZE,
                         (void *)l1_table, l1_sectors);
         if (ret < 0) {
@@ -1939,7 +1881,7 @@ int qcow2_expand_zero_clusters(BlockDriverState *bs,
 
         ret = expand_zero_clusters_in_l1(bs, l1_table, s->snapshots[i].l1_size,
                                          &visited_l1_entries, l1_entries,
-                                         status_cb, cb_opaque);
+                                         status_cb);
         if (ret < 0) {
             goto fail;
         }

block/qcow2-refcount.c

@@ -22,13 +22,10 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
-#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "block/qcow2.h"
 #include "qemu/range.h"
-#include "qemu/bswap.h"
 
 static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size);
 static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
@@ -83,16 +80,6 @@ static Qcow2SetRefcountFunc *const set_refcount_funcs[] = {
 /*********************************************************/
 /* refcount handling */
 
-static void update_max_refcount_table_index(BDRVQcow2State *s)
-{
-    unsigned i = s->refcount_table_size - 1;
-    while (i > 0 && (s->refcount_table[i] & REFT_OFFSET_MASK) == 0) {
-        i--;
-    }
-    /* Set s->max_refcount_table_index to the index of the last used entry */
-    s->max_refcount_table_index = i;
-}
-
 int qcow2_refcount_init(BlockDriverState *bs)
 {
     BDRVQcow2State *s = bs->opaque;
@@ -114,14 +101,13 @@ int qcow2_refcount_init(BlockDriverState *bs)
             goto fail;
         }
         BLKDBG_EVENT(bs->file, BLKDBG_REFTABLE_LOAD);
-        ret = bdrv_pread(bs->file, s->refcount_table_offset,
+        ret = bdrv_pread(bs->file->bs, s->refcount_table_offset,
                          s->refcount_table, refcount_table_size2);
         if (ret < 0) {
             goto fail;
         }
         for(i = 0; i < s->refcount_table_size; i++)
             be64_to_cpus(&s->refcount_table[i]);
-        update_max_refcount_table_index(s);
     }
     return 0;
  fail:
@@ -229,10 +215,13 @@ static int load_refcount_block(BlockDriverState *bs,
                                void **refcount_block)
 {
     BDRVQcow2State *s = bs->opaque;
+    int ret;
 
     BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_LOAD);
-    return qcow2_cache_get(bs, s->refcount_block_cache, refcount_block_offset,
-                           refcount_block);
+    ret = qcow2_cache_get(bs, s->refcount_block_cache, refcount_block_offset,
+        refcount_block);
+
+    return ret;
 }
 
 /*
@@ -442,7 +431,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
     if (refcount_table_index < s->refcount_table_size) {
         uint64_t data64 = cpu_to_be64(new_block);
         BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_HOOKUP);
-        ret = bdrv_pwrite_sync(bs->file,
+        ret = bdrv_pwrite_sync(bs->file->bs,
             s->refcount_table_offset + refcount_table_index * sizeof(uint64_t),
             &data64, sizeof(data64));
         if (ret < 0) {
@@ -450,10 +439,6 @@ static int alloc_refcount_block(BlockDriverState *bs,
         }
 
         s->refcount_table[refcount_table_index] = new_block;
-        /* If there's a hole in s->refcount_table then it can happen
-         * that refcount_table_index < s->max_refcount_table_index */
-        s->max_refcount_table_index =
-            MAX(s->max_refcount_table_index, refcount_table_index);
 
         /* The new refcount block may be where the caller intended to put its
          * data, so let it restart the search. */
@@ -502,12 +487,14 @@ static int alloc_refcount_block(BlockDriverState *bs,
         uint64_t table_clusters =
             size_to_clusters(s, table_size * sizeof(uint64_t));
         blocks_clusters = 1 +
-            DIV_ROUND_UP(table_clusters, s->refcount_block_size);
+            ((table_clusters + s->refcount_block_size - 1)
+            / s->refcount_block_size);
         uint64_t meta_clusters = table_clusters + blocks_clusters;
 
         last_table_size = table_size;
         table_size = next_refcount_table_size(s, blocks_used +
-            DIV_ROUND_UP(meta_clusters, s->refcount_block_size));
+            ((meta_clusters + s->refcount_block_size - 1)
+            / s->refcount_block_size));
 
     } while (last_table_size != table_size);
 
@@ -548,7 +535,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
 
     /* Write refcount blocks to disk */
     BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE_BLOCKS);
-    ret = bdrv_pwrite_sync(bs->file, meta_offset, new_blocks,
+    ret = bdrv_pwrite_sync(bs->file->bs, meta_offset, new_blocks,
         blocks_clusters * s->cluster_size);
     g_free(new_blocks);
     new_blocks = NULL;
@@ -562,7 +549,7 @@ static int alloc_refcount_block(BlockDriverState *bs,
     }
 
     BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_WRITE_TABLE);
-    ret = bdrv_pwrite_sync(bs->file, table_offset, new_table,
+    ret = bdrv_pwrite_sync(bs->file->bs, table_offset, new_table,
         table_size * sizeof(uint64_t));
     if (ret < 0) {
         goto fail_table;
@@ -577,10 +564,10 @@ static int alloc_refcount_block(BlockDriverState *bs,
         uint64_t d64;
         uint32_t d32;
     } data;
-    data.d64 = cpu_to_be64(table_offset);
-    data.d32 = cpu_to_be32(table_clusters);
+    cpu_to_be64w(&data.d64, table_offset);
+    cpu_to_be32w(&data.d32, table_clusters);
     BLKDBG_EVENT(bs->file, BLKDBG_REFBLOCK_ALLOC_SWITCH_TABLE);
-    ret = bdrv_pwrite_sync(bs->file,
+    ret = bdrv_pwrite_sync(bs->file->bs,
                            offsetof(QCowHeader, refcount_table_offset),
                            &data, sizeof(data));
     if (ret < 0) {
@@ -595,7 +582,6 @@ static int alloc_refcount_block(BlockDriverState *bs,
     s->refcount_table = new_table;
     s->refcount_table_size = table_size;
     s->refcount_table_offset = table_offset;
-    update_max_refcount_table_index(s);
 
     /* Free old table. */
     qcow2_free_clusters(bs, old_table_offset, old_table_size * sizeof(uint64_t),
@@ -631,7 +617,9 @@ void qcow2_process_discards(BlockDriverState *bs, int ret)
 
         /* Discard is optional, ignore the return value */
         if (ret >= 0) {
-            bdrv_pdiscard(bs->file->bs, d->offset, d->bytes);
+            bdrv_discard(bs->file->bs,
+                         d->offset >> BDRV_SECTOR_BITS,
+                         d->bytes >> BDRV_SECTOR_BITS);
         }
 
         g_free(d);
@@ -1028,17 +1016,18 @@ void qcow2_free_any_clusters(BlockDriverState *bs, uint64_t l2_entry,
         }
         break;
     case QCOW2_CLUSTER_NORMAL:
-    case QCOW2_CLUSTER_ZERO_ALLOC:
-        if (offset_into_cluster(s, l2_entry & L2E_OFFSET_MASK)) {
-            qcow2_signal_corruption(bs, false, -1, -1,
-                                    "Cannot free unaligned cluster %#llx",
-                                    l2_entry & L2E_OFFSET_MASK);
-        } else {
-            qcow2_free_clusters(bs, l2_entry & L2E_OFFSET_MASK,
-                                nb_clusters << s->cluster_bits, type);
+    case QCOW2_CLUSTER_ZERO:
+        if (l2_entry & L2E_OFFSET_MASK) {
+            if (offset_into_cluster(s, l2_entry & L2E_OFFSET_MASK)) {
+                qcow2_signal_corruption(bs, false, -1, -1,
+                                        "Cannot free unaligned cluster %#llx",
+                                        l2_entry & L2E_OFFSET_MASK);
+            } else {
+                qcow2_free_clusters(bs, l2_entry & L2E_OFFSET_MASK,
+                                    nb_clusters << s->cluster_bits, type);
+            }
         }
         break;
-    case QCOW2_CLUSTER_ZERO_PLAIN:
     case QCOW2_CLUSTER_UNALLOCATED:
         break;
     default:
@@ -1058,9 +1047,9 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
     int64_t l1_table_offset, int l1_size, int addend)
 {
     BDRVQcow2State *s = bs->opaque;
-    uint64_t *l1_table, *l2_table, l2_offset, entry, l1_size2, refcount;
+    uint64_t *l1_table, *l2_table, l2_offset, offset, l1_size2, refcount;
     bool l1_allocated = false;
-    int64_t old_entry, old_l2_offset;
+    int64_t old_offset, old_l2_offset;
     int i, j, l1_modified = 0, nb_csectors;
     int ret;
 
@@ -1083,21 +1072,20 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
         }
         l1_allocated = true;
 
-        ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2);
+        ret = bdrv_pread(bs->file->bs, l1_table_offset, l1_table, l1_size2);
         if (ret < 0) {
             goto fail;
         }
 
-        for (i = 0; i < l1_size; i++) {
+        for(i = 0;i < l1_size; i++)
             be64_to_cpus(&l1_table[i]);
-        }
     } else {
         assert(l1_size == s->l1_size);
         l1_table = s->l1_table;
         l1_allocated = false;
     }
 
-    for (i = 0; i < l1_size; i++) {
+    for(i = 0; i < l1_size; i++) {
         l2_offset = l1_table[i];
         if (l2_offset) {
             old_l2_offset = l2_offset;
@@ -1117,79 +1105,81 @@ int qcow2_update_snapshot_refcount(BlockDriverState *bs,
                 goto fail;
             }
 
-            for (j = 0; j < s->l2_size; j++) {
+            for(j = 0; j < s->l2_size; j++) {
                 uint64_t cluster_index;
-                uint64_t offset;
 
-                entry = be64_to_cpu(l2_table[j]);
-                old_entry = entry;
-                entry &= ~QCOW_OFLAG_COPIED;
-                offset = entry & L2E_OFFSET_MASK;
+                offset = be64_to_cpu(l2_table[j]);
+                old_offset = offset;
+                offset &= ~QCOW_OFLAG_COPIED;
 
-                switch (qcow2_get_cluster_type(entry)) {
-                case QCOW2_CLUSTER_COMPRESSED:
-                    nb_csectors = ((entry >> s->csize_shift) &
-                                   s->csize_mask) + 1;
-                    if (addend != 0) {
-                        ret = update_refcount(bs,
-                                (entry & s->cluster_offset_mask) & ~511,
+                switch (qcow2_get_cluster_type(offset)) {
+                    case QCOW2_CLUSTER_COMPRESSED:
+                        nb_csectors = ((offset >> s->csize_shift) &
+                                       s->csize_mask) + 1;
+                        if (addend != 0) {
+                            ret = update_refcount(bs,
+                                (offset & s->cluster_offset_mask) & ~511,
                                 nb_csectors * 512, abs(addend), addend < 0,
                                 QCOW2_DISCARD_SNAPSHOT);
-                        if (ret < 0) {
+                            if (ret < 0) {
+                                goto fail;
+                            }
+                        }
+                        /* compressed clusters are never modified */
+                        refcount = 2;
+                        break;
+
+                    case QCOW2_CLUSTER_NORMAL:
+                    case QCOW2_CLUSTER_ZERO:
+                        if (offset_into_cluster(s, offset & L2E_OFFSET_MASK)) {
+                            qcow2_signal_corruption(bs, true, -1, -1, "Data "
+                                                    "cluster offset %#llx "
+                                                    "unaligned (L2 offset: %#"
+                                                    PRIx64 ", L2 index: %#x)",
+                                                    offset & L2E_OFFSET_MASK,
+                                                    l2_offset, j);
+                            ret = -EIO;
                             goto fail;
                         }
-                    }
-                    /* compressed clusters are never modified */
-                    refcount = 2;
-                    break;
 
-                case QCOW2_CLUSTER_NORMAL:
-                case QCOW2_CLUSTER_ZERO_ALLOC:
-                    if (offset_into_cluster(s, offset)) {
-                        qcow2_signal_corruption(bs, true, -1, -1, "Cluster "
-                                                "allocation offset %#" PRIx64
-                                                " unaligned (L2 offset: %#"
-                                                PRIx64 ", L2 index: %#x)",
-                                                offset, l2_offset, j);
-                        ret = -EIO;
-                        goto fail;
-                    }
-
-                    cluster_index = offset >> s->cluster_bits;
-                    assert(cluster_index);
-                    if (addend != 0) {
-                        ret = qcow2_update_cluster_refcount(bs,
+                        cluster_index = (offset & L2E_OFFSET_MASK) >> s->cluster_bits;
+                        if (!cluster_index) {
+                            /* unallocated */
+                            refcount = 0;
+                            break;
+                        }
+                        if (addend != 0) {
+                            ret = qcow2_update_cluster_refcount(bs,
                                     cluster_index, abs(addend), addend < 0,
                                     QCOW2_DISCARD_SNAPSHOT);
+                            if (ret < 0) {
+                                goto fail;
+                            }
+                        }
+
+                        ret = qcow2_get_refcount(bs, cluster_index, &refcount);
                         if (ret < 0) {
                             goto fail;
                         }
-                    }
+                        break;
 
-                    ret = qcow2_get_refcount(bs, cluster_index, &refcount);
-                    if (ret < 0) {
-                        goto fail;
-                    }
-                    break;
+                    case QCOW2_CLUSTER_UNALLOCATED:
+                        refcount = 0;
+                        break;
 
-                case QCOW2_CLUSTER_ZERO_PLAIN:
-                case QCOW2_CLUSTER_UNALLOCATED:
-                    refcount = 0;
-                    break;
-
-                default:
-                    abort();
+                    default:
+                        abort();
                 }
 
                 if (refcount == 1) {
-                    entry |= QCOW_OFLAG_COPIED;
+                    offset |= QCOW_OFLAG_COPIED;
                 }
-                if (entry != old_entry) {
+                if (offset != old_offset) {
                     if (addend > 0) {
                         qcow2_cache_set_dependency(bs, s->l2_table_cache,
                             s->refcount_block_cache);
                     }
-                    l2_table[j] = cpu_to_be64(entry);
+                    l2_table[j] = cpu_to_be64(offset);
                     qcow2_cache_entry_mark_dirty(bs, s->l2_table_cache,
                                                  l2_table);
                 }
@@ -1235,7 +1225,7 @@ fail:
             cpu_to_be64s(&l1_table[i]);
         }
 
-        ret = bdrv_pwrite_sync(bs->file, l1_table_offset,
+        ret = bdrv_pwrite_sync(bs->file->bs, l1_table_offset,
                                l1_table, l1_size2);
 
         for (i = 0; i < l1_size; i++) {
@@ -1355,9 +1345,6 @@ static int inc_refcounts(BlockDriverState *bs,
         if (refcount == s->refcount_max) {
             fprintf(stderr, "ERROR: overflow cluster offset=0x%" PRIx64
                     "\n", cluster_offset);
-            fprintf(stderr, "Use qemu-img amend to increase the refcount entry "
-                    "width or qemu-img convert to create a clean copy if the "
-                    "image cannot be opened for writing\n");
             res->corruptions++;
             continue;
         }
@@ -1394,7 +1381,7 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
     l2_size = s->l2_size * sizeof(uint64_t);
     l2_table = g_malloc(l2_size);
 
-    ret = bdrv_pread(bs->file, l2_offset, l2_table, l2_size);
+    ret = bdrv_pread(bs->file->bs, l2_offset, l2_table, l2_size);
     if (ret < 0) {
         fprintf(stderr, "ERROR: I/O error in check_refcounts_l2\n");
         res->check_errors++;
@@ -1439,7 +1426,12 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
             }
             break;
 
-        case QCOW2_CLUSTER_ZERO_ALLOC:
+        case QCOW2_CLUSTER_ZERO:
+            if ((l2_entry & L2E_OFFSET_MASK) == 0) {
+                break;
+            }
+            /* fall through */
+
         case QCOW2_CLUSTER_NORMAL:
         {
             uint64_t offset = l2_entry & L2E_OFFSET_MASK;
@@ -1469,7 +1461,6 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
             break;
         }
 
-        case QCOW2_CLUSTER_ZERO_PLAIN:
         case QCOW2_CLUSTER_UNALLOCATED:
             break;
 
@@ -1522,7 +1513,7 @@ static int check_refcounts_l1(BlockDriverState *bs,
             res->check_errors++;
             goto fail;
         }
-        ret = bdrv_pread(bs->file, l1_table_offset, l1_table, l1_size2);
+        ret = bdrv_pread(bs->file->bs, l1_table_offset, l1_table, l1_size2);
         if (ret < 0) {
             fprintf(stderr, "ERROR: I/O error in check_refcounts_l1\n");
             res->check_errors++;
@@ -1620,7 +1611,7 @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res,
             }
         }
 
-        ret = bdrv_pread(bs->file, l2_offset, l2_table,
+        ret = bdrv_pread(bs->file->bs, l2_offset, l2_table,
                          s->l2_size * sizeof(uint64_t));
         if (ret < 0) {
             fprintf(stderr, "ERROR: Could not read L2 table: %s\n",
@@ -1632,10 +1623,10 @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res,
         for (j = 0; j < s->l2_size; j++) {
             uint64_t l2_entry = be64_to_cpu(l2_table[j]);
             uint64_t data_offset = l2_entry & L2E_OFFSET_MASK;
-            QCow2ClusterType cluster_type = qcow2_get_cluster_type(l2_entry);
+            int cluster_type = qcow2_get_cluster_type(l2_entry);
 
-            if (cluster_type == QCOW2_CLUSTER_NORMAL ||
-                cluster_type == QCOW2_CLUSTER_ZERO_ALLOC) {
+            if ((cluster_type == QCOW2_CLUSTER_NORMAL) ||
+                ((cluster_type == QCOW2_CLUSTER_ZERO) && (data_offset != 0))) {
                 ret = qcow2_get_refcount(bs,
                                          data_offset >> s->cluster_bits,
                                          &refcount);
@@ -1672,7 +1663,7 @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res,
                 goto fail;
             }
 
-            ret = bdrv_pwrite(bs->file, l2_offset, l2_table,
+            ret = bdrv_pwrite(bs->file->bs, l2_offset, l2_table,
                               s->cluster_size);
             if (ret < 0) {
                 fprintf(stderr, "ERROR: Could not write L2 table: %s\n",
@@ -1722,17 +1713,14 @@ static int check_refblocks(BlockDriverState *bs, BdrvCheckResult *res,
 
             if (fix & BDRV_FIX_ERRORS) {
                 int64_t new_nb_clusters;
-                Error *local_err = NULL;
 
                 if (offset > INT64_MAX - s->cluster_size) {
                     ret = -EINVAL;
                     goto resize_fail;
                 }
 
-                ret = bdrv_truncate(bs->file, offset + s->cluster_size,
-                                    &local_err);
+                ret = bdrv_truncate(bs->file->bs, offset + s->cluster_size);
                 if (ret < 0) {
-                    error_report_err(local_err);
                     goto resize_fail;
                 }
                 size = bdrv_getlength(bs->file->bs);
@@ -2109,7 +2097,7 @@ write_refblocks:
         on_disk_refblock = (void *)((char *) *refcount_table +
                                     refblock_index * s->cluster_size);
 
-        ret = bdrv_write(bs->file, refblock_offset / BDRV_SECTOR_SIZE,
+        ret = bdrv_write(bs->file->bs, refblock_offset / BDRV_SECTOR_SIZE,
                          on_disk_refblock, s->cluster_sectors);
         if (ret < 0) {
             fprintf(stderr, "ERROR writing refblock: %s\n", strerror(-ret));
@@ -2158,7 +2146,7 @@ write_refblocks:
     }
 
     assert(reftable_size < INT_MAX / sizeof(uint64_t));
-    ret = bdrv_pwrite(bs->file, reftable_offset, on_disk_reftable,
+    ret = bdrv_pwrite(bs->file->bs, reftable_offset, on_disk_reftable,
                       reftable_size * sizeof(uint64_t));
     if (ret < 0) {
         fprintf(stderr, "ERROR writing reftable: %s\n", strerror(-ret));
@@ -2166,11 +2154,12 @@ write_refblocks:
     }
 
     /* Enter new reftable into the image header */
-    reftable_offset_and_clusters.reftable_offset = cpu_to_be64(reftable_offset);
-    reftable_offset_and_clusters.reftable_clusters =
-        cpu_to_be32(size_to_clusters(s, reftable_size * sizeof(uint64_t)));
-    ret = bdrv_pwrite_sync(bs->file,
-                           offsetof(QCowHeader, refcount_table_offset),
+    cpu_to_be64w(&reftable_offset_and_clusters.reftable_offset,
+                 reftable_offset);
+    cpu_to_be32w(&reftable_offset_and_clusters.reftable_clusters,
+                 size_to_clusters(s, reftable_size * sizeof(uint64_t)));
+    ret = bdrv_pwrite_sync(bs->file->bs, offsetof(QCowHeader,
+                                                  refcount_table_offset),
                            &reftable_offset_and_clusters,
                            sizeof(reftable_offset_and_clusters));
     if (ret < 0) {
@@ -2184,7 +2173,6 @@ write_refblocks:
     s->refcount_table = on_disk_reftable;
     s->refcount_table_offset = reftable_offset;
     s->refcount_table_size = reftable_size;
-    update_max_refcount_table_index(s);
 
     return 0;
 
@@ -2397,11 +2385,7 @@ int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset,
     }
 
     if ((chk & QCOW2_OL_REFCOUNT_BLOCK) && s->refcount_table) {
-        unsigned last_entry = s->max_refcount_table_index;
-        assert(last_entry < s->refcount_table_size);
-        assert(last_entry + 1 == s->refcount_table_size ||
-               (s->refcount_table[last_entry + 1] & REFT_OFFSET_MASK) == 0);
-        for (i = 0; i <= last_entry; i++) {
+        for (i = 0; i < s->refcount_table_size; i++) {
             if ((s->refcount_table[i] & REFT_OFFSET_MASK) &&
                 overlaps_with(s->refcount_table[i] & REFT_OFFSET_MASK,
                 s->cluster_size)) {
@@ -2422,7 +2406,7 @@ int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset,
                 return -ENOMEM;
             }
 
-            ret = bdrv_pread(bs->file, l1_ofs, l1, l1_sz2);
+            ret = bdrv_pread(bs->file->bs, l1_ofs, l1, l1_sz2);
             if (ret < 0) {
                 g_free(l1);
                 return ret;
@@ -2483,451 +2467,3 @@ int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
 
     return 0;
 }
-
-/* A pointer to a function of this type is given to walk_over_reftable(). That
- * function will create refblocks and pass them to a RefblockFinishOp once they
- * are completed (@refblock). @refblock_empty is set if the refblock is
- * completely empty.
- *
- * Along with the refblock, a corresponding reftable entry is passed, in the
- * reftable @reftable (which may be reallocated) at @reftable_index.
- *
- * @allocated should be set to true if a new cluster has been allocated.
- */
-typedef int (RefblockFinishOp)(BlockDriverState *bs, uint64_t **reftable,
-                               uint64_t reftable_index, uint64_t *reftable_size,
-                               void *refblock, bool refblock_empty,
-                               bool *allocated, Error **errp);
-
-/**
- * This "operation" for walk_over_reftable() allocates the refblock on disk (if
- * it is not empty) and inserts its offset into the new reftable. The size of
- * this new reftable is increased as required.
- */
-static int alloc_refblock(BlockDriverState *bs, uint64_t **reftable,
-                          uint64_t reftable_index, uint64_t *reftable_size,
-                          void *refblock, bool refblock_empty, bool *allocated,
-                          Error **errp)
-{
-    BDRVQcow2State *s = bs->opaque;
-    int64_t offset;
-
-    if (!refblock_empty && reftable_index >= *reftable_size) {
-        uint64_t *new_reftable;
-        uint64_t new_reftable_size;
-
-        new_reftable_size = ROUND_UP(reftable_index + 1,
-                                     s->cluster_size / sizeof(uint64_t));
-        if (new_reftable_size > QCOW_MAX_REFTABLE_SIZE / sizeof(uint64_t)) {
-            error_setg(errp,
-                       "This operation would make the refcount table grow "
-                       "beyond the maximum size supported by QEMU, aborting");
-            return -ENOTSUP;
-        }
-
-        new_reftable = g_try_realloc(*reftable, new_reftable_size *
-                                                sizeof(uint64_t));
-        if (!new_reftable) {
-            error_setg(errp, "Failed to increase reftable buffer size");
-            return -ENOMEM;
-        }
-
-        memset(new_reftable + *reftable_size, 0,
-               (new_reftable_size - *reftable_size) * sizeof(uint64_t));
-
-        *reftable      = new_reftable;
-        *reftable_size = new_reftable_size;
-    }
-
-    if (!refblock_empty && !(*reftable)[reftable_index]) {
-        offset = qcow2_alloc_clusters(bs, s->cluster_size);
-        if (offset < 0) {
-            error_setg_errno(errp, -offset, "Failed to allocate refblock");
-            return offset;
-        }
-        (*reftable)[reftable_index] = offset;
-        *allocated = true;
-    }
-
-    return 0;
-}
-
-/**
- * This "operation" for walk_over_reftable() writes the refblock to disk at the
- * offset specified by the new reftable's entry. It does not modify the new
- * reftable or change any refcounts.
- */
-static int flush_refblock(BlockDriverState *bs, uint64_t **reftable,
-                          uint64_t reftable_index, uint64_t *reftable_size,
-                          void *refblock, bool refblock_empty, bool *allocated,
-                          Error **errp)
-{
-    BDRVQcow2State *s = bs->opaque;
-    int64_t offset;
-    int ret;
-
-    if (reftable_index < *reftable_size && (*reftable)[reftable_index]) {
-        offset = (*reftable)[reftable_index];
-
-        ret = qcow2_pre_write_overlap_check(bs, 0, offset, s->cluster_size);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret, "Overlap check failed");
-            return ret;
-        }
-
-        ret = bdrv_pwrite(bs->file, offset, refblock, s->cluster_size);
-        if (ret < 0) {
-            error_setg_errno(errp, -ret, "Failed to write refblock");
-            return ret;
-        }
-    } else {
-        assert(refblock_empty);
-    }
-
-    return 0;
-}
-
-/**
- * This function walks over the existing reftable and every referenced refblock;
- * if @new_set_refcount is non-NULL, it is called for every refcount entry to
- * create an equal new entry in the passed @new_refblock. Once that
- * @new_refblock is completely filled, @operation will be called.
- *
- * @status_cb and @cb_opaque are used for the amend operation's status callback.
- * @index is the index of the walk_over_reftable() calls and @total is the total
- * number of walk_over_reftable() calls per amend operation. Both are used for
- * calculating the parameters for the status callback.
- *
- * @allocated is set to true if a new cluster has been allocated.
- */
-static int walk_over_reftable(BlockDriverState *bs, uint64_t **new_reftable,
-                              uint64_t *new_reftable_index,
-                              uint64_t *new_reftable_size,
-                              void *new_refblock, int new_refblock_size,
-                              int new_refcount_bits,
-                              RefblockFinishOp *operation, bool *allocated,
-                              Qcow2SetRefcountFunc *new_set_refcount,
-                              BlockDriverAmendStatusCB *status_cb,
-                              void *cb_opaque, int index, int total,
-                              Error **errp)
-{
-    BDRVQcow2State *s = bs->opaque;
-    uint64_t reftable_index;
-    bool new_refblock_empty = true;
-    int refblock_index;
-    int new_refblock_index = 0;
-    int ret;
-
-    for (reftable_index = 0; reftable_index < s->refcount_table_size;
-         reftable_index++)
-    {
-        uint64_t refblock_offset = s->refcount_table[reftable_index]
-                                 & REFT_OFFSET_MASK;
-
-        status_cb(bs, (uint64_t)index * s->refcount_table_size + reftable_index,
-                  (uint64_t)total * s->refcount_table_size, cb_opaque);
-
-        if (refblock_offset) {
-            void *refblock;
-
-            if (offset_into_cluster(s, refblock_offset)) {
-                qcow2_signal_corruption(bs, true, -1, -1, "Refblock offset %#"
-                                        PRIx64 " unaligned (reftable index: %#"
-                                        PRIx64 ")", refblock_offset,
-                                        reftable_index);
-                error_setg(errp,
-                           "Image is corrupt (unaligned refblock offset)");
-                return -EIO;
-            }
-
-            ret = qcow2_cache_get(bs, s->refcount_block_cache, refblock_offset,
-                                  &refblock);
-            if (ret < 0) {
-                error_setg_errno(errp, -ret, "Failed to retrieve refblock");
-                return ret;
-            }
-
-            for (refblock_index = 0; refblock_index < s->refcount_block_size;
-                 refblock_index++)
-            {
-                uint64_t refcount;
-
-                if (new_refblock_index >= new_refblock_size) {
-                    /* new_refblock is now complete */
-                    ret = operation(bs, new_reftable, *new_reftable_index,
-                                    new_reftable_size, new_refblock,
-                                    new_refblock_empty, allocated, errp);
-                    if (ret < 0) {
-                        qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
-                        return ret;
-                    }
-
-                    (*new_reftable_index)++;
-                    new_refblock_index = 0;
-                    new_refblock_empty = true;
-                }
-
-                refcount = s->get_refcount(refblock, refblock_index);
-                if (new_refcount_bits < 64 && refcount >> new_refcount_bits) {
-                    uint64_t offset;
-
-                    qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
-
-                    offset = ((reftable_index << s->refcount_block_bits)
-                              + refblock_index) << s->cluster_bits;
-
-                    error_setg(errp, "Cannot decrease refcount entry width to "
-                               "%i bits: Cluster at offset %#" PRIx64 " has a "
-                               "refcount of %" PRIu64, new_refcount_bits,
-                               offset, refcount);
-                    return -EINVAL;
-                }
-
-                if (new_set_refcount) {
-                    new_set_refcount(new_refblock, new_refblock_index++,
-                                     refcount);
-                } else {
-                    new_refblock_index++;
-                }
-                new_refblock_empty = new_refblock_empty && refcount == 0;
-            }
-
-            qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
-        } else {
-            /* No refblock means every refcount is 0 */
-            for (refblock_index = 0; refblock_index < s->refcount_block_size;
-                 refblock_index++)
-            {
-                if (new_refblock_index >= new_refblock_size) {
-                    /* new_refblock is now complete */
-                    ret = operation(bs, new_reftable, *new_reftable_index,
-                                    new_reftable_size, new_refblock,
-                                    new_refblock_empty, allocated, errp);
-                    if (ret < 0) {
-                        return ret;
-                    }
-
-                    (*new_reftable_index)++;
-                    new_refblock_index = 0;
-                    new_refblock_empty = true;
-                }
-
-                if (new_set_refcount) {
-                    new_set_refcount(new_refblock, new_refblock_index++, 0);
-                } else {
-                    new_refblock_index++;
-                }
-            }
-        }
-    }
-
-    if (new_refblock_index > 0) {
-        /* Complete the potentially existing partially filled final refblock */
-        if (new_set_refcount) {
-            for (; new_refblock_index < new_refblock_size;
-                 new_refblock_index++)
-            {
-                new_set_refcount(new_refblock, new_refblock_index, 0);
-            }
-        }
-
-        ret = operation(bs, new_reftable, *new_reftable_index,
-                        new_reftable_size, new_refblock, new_refblock_empty,
-                        allocated, errp);
-        if (ret < 0) {
-            return ret;
-        }
-
-        (*new_reftable_index)++;
-    }
-
-    status_cb(bs, (uint64_t)(index + 1) * s->refcount_table_size,
-              (uint64_t)total * s->refcount_table_size, cb_opaque);
-
-    return 0;
-}
-
-int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order,
-                                BlockDriverAmendStatusCB *status_cb,
-                                void *cb_opaque, Error **errp)
-{
-    BDRVQcow2State *s = bs->opaque;
-    Qcow2GetRefcountFunc *new_get_refcount;
-    Qcow2SetRefcountFunc *new_set_refcount;
-    void *new_refblock = qemu_blockalign(bs->file->bs, s->cluster_size);
-    uint64_t *new_reftable = NULL, new_reftable_size = 0;
-    uint64_t *old_reftable, old_reftable_size, old_reftable_offset;
-    uint64_t new_reftable_index = 0;
-    uint64_t i;
-    int64_t new_reftable_offset = 0, allocated_reftable_size = 0;
-    int new_refblock_size, new_refcount_bits = 1 << refcount_order;
-    int old_refcount_order;
-    int walk_index = 0;
-    int ret;
-    bool new_allocation;
-
-    assert(s->qcow_version >= 3);
-    assert(refcount_order >= 0 && refcount_order <= 6);
-
-    /* see qcow2_open() */
-    new_refblock_size = 1 << (s->cluster_bits - (refcount_order - 3));
-
-    new_get_refcount = get_refcount_funcs[refcount_order];
-    new_set_refcount = set_refcount_funcs[refcount_order];
-
-
-    do {
-        int total_walks;
-
-        new_allocation = false;
-
-        /* At least we have to do this walk and the one which writes the
-         * refblocks; also, at least we have to do this loop here at least
-         * twice (normally), first to do the allocations, and second to
-         * determine that everything is correctly allocated, this then makes
-         * three walks in total */
-        total_walks = MAX(walk_index + 2, 3);
-
-        /* First, allocate the structures so they are present in the refcount
-         * structures */
-        ret = walk_over_reftable(bs, &new_reftable, &new_reftable_index,
-                                 &new_reftable_size, NULL, new_refblock_size,
-                                 new_refcount_bits, &alloc_refblock,
-                                 &new_allocation, NULL, status_cb, cb_opaque,
-                                 walk_index++, total_walks, errp);
-        if (ret < 0) {
-            goto done;
-        }
-
-        new_reftable_index = 0;
-
-        if (new_allocation) {
-            if (new_reftable_offset) {
-                qcow2_free_clusters(bs, new_reftable_offset,
-                                    allocated_reftable_size * sizeof(uint64_t),
-                                    QCOW2_DISCARD_NEVER);
-            }
-
-            new_reftable_offset = qcow2_alloc_clusters(bs, new_reftable_size *
-                                                           sizeof(uint64_t));
-            if (new_reftable_offset < 0) {
-                error_setg_errno(errp, -new_reftable_offset,
-                                 "Failed to allocate the new reftable");
-                ret = new_reftable_offset;
-                goto done;
-            }
-            allocated_reftable_size = new_reftable_size;
-        }
-    } while (new_allocation);
-
-    /* Second, write the new refblocks */
-    ret = walk_over_reftable(bs, &new_reftable, &new_reftable_index,
-                             &new_reftable_size, new_refblock,
-                             new_refblock_size, new_refcount_bits,
-                             &flush_refblock, &new_allocation, new_set_refcount,
-                             status_cb, cb_opaque, walk_index, walk_index + 1,
-                             errp);
-    if (ret < 0) {
-        goto done;
-    }
-    assert(!new_allocation);
-
-
-    /* Write the new reftable */
-    ret = qcow2_pre_write_overlap_check(bs, 0, new_reftable_offset,
-                                        new_reftable_size * sizeof(uint64_t));
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Overlap check failed");
-        goto done;
-    }
-
-    for (i = 0; i < new_reftable_size; i++) {
-        cpu_to_be64s(&new_reftable[i]);
-    }
-
-    ret = bdrv_pwrite(bs->file, new_reftable_offset, new_reftable,
-                      new_reftable_size * sizeof(uint64_t));
-
-    for (i = 0; i < new_reftable_size; i++) {
-        be64_to_cpus(&new_reftable[i]);
-    }
-
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Failed to write the new reftable");
-        goto done;
-    }
-
-
-    /* Empty the refcount cache */
-    ret = qcow2_cache_flush(bs, s->refcount_block_cache);
-    if (ret < 0) {
-        error_setg_errno(errp, -ret, "Failed to flush the refblock cache");
-        goto done;
-    }
-
-    /* Update the image header to point to the new reftable; this only updates
-     * the fields which are relevant to qcow2_update_header(); other fields
-     * such as s->refcount_table or s->refcount_bits stay stale for now
-     * (because we have to restore everything if qcow2_update_header() fails) */
-    old_refcount_order  = s->refcount_order;
-    old_reftable_size   = s->refcount_table_size;
-    old_reftable_offset = s->refcount_table_offset;
-
-    s->refcount_order        = refcount_order;
-    s->refcount_table_size   = new_reftable_size;
-    s->refcount_table_offset = new_reftable_offset;
-
-    ret = qcow2_update_header(bs);
-    if (ret < 0) {
-        s->refcount_order        = old_refcount_order;
-        s->refcount_table_size   = old_reftable_size;
-        s->refcount_table_offset = old_reftable_offset;
-        error_setg_errno(errp, -ret, "Failed to update the qcow2 header");
-        goto done;
-    }
-
-    /* Now update the rest of the in-memory information */
-    old_reftable = s->refcount_table;
-    s->refcount_table = new_reftable;
-    update_max_refcount_table_index(s);
-
-    s->refcount_bits = 1 << refcount_order;
-    s->refcount_max = UINT64_C(1) << (s->refcount_bits - 1);
-    s->refcount_max += s->refcount_max - 1;
-
-    s->refcount_block_bits = s->cluster_bits - (refcount_order - 3);
-    s->refcount_block_size = 1 << s->refcount_block_bits;
-
-    s->get_refcount = new_get_refcount;
-    s->set_refcount = new_set_refcount;
-
-    /* For cleaning up all old refblocks and the old reftable below the "done"
-     * label */
-    new_reftable        = old_reftable;
-    new_reftable_size   = old_reftable_size;
-    new_reftable_offset = old_reftable_offset;
-
-done:
-    if (new_reftable) {
-        /* On success, new_reftable actually points to the old reftable (and
-         * new_reftable_size is the old reftable's size); but that is just
-         * fine */
-        for (i = 0; i < new_reftable_size; i++) {
-            uint64_t offset = new_reftable[i] & REFT_OFFSET_MASK;
-            if (offset) {
-                qcow2_free_clusters(bs, offset, s->cluster_size,
-                                    QCOW2_DISCARD_OTHER);
-            }
-        }
-        g_free(new_reftable);
-
-        if (new_reftable_offset > 0) {
-            qcow2_free_clusters(bs, new_reftable_offset,
-                                new_reftable_size * sizeof(uint64_t),
-                                QCOW2_DISCARD_OTHER);
-        }
-    }
-
-    qemu_vfree(new_refblock);
-    return ret;
-}

block/qcow2-snapshot.c

@@ -22,13 +22,10 @@
  * THE SOFTWARE.
  */
 
-#include "qemu/osdep.h"
-#include "qapi/error.h"
+#include "qemu-common.h"
 #include "block/block_int.h"
 #include "block/qcow2.h"
-#include "qemu/bswap.h"
 #include "qemu/error-report.h"
-#include "qemu/cutils.h"
 
 void qcow2_free_snapshots(BlockDriverState *bs)
 {
@@ -67,7 +64,7 @@ int qcow2_read_snapshots(BlockDriverState *bs)
     for(i = 0; i < s->nb_snapshots; i++) {
         /* Read statically sized part of the snapshot header */
         offset = align_offset(offset, 8);
-        ret = bdrv_pread(bs->file, offset, &h, sizeof(h));
+        ret = bdrv_pread(bs->file->bs, offset, &h, sizeof(h));
         if (ret < 0) {
             goto fail;
         }
@@ -86,7 +83,7 @@ int qcow2_read_snapshots(BlockDriverState *bs)
         name_size = be16_to_cpu(h.name_size);
 
         /* Read extra data */
-        ret = bdrv_pread(bs->file, offset, &extra,
+        ret = bdrv_pread(bs->file->bs, offset, &extra,
                          MIN(sizeof(extra), extra_data_size));
         if (ret < 0) {
             goto fail;
@@ -105,7 +102,7 @@ int qcow2_read_snapshots(BlockDriverState *bs)
 
         /* Read snapshot ID */
         sn->id_str = g_malloc(id_str_size + 1);
-        ret = bdrv_pread(bs->file, offset, sn->id_str, id_str_size);
+        ret = bdrv_pread(bs->file->bs, offset, sn->id_str, id_str_size);
         if (ret < 0) {
             goto fail;
         }
@@ -114,7 +111,7 @@ int qcow2_read_snapshots(BlockDriverState *bs)
 
         /* Read snapshot name */
         sn->name = g_malloc(name_size + 1);
-        ret = bdrv_pread(bs->file, offset, sn->name, name_size);
+        ret = bdrv_pread(bs->file->bs, offset, sn->name, name_size);
         if (ret < 0) {
             goto fail;
         }
@@ -217,25 +214,25 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
         h.name_size = cpu_to_be16(name_size);
         offset = align_offset(offset, 8);
 
-        ret = bdrv_pwrite(bs->file, offset, &h, sizeof(h));
+        ret = bdrv_pwrite(bs->file->bs, offset, &h, sizeof(h));
         if (ret < 0) {
             goto fail;
         }
         offset += sizeof(h);
 
-        ret = bdrv_pwrite(bs->file, offset, &extra, sizeof(extra));
+        ret = bdrv_pwrite(bs->file->bs, offset, &extra, sizeof(extra));
         if (ret < 0) {
             goto fail;
         }
         offset += sizeof(extra);
 
-        ret = bdrv_pwrite(bs->file, offset, sn->id_str, id_str_size);
+        ret = bdrv_pwrite(bs->file->bs, offset, sn->id_str, id_str_size);
         if (ret < 0) {
             goto fail;
         }
         offset += id_str_size;
 
-        ret = bdrv_pwrite(bs->file, offset, sn->name, name_size);
+        ret = bdrv_pwrite(bs->file->bs, offset, sn->name, name_size);
         if (ret < 0) {
             goto fail;
         }
@@ -257,7 +254,7 @@ static int qcow2_write_snapshots(BlockDriverState *bs)
     header_data.nb_snapshots        = cpu_to_be32(s->nb_snapshots);
     header_data.snapshots_offset    = cpu_to_be64(snapshots_offset);
 
-    ret = bdrv_pwrite_sync(bs->file, offsetof(QCowHeader, nb_snapshots),
+    ret = bdrv_pwrite_sync(bs->file->bs, offsetof(QCowHeader, nb_snapshots),
                            &header_data, sizeof(header_data));
     if (ret < 0) {
         goto fail;
@@ -399,7 +396,7 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
         goto fail;
     }
 
-    ret = bdrv_pwrite(bs->file, sn->l1_table_offset, l1_table,
+    ret = bdrv_pwrite(bs->file->bs, sn->l1_table_offset, l1_table,
                       s->l1_size * sizeof(uint64_t));
     if (ret < 0) {
         goto fail;
@@ -440,9 +437,10 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
 
     /* The VM state isn't needed any more in the active L1 table; in fact, it
      * hurts by causing expensive COW for the next snapshot. */
-    qcow2_cluster_discard(bs, qcow2_vm_state_offset(s),
-                          align_offset(sn->vm_state_size, s->cluster_size),
-                          QCOW2_DISCARD_NEVER, false);
+    qcow2_discard_clusters(bs, qcow2_vm_state_offset(s),
+                           align_offset(sn->vm_state_size, s->cluster_size)
+                                >> BDRV_SECTOR_BITS,
+                           QCOW2_DISCARD_NEVER, false);
 
 #ifdef DEBUG_ALLOC
     {
@@ -511,7 +509,7 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
         goto fail;
     }
 
-    ret = bdrv_pread(bs->file, sn->l1_table_offset,
+    ret = bdrv_pread(bs->file->bs, sn->l1_table_offset,
                      sn_l1_table, sn_l1_bytes);
     if (ret < 0) {
         goto fail;
@@ -529,7 +527,7 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
         goto fail;
     }
 
-    ret = bdrv_pwrite_sync(bs->file, s->l1_table_offset, sn_l1_table,
+    ret = bdrv_pwrite_sync(bs->file->bs, s->l1_table_offset, sn_l1_table,
                            cur_l1_bytes);
     if (ret < 0) {
         goto fail;
@@ -715,7 +713,7 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs,
         return -ENOMEM;
     }
 
-    ret = bdrv_pread(bs->file, sn->l1_table_offset,
+    ret = bdrv_pread(bs->file->bs, sn->l1_table_offset,
                      new_l1_table, new_l1_bytes);
     if (ret < 0) {
         error_setg(errp, "Failed to read l1 table for snapshot");

block/qcow2.h

@@ -251,7 +251,6 @@ typedef struct BDRVQcow2State {
     uint64_t *refcount_table;
     uint64_t refcount_table_offset;
     uint32_t refcount_table_size;
-    uint32_t max_refcount_table_index; /* Last used entry in refcount_table */
     uint64_t free_cluster_index;
     uint64_t free_byte_offset;
 
@@ -303,8 +302,8 @@ typedef struct Qcow2COWRegion {
      */
     uint64_t    offset;
 
-    /** Number of bytes to copy */
-    int         nb_bytes;
+    /** Number of sectors to copy */
+    int         nb_sectors;
 } Qcow2COWRegion;
 
 /**
@@ -319,12 +318,15 @@ typedef struct QCowL2Meta
     /** Host offset of the first newly allocated cluster */
     uint64_t alloc_offset;
 
+    /**
+     * 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;
 
-    /** Do not free the old clusters */
-    bool keep_old_clusters;
-
     /**
      * Requests that overlap with this allocation and wait to be restarted
      * when the allocating request has completed.
@@ -349,13 +351,12 @@ typedef struct QCowL2Meta
     QLIST_ENTRY(QCowL2Meta) next_in_flight;
 } QCowL2Meta;
 
-typedef enum QCow2ClusterType {
+enum {
     QCOW2_CLUSTER_UNALLOCATED,
-    QCOW2_CLUSTER_ZERO_PLAIN,
-    QCOW2_CLUSTER_ZERO_ALLOC,
     QCOW2_CLUSTER_NORMAL,
     QCOW2_CLUSTER_COMPRESSED,
-} QCow2ClusterType;
+    QCOW2_CLUSTER_ZERO
+};
 
 typedef enum QCow2MetadataOverlap {
     QCOW2_OL_MAIN_HEADER_BITNR    = 0,
@@ -444,15 +445,12 @@ static inline uint64_t qcow2_max_refcount_clusters(BDRVQcow2State *s)
     return QCOW_MAX_REFTABLE_SIZE >> s->cluster_bits;
 }
 
-static inline QCow2ClusterType qcow2_get_cluster_type(uint64_t l2_entry)
+static inline int qcow2_get_cluster_type(uint64_t l2_entry)
 {
     if (l2_entry & QCOW_OFLAG_COMPRESSED) {
         return QCOW2_CLUSTER_COMPRESSED;
     } else if (l2_entry & QCOW_OFLAG_ZERO) {
-        if (l2_entry & L2E_OFFSET_MASK) {
-            return QCOW2_CLUSTER_ZERO_ALLOC;
-        }
-        return QCOW2_CLUSTER_ZERO_PLAIN;
+        return QCOW2_CLUSTER_ZERO;
     } else if (!(l2_entry & L2E_OFFSET_MASK)) {
         return QCOW2_CLUSTER_UNALLOCATED;
     } else {
@@ -473,7 +471,8 @@ static inline uint64_t l2meta_cow_start(QCowL2Meta *m)
 
 static inline uint64_t l2meta_cow_end(QCowL2Meta *m)
 {
-    return m->offset + m->cow_end.offset + m->cow_end.nb_bytes;
+    return m->offset + m->cow_end.offset
+        + (m->cow_end.nb_sectors << BDRV_SECTOR_BITS);
 }
 
 static inline uint64_t refcount_diff(uint64_t r1, uint64_t r2)
@@ -481,6 +480,8 @@ static inline uint64_t refcount_diff(uint64_t r1, uint64_t r2)
     return r1 > r2 ? r1 - r2 : r2 - r1;
 }
 
+// FIXME Need qcow2_ prefix to global functions
+
 /* qcow2.c functions */
 int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov,
                   int64_t sector_num, int nb_sectors);
@@ -528,38 +529,31 @@ int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset,
 int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
                                   int64_t size);
 
-int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order,
-                                BlockDriverAmendStatusCB *status_cb,
-                                void *cb_opaque, Error **errp);
-
 /* qcow2-cluster.c functions */
 int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
                         bool exact_size);
 int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index);
+void qcow2_l2_cache_reset(BlockDriverState *bs);
 int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset);
 int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num,
                           uint8_t *out_buf, const uint8_t *in_buf,
                           int nb_sectors, bool enc, Error **errp);
 
 int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
-                             unsigned int *bytes, uint64_t *cluster_offset);
+    int *num, uint64_t *cluster_offset);
 int qcow2_alloc_cluster_offset(BlockDriverState *bs, uint64_t offset,
-                               unsigned int *bytes, uint64_t *host_offset,
-                               QCowL2Meta **m);
+    int *num, uint64_t *host_offset, QCowL2Meta **m);
 uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
                                          uint64_t offset,
                                          int compressed_size);
 
 int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m);
-int qcow2_cluster_discard(BlockDriverState *bs, uint64_t offset,
-                          uint64_t bytes, enum qcow2_discard_type type,
-                          bool full_discard);
-int qcow2_cluster_zeroize(BlockDriverState *bs, uint64_t offset,
-                          uint64_t bytes, int flags);
+int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
+    int nb_sectors, enum qcow2_discard_type type, bool full_discard);
+int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors);
 
 int qcow2_expand_zero_clusters(BlockDriverState *bs,
-                               BlockDriverAmendStatusCB *status_cb,
-                               void *cb_opaque);
+                               BlockDriverAmendStatusCB *status_cb);
 
 /* qcow2-snapshot.c functions */
 int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info);
@@ -584,7 +578,6 @@ int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c);
 void qcow2_cache_entry_mark_dirty(BlockDriverState *bs, Qcow2Cache *c,
      void *table);
 int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c);
-int qcow2_cache_write(BlockDriverState *bs, Qcow2Cache *c);
 int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c,
     Qcow2Cache *dependency);
 void qcow2_cache_depends_on_flush(Qcow2Cache *c);