include/block/block_int: Document protocol related functions

Clarify that:

- for protocols the brdv_file_open function is used instead
of bdrv_open;

- when protocol_name is set, a driver should expect
to be given only a filename and no other options.

Signed-off-by: Fabiano Rosas <farosas@linux.vnet.ibm.com>

.gitignore

@@ -36,7 +36,6 @@
 /qapi/qapi-commands-common.[ch]
 /qapi/qapi-commands-crypto.[ch]
 /qapi/qapi-commands-introspect.[ch]
-/qapi/qapi-commands-job.[ch]
 /qapi/qapi-commands-migration.[ch]
 /qapi/qapi-commands-misc.[ch]
 /qapi/qapi-commands-net.[ch]
@@ -54,7 +53,6 @@
 /qapi/qapi-events-common.[ch]
 /qapi/qapi-events-crypto.[ch]
 /qapi/qapi-events-introspect.[ch]
-/qapi/qapi-events-job.[ch]
 /qapi/qapi-events-migration.[ch]
 /qapi/qapi-events-misc.[ch]
 /qapi/qapi-events-net.[ch]
@@ -73,7 +71,6 @@
 /qapi/qapi-types-common.[ch]
 /qapi/qapi-types-crypto.[ch]
 /qapi/qapi-types-introspect.[ch]
-/qapi/qapi-types-job.[ch]
 /qapi/qapi-types-migration.[ch]
 /qapi/qapi-types-misc.[ch]
 /qapi/qapi-types-net.[ch]
@@ -91,7 +88,6 @@
 /qapi/qapi-visit-common.[ch]
 /qapi/qapi-visit-crypto.[ch]
 /qapi/qapi-visit-introspect.[ch]
-/qapi/qapi-visit-job.[ch]
 /qapi/qapi-visit-migration.[ch]
 /qapi/qapi-visit-misc.[ch]
 /qapi/qapi-visit-net.[ch]
@@ -155,7 +151,6 @@
 .sdk
 *.gcda
 *.gcno
-*.gcov
 /pc-bios/bios-pq/status
 /pc-bios/vgabios-pq/status
 /pc-bios/optionrom/linuxboot.asm
@@ -211,4 +206,3 @@ trace-dtrace-root.h
 trace-dtrace-root.dtrace
 trace-ust-all.h
 trace-ust-all.c
-/target/arm/decode-sve.inc.c

.gitmodules

@@ -1,3 +1,6 @@
+[submodule "roms/vgabios"]
+	path = roms/vgabios
+	url = git://git.qemu-project.org/vgabios.git/
 [submodule "roms/seabios"]
 	path = roms/seabios
 	url = git://git.qemu-project.org/seabios.git/
@@ -15,7 +18,7 @@
 	url = git://git.qemu-project.org/openhackware.git
 [submodule "roms/qemu-palcode"]
 	path = roms/qemu-palcode
-	url = git://git.qemu.org/qemu-palcode.git
+	url = git://github.com/rth7680/qemu-palcode.git
 [submodule "roms/sgabios"]
 	path = roms/sgabios
 	url = git://git.qemu-project.org/sgabios.git
@@ -42,4 +45,4 @@
 	url = git://github.com/hdeller/seabios-hppa.git
 [submodule "roms/u-boot-sam460ex"]
 	path = roms/u-boot-sam460ex
-	url = git://git.qemu.org/u-boot-sam460ex.git
+	url = git://github.com/zbalaton/u-boot-sam460ex

.mailmap

@@ -1,7 +1,6 @@
-# This mailmap fixes up author names/addresses.
-
-# The first section translates weird addresses from the original git import
-# into proper addresses so that they are counted properly by git shortlog.
+# This mailmap just translates the weird addresses from the original import into git
+# into proper addresses so that they are counted properly in git shortlog output.
+#
 Andrzej Zaborowski <balrogg@gmail.com> balrog <balrog@c046a42c-6fe2-441c-8c8c-71466251a162>
 Anthony Liguori <anthony@codemonkey.ws> aliguori <aliguori@c046a42c-6fe2-441c-8c8c-71466251a162>
 Anthony Liguori <anthony@codemonkey.ws> Anthony Liguori <aliguori@us.ibm.com>
@@ -16,19 +15,10 @@ Paul Burton <paul.burton@mips.com> <paul.burton@imgtec.com>
 Paul Burton <paul.burton@mips.com> <paul@archlinuxmips.org>
 Thiemo Seufer <ths@networkno.de> ths <ths@c046a42c-6fe2-441c-8c8c-71466251a162>
 malc <av1474@comtv.ru> malc <malc@c046a42c-6fe2-441c-8c8c-71466251a162>
-
 # There is also a:
 #    (no author) <(no author)@c046a42c-6fe2-441c-8c8c-71466251a162>
 # for the cvs2svn initialization commit e63c3dc74bf.
-
-# Next, translate a few commits where mailman rewrote the From: line due
-# to strict SPF, although we prefer to avoid adding more entries like that.
-Ed Swierk <eswierk@skyportsystems.com> Ed Swierk via Qemu-devel <qemu-devel@nongnu.org>
-Ian McKellar <ianloic@google.com> Ian McKellar via Qemu-devel <qemu-devel@nongnu.org>
-Julia Suvorova <jusual@mail.ru> Julia Suvorova via Qemu-devel <qemu-devel@nongnu.org>
-Justin Terry (VM) <juterry@microsoft.com> Justin Terry (VM) via Qemu-devel <qemu-devel@nongnu.org>
-
-
+#
 # Also list preferred name forms where people have changed their
 # git author config
 Daniel P. Berrangé <berrange@redhat.com>

.shippable.yml

@@ -35,5 +35,13 @@ build:
     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

@@ -1,8 +1,4 @@
-# The current Travis default is a container based 14.04 Trust on EC2
-# Additional builds with specific requirements for a full VM need to
-# be added as additional matrix: entries later on
 sudo: false
-dist: trusty
 language: c
 python:
   - "2.6"
@@ -38,7 +34,6 @@ addons:
       - libvte-2.90-dev
       - sparse
       - uuid-dev
-      - gcovr
 
 # The channel name "irc.oftc.net#qemu" is encrypted against qemu/qemu
 # to prevent IRC notifications from forks. This was created using:
@@ -51,15 +46,12 @@ notifications:
     on_failure: always
 env:
   global:
-    - SRC_DIR="."
-    - BUILD_DIR="."
     - TEST_CMD="make check"
     - MAKEFLAGS="-j3"
   matrix:
-    - CONFIG="--disable-system"
-    - CONFIG="--disable-user"
-    - CONFIG="--enable-debug --enable-debug-tcg"
-    - CONFIG="--disable-linux-aio --disable-cap-ng --disable-attr --disable-brlapi --disable-uuid --disable-libusb --disable-user"
+    - 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 --disable-linux-user"
     - CONFIG="--with-coroutine=ucontext --disable-linux-user"
     - CONFIG="--with-coroutine=sigaltstack --disable-linux-user"
@@ -69,39 +61,31 @@ git:
 before_install:
   - if [ "$TRAVIS_OS_NAME" == "osx" ]; then brew update ; fi
   - if [ "$TRAVIS_OS_NAME" == "osx" ]; then brew install libffi gettext glib pixman ; fi
-  - git submodule update --init --recursive capstone dtc ui/keycodemapdb
+  - wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
+  - git submodule update --init --recursive
 before_script:
-  - mkdir -p ${BUILD_DIR} && cd ${BUILD_DIR}
-  - ${SRC_DIR}/configure ${CONFIG} || { cat config.log && exit 1; }
+  - ./configure ${CONFIG}
 script:
   - make ${MAKEFLAGS} && ${TEST_CMD}
 matrix:
   include:
-    # Test out-of-tree builds
-    - env: CONFIG="--enable-debug --enable-debug-tcg"
-           BUILD_DIR="out-of-tree/build/dir" SRC_DIR="../../.."
-    # Test with Clang for compile portability (Travis uses clang-5.0)
-    - env: CONFIG="--disable-system"
-      compiler: clang
-    - env: CONFIG="--disable-user"
+    # Test with CLang for compile portability
+    - env: CONFIG=""
       compiler: clang
     # gprof/gcov are GCC features
-    - env: CONFIG="--enable-gprof --enable-gcov --disable-pie --target-list=aarch64-softmmu,arm-softmmu,i386-softmmu,mips-softmmu,mips64-softmmu,ppc64-softmmu,riscv64-softmmu,s390x-softmmu,x86_64-softmmu"
-      after_success:
-        - ${SRC_DIR}/scripts/travis/coverage-summary.sh
+    - env: CONFIG="--enable-gprof --enable-gcov --disable-pie"
       compiler: gcc
     # We manually include builds which we disable "make check" for
     - env: CONFIG="--enable-debug --enable-tcg-interpreter"
            TEST_CMD=""
       compiler: gcc
-    # We don't need to exercise every backend with every front-end
-    - env: CONFIG="--enable-trace-backends=log,simple,syslog --disable-system"
+    - env: CONFIG="--enable-trace-backends=simple"
            TEST_CMD=""
       compiler: gcc
-    - env: CONFIG="--enable-trace-backends=ftrace --target-list=x86_64-softmmu"
+    - env: CONFIG="--enable-trace-backends=ftrace"
            TEST_CMD=""
       compiler: gcc
-    - env: CONFIG="--enable-trace-backends=ust --target-list=x86_64-softmmu"
+    - env: CONFIG="--enable-trace-backends=ust"
            TEST_CMD=""
       compiler: gcc
     - env: CONFIG="--disable-tcg"
@@ -110,24 +94,80 @@ matrix:
     - env: CONFIG=""
       os: osx
       compiler: clang
-    # Python builds
-    - env: CONFIG="--target-list=x86_64-softmmu"
+    # Plain Trusty System Build
+    - env: CONFIG="--disable-linux-user"
+      sudo: required
+      addons:
+      dist: trusty
+      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
+      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 & python 3.0
+    - sudo: required
+      addons:
+      dist: trusty
+      language: generic
+      compiler: none
       python:
         - "3.0"
-    - env: CONFIG="--target-list=x86_64-softmmu"
+      env:
+        - COMPILER_NAME=clang CXX=clang++-3.9 CC=clang-3.9
+        - CONFIG="--disable-linux-user --cc=clang-3.9 --cxx=clang++-3.9 --python=/usr/bin/python3"
+      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 & python 3.6
+    - sudo: required
+      addons:
+      dist: trusty
+      language: generic
+      compiler: none
       python:
         - "3.6"
+      env:
+        - COMPILER_NAME=clang CXX=clang++-3.9 CC=clang-3.9
+        - CONFIG="--disable-system --cc=clang-3.9 --cxx=clang++-3.9 --python=/usr/bin/python3"
+      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:
-          update: true
           sources:
             # PPAs for newer toolchains
             - ubuntu-toolchain-r-test
           packages:
             # Extra toolchains
-            - gcc-7
-            - g++-7
+            - gcc-5
+            - g++-5
             # Build dependencies
             - libaio-dev
             - libattr1-dev
@@ -156,16 +196,8 @@ matrix:
       language: generic
       compiler: none
       env:
-        - COMPILER_NAME=gcc CXX=g++-7 CC=gcc-7
-        - CONFIG="--cc=gcc-7 --cxx=g++-7 --disable-pie --disable-linux-user"
+        - 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 && exit 1; }
-    - env:
-        - CONFIG="--disable-system --disable-docs"
-        - TEST_CMD="make check-tcg"
-      script:
-        - make ${MAKEFLAGS} && ${TEST_CMD} ${MAKEFLAGS}
-      sudo: required
-      dist: trusty
-      compiler: gcc
+        - ./configure ${CONFIG} --extra-cflags="-g3 -O0 -fsanitize=thread -fuse-ld=gold" || cat config.log

CODING_STYLE

@@ -124,23 +124,6 @@ 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.
 
-Multiline comment blocks should have a row of stars on the left,
-and the initial /* and terminating */ both on their own lines:
-    /*
-     * like
-     * this
-     */
-This is the same format required by the Linux kernel coding style.
-
-(Some of the existing comments in the codebase use the GNU Coding
-Standards form which does not have stars on the left, or other
-variations; avoid these when writing new comments, but don't worry
-about converting to the preferred form unless you're editing that
-comment anyway.)
-
-Rationale: Consistency, and ease of visually picking out a multiline
-comment from the surrounding code.
-
 8. trace-events style
 
 8.1 0x prefix

COPYING.PYTHON

@@ -0,0 +1,270 @@
+A. HISTORY OF THE SOFTWARE
+==========================
+
+Python was created in the early 1990s by Guido van Rossum at Stichting
+Mathematisch Centrum (CWI, see http://www.cwi.nl) in the Netherlands
+as a successor of a language called ABC.  Guido remains Python's
+principal author, although it includes many contributions from others.
+
+In 1995, Guido continued his work on Python at the Corporation for
+National Research Initiatives (CNRI, see http://www.cnri.reston.va.us)
+in Reston, Virginia where he released several versions of the
+software.
+
+In May 2000, Guido and the Python core development team moved to
+BeOpen.com to form the BeOpen PythonLabs team.  In October of the same
+year, the PythonLabs team moved to Digital Creations (now Zope
+Corporation, see http://www.zope.com).  In 2001, the Python Software
+Foundation (PSF, see http://www.python.org/psf/) was formed, a
+non-profit organization created specifically to own Python-related
+Intellectual Property.  Zope Corporation is a sponsoring member of
+the PSF.
+
+All Python releases are Open Source (see http://www.opensource.org for
+the Open Source Definition).  Historically, most, but not all, Python
+releases have also been GPL-compatible; the table below summarizes
+the various releases.
+
+    Release         Derived     Year        Owner       GPL-
+                    from                                compatible? (1)
+
+    0.9.0 thru 1.2              1991-1995   CWI         yes
+    1.3 thru 1.5.2  1.2         1995-1999   CNRI        yes
+    1.6             1.5.2       2000        CNRI        no
+    2.0             1.6         2000        BeOpen.com  no
+    1.6.1           1.6         2001        CNRI        yes (2)
+    2.1             2.0+1.6.1   2001        PSF         no
+    2.0.1           2.0+1.6.1   2001        PSF         yes
+    2.1.1           2.1+2.0.1   2001        PSF         yes
+    2.2             2.1.1       2001        PSF         yes
+    2.1.2           2.1.1       2002        PSF         yes
+    2.1.3           2.1.2       2002        PSF         yes
+    2.2.1           2.2         2002        PSF         yes
+    2.2.2           2.2.1       2002        PSF         yes
+    2.2.3           2.2.2       2003        PSF         yes
+    2.3             2.2.2       2002-2003   PSF         yes
+    2.3.1           2.3         2002-2003   PSF         yes
+    2.3.2           2.3.1       2002-2003   PSF         yes
+    2.3.3           2.3.2       2002-2003   PSF         yes
+    2.3.4           2.3.3       2004        PSF         yes
+    2.3.5           2.3.4       2005        PSF         yes
+    2.4             2.3         2004        PSF         yes
+    2.4.1           2.4         2005        PSF         yes
+    2.4.2           2.4.1       2005        PSF         yes
+    2.4.3           2.4.2       2006        PSF         yes
+    2.5             2.4         2006        PSF         yes
+    2.7             2.6         2010        PSF         yes
+
+Footnotes:
+
+(1) GPL-compatible doesn't mean that we're distributing Python under
+    the GPL.  All Python licenses, unlike the GPL, let you distribute
+    a modified version without making your changes open source.  The
+    GPL-compatible licenses make it possible to combine Python with
+    other software that is released under the GPL; the others don't.
+
+(2) According to Richard Stallman, 1.6.1 is not GPL-compatible,
+    because its license has a choice of law clause.  According to
+    CNRI, however, Stallman's lawyer has told CNRI's lawyer that 1.6.1
+    is "not incompatible" with the GPL.
+
+Thanks to the many outside volunteers who have worked under Guido's
+direction to make these releases possible.
+
+
+B. TERMS AND CONDITIONS FOR ACCESSING OR OTHERWISE USING PYTHON
+===============================================================
+
+PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2
+--------------------------------------------
+
+1. This LICENSE AGREEMENT is between the Python Software Foundation
+("PSF"), and the Individual or Organization ("Licensee") accessing and
+otherwise using this software ("Python") in source or binary form and
+its associated documentation.
+
+2. Subject to the terms and conditions of this License Agreement, PSF
+hereby grants Licensee a nonexclusive, royalty-free, world-wide
+license to reproduce, analyze, test, perform and/or display publicly,
+prepare derivative works, distribute, and otherwise use Python
+alone or in any derivative version, provided, however, that PSF's
+License Agreement and PSF's notice of copyright, i.e., "Copyright (c)
+2001, 2002, 2003, 2004, 2005, 2006 Python Software Foundation; All Rights
+Reserved" are retained in Python alone or in any derivative version 
+prepared by Licensee.
+
+3. In the event Licensee prepares a derivative work that is based on
+or incorporates Python or any part thereof, and wants to make
+the derivative work available to others as provided herein, then
+Licensee hereby agrees to include in any such work a brief summary of
+the changes made to Python.
+
+4. PSF is making Python available to Licensee on an "AS IS"
+basis.  PSF MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
+IMPLIED.  BY WAY OF EXAMPLE, BUT NOT LIMITATION, PSF MAKES NO AND
+DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
+FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON WILL NOT
+INFRINGE ANY THIRD PARTY RIGHTS.
+
+5. PSF SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON
+FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS
+A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON,
+OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
+
+6. This License Agreement will automatically terminate upon a material
+breach of its terms and conditions.
+
+7. Nothing in this License Agreement shall be deemed to create any
+relationship of agency, partnership, or joint venture between PSF and
+Licensee.  This License Agreement does not grant permission to use PSF
+trademarks or trade name in a trademark sense to endorse or promote
+products or services of Licensee, or any third party.
+
+8. By copying, installing or otherwise using Python, Licensee
+agrees to be bound by the terms and conditions of this License
+Agreement.
+
+
+BEOPEN.COM LICENSE AGREEMENT FOR PYTHON 2.0
+-------------------------------------------
+
+BEOPEN PYTHON OPEN SOURCE LICENSE AGREEMENT VERSION 1
+
+1. This LICENSE AGREEMENT is between BeOpen.com ("BeOpen"), having an
+office at 160 Saratoga Avenue, Santa Clara, CA 95051, and the
+Individual or Organization ("Licensee") accessing and otherwise using
+this software in source or binary form and its associated
+documentation ("the Software").
+
+2. Subject to the terms and conditions of this BeOpen Python License
+Agreement, BeOpen hereby grants Licensee a non-exclusive,
+royalty-free, world-wide license to reproduce, analyze, test, perform
+and/or display publicly, prepare derivative works, distribute, and
+otherwise use the Software alone or in any derivative version,
+provided, however, that the BeOpen Python License is retained in the
+Software, alone or in any derivative version prepared by Licensee.
+
+3. BeOpen is making the Software available to Licensee on an "AS IS"
+basis.  BEOPEN MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
+IMPLIED.  BY WAY OF EXAMPLE, BUT NOT LIMITATION, BEOPEN MAKES NO AND
+DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
+FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE SOFTWARE WILL NOT
+INFRINGE ANY THIRD PARTY RIGHTS.
+
+4. BEOPEN SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF THE
+SOFTWARE FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS
+AS A RESULT OF USING, MODIFYING OR DISTRIBUTING THE SOFTWARE, OR ANY
+DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
+
+5. This License Agreement will automatically terminate upon a material
+breach of its terms and conditions.
+
+6. This License Agreement shall be governed by and interpreted in all
+respects by the law of the State of California, excluding conflict of
+law provisions.  Nothing in this License Agreement shall be deemed to
+create any relationship of agency, partnership, or joint venture
+between BeOpen and Licensee.  This License Agreement does not grant
+permission to use BeOpen trademarks or trade names in a trademark
+sense to endorse or promote products or services of Licensee, or any
+third party.  As an exception, the "BeOpen Python" logos available at
+http://www.pythonlabs.com/logos.html may be used according to the
+permissions granted on that web page.
+
+7. By copying, installing or otherwise using the software, Licensee
+agrees to be bound by the terms and conditions of this License
+Agreement.
+
+
+CNRI LICENSE AGREEMENT FOR PYTHON 1.6.1
+---------------------------------------
+
+1. This LICENSE AGREEMENT is between the Corporation for National
+Research Initiatives, having an office at 1895 Preston White Drive,
+Reston, VA 20191 ("CNRI"), and the Individual or Organization
+("Licensee") accessing and otherwise using Python 1.6.1 software in
+source or binary form and its associated documentation.
+
+2. Subject to the terms and conditions of this License Agreement, CNRI
+hereby grants Licensee a nonexclusive, royalty-free, world-wide
+license to reproduce, analyze, test, perform and/or display publicly,
+prepare derivative works, distribute, and otherwise use Python 1.6.1
+alone or in any derivative version, provided, however, that CNRI's
+License Agreement and CNRI's notice of copyright, i.e., "Copyright (c)
+1995-2001 Corporation for National Research Initiatives; All Rights
+Reserved" are retained in Python 1.6.1 alone or in any derivative
+version prepared by Licensee.  Alternately, in lieu of CNRI's License
+Agreement, Licensee may substitute the following text (omitting the
+quotes): "Python 1.6.1 is made available subject to the terms and
+conditions in CNRI's License Agreement.  This Agreement together with
+Python 1.6.1 may be located on the Internet using the following
+unique, persistent identifier (known as a handle): 1895.22/1013.  This
+Agreement may also be obtained from a proxy server on the Internet
+using the following URL: http://hdl.handle.net/1895.22/1013".
+
+3. In the event Licensee prepares a derivative work that is based on
+or incorporates Python 1.6.1 or any part thereof, and wants to make
+the derivative work available to others as provided herein, then
+Licensee hereby agrees to include in any such work a brief summary of
+the changes made to Python 1.6.1.
+
+4. CNRI is making Python 1.6.1 available to Licensee on an "AS IS"
+basis.  CNRI MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
+IMPLIED.  BY WAY OF EXAMPLE, BUT NOT LIMITATION, CNRI MAKES NO AND
+DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
+FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON 1.6.1 WILL NOT
+INFRINGE ANY THIRD PARTY RIGHTS.
+
+5. CNRI SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON
+1.6.1 FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS
+A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON 1.6.1,
+OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
+
+6. This License Agreement will automatically terminate upon a material
+breach of its terms and conditions.
+
+7. This License Agreement shall be governed by the federal
+intellectual property law of the United States, including without
+limitation the federal copyright law, and, to the extent such
+U.S. federal law does not apply, by the law of the Commonwealth of
+Virginia, excluding Virginia's conflict of law provisions.
+Notwithstanding the foregoing, with regard to derivative works based
+on Python 1.6.1 that incorporate non-separable material that was
+previously distributed under the GNU General Public License (GPL), the
+law of the Commonwealth of Virginia shall govern this License
+Agreement only as to issues arising under or with respect to
+Paragraphs 4, 5, and 7 of this License Agreement.  Nothing in this
+License Agreement shall be deemed to create any relationship of
+agency, partnership, or joint venture between CNRI and Licensee.  This
+License Agreement does not grant permission to use CNRI trademarks or
+trade name in a trademark sense to endorse or promote products or
+services of Licensee, or any third party.
+
+8. By clicking on the "ACCEPT" button where indicated, or by copying,
+installing or otherwise using Python 1.6.1, Licensee agrees to be
+bound by the terms and conditions of this License Agreement.
+
+        ACCEPT
+
+
+CWI LICENSE AGREEMENT FOR PYTHON 0.9.0 THROUGH 1.2
+--------------------------------------------------
+
+Copyright (c) 1991 - 1995, Stichting Mathematisch Centrum Amsterdam,
+The Netherlands.  All rights reserved.
+
+Permission to use, copy, modify, and distribute this software and its
+documentation for any purpose and without fee is hereby granted,
+provided that the above copyright notice appear in all copies and that
+both that copyright notice and this permission notice appear in
+supporting documentation, and that the name of Stichting Mathematisch
+Centrum or CWI not be used in advertising or publicity pertaining to
+distribution of the software without specific, written prior
+permission.
+
+STICHTING MATHEMATISCH CENTRUM DISCLAIMS ALL WARRANTIES WITH REGARD TO
+THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
+FITNESS, IN NO EVENT SHALL STICHTING MATHEMATISCH CENTRUM BE LIABLE
+FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
+OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.

HACKING

@@ -118,15 +118,6 @@ Please note that g_malloc will exit on allocation failure, so there
 is no need to test for failure (as you would have to with malloc).
 Calling g_malloc with a zero size is valid and will return NULL.
 
-Prefer g_new(T, n) instead of g_malloc(sizeof(T) * n) for the following
-reasons:
-
-  a. It catches multiplication overflowing size_t;
-  b. It returns T * instead of void *, letting compiler catch more type
-     errors.
-
-Declarations like T *v = g_malloc(sizeof(*v)) are acceptable, though.
-
 Memory allocated by qemu_memalign or qemu_blockalign must be freed with
 qemu_vfree, since breaking this will cause problems on Win32.
 

MAINTAINERS

@@ -127,6 +127,7 @@ Alpha
 M: Richard Henderson <rth@twiddle.net>
 S: Maintained
 F: target/alpha/
+F: hw/alpha/
 F: tests/tcg/alpha/
 F: disas/alpha.c
 
@@ -135,8 +136,6 @@ M: Peter Maydell <peter.maydell@linaro.org>
 L: qemu-arm@nongnu.org
 S: Maintained
 F: target/arm/
-F: tests/tcg/arm/
-F: tests/tcg/aarch64/
 F: hw/arm/
 F: hw/cpu/a*mpcore.c
 F: include/hw/cpu/a*mpcore.h
@@ -187,7 +186,7 @@ F: disas/microblaze.c
 
 MIPS
 M: Aurelien Jarno <aurelien@aurel32.net>
-M: Aleksandar Markovic <aleksandar.markovic@mips.com>
+M: Yongbok Kim <yongbok.kim@mips.com>
 S: Maintained
 F: target/mips/
 F: hw/mips/
@@ -285,15 +284,13 @@ M: Richard Henderson <rth@twiddle.net>
 M: Eduardo Habkost <ehabkost@redhat.com>
 S: Maintained
 F: target/i386/
-F: tests/tcg/i386/
-F: tests/tcg/x86_64/
 F: hw/i386/
 F: disas/i386.c
 T: git git://github.com/ehabkost/qemu.git x86-next
 
 Xtensa
 M: Max Filippov <jcmvbkbc@gmail.com>
-W: http://wiki.osll.ru/doku.php?id=etc:users:jcmvbkbc:qemu-target-xtensa
+W: http://wiki.osll.spb.ru/doku.php?id=etc:users:jcmvbkbc:qemu-target-xtensa
 S: Maintained
 F: target/xtensa/
 F: hw/xtensa/
@@ -307,10 +304,6 @@ F: target/tricore/
 F: hw/tricore/
 F: include/hw/tricore/
 
-Multiarch Linux User Tests
-M: Alex Bennée <alex.bennee@linaro.org>
-F: tests/tcg/multiarch/
-
 Guest CPU Cores (KVM):
 ----------------------
 
@@ -420,12 +413,6 @@ F: include/*/*win32*
 X: qga/*win32*
 F: qemu.nsi
 
-Alpha Machines
-M: Richard Henderson <rth@twiddle.net>
-S: Maintained
-F: hw/alpha/
-F: hw/isa/smc37c669-superio.c
-
 ARM Machines
 ------------
 Allwinner-a10
@@ -455,10 +442,6 @@ F: hw/timer/cmsdk-apb-timer.c
 F: include/hw/timer/cmsdk-apb-timer.h
 F: hw/char/cmsdk-apb-uart.c
 F: include/hw/char/cmsdk-apb-uart.h
-F: hw/misc/tz-ppc.c
-F: include/hw/misc/tz-ppc.h
-F: hw/misc/tz-mpc.c
-F: include/hw/misc/tz-mpc.h
 
 ARM cores
 M: Peter Maydell <peter.maydell@linaro.org>
@@ -501,10 +484,9 @@ F: include/hw/arm/digic.h
 F: hw/*/digic*
 
 Gumstix
-M: Philippe Mathieu-Daudé <f4bug@amsat.org>
 L: qemu-devel@nongnu.org
 L: qemu-arm@nongnu.org
-S: Odd Fixes
+S: Orphan
 F: hw/arm/gumstix.c
 
 i.MX31
@@ -528,11 +510,8 @@ M: Peter Maydell <peter.maydell@linaro.org>
 L: qemu-arm@nongnu.org
 S: Maintained
 F: hw/arm/mps2.c
-F: hw/arm/mps2-tz.c
-F: hw/misc/mps2-*.c
-F: include/hw/misc/mps2-*.h
-F: hw/arm/iotkit.c
-F: include/hw/arm/iotkit.h
+F: hw/misc/mps2-scc.c
+F: include/hw/misc/mps2-scc.h
 
 Musicpal
 M: Jan Kiszka <jan.kiszka@web.de>
@@ -645,17 +624,6 @@ M: Subbaraya Sundeep <sundeep.lkml@gmail.com>
 S: Maintained
 F: hw/arm/msf2-som.c
 
-ASPEED BMCs
-M: Cédric Le Goater <clg@kaod.org>
-R: Andrew Jeffery <andrew@aj.id.au>
-R: Joel Stanley <joel@jms.id.au>
-L: qemu-arm@nongnu.org
-S: Maintained
-F: hw/*/*aspeed*
-F: include/hw/*/*aspeed*
-F: hw/net/ftgmac100.c
-F: include/hw/net/ftgmac100.h
-
 CRIS Machines
 -------------
 Axis Dev88
@@ -718,7 +686,7 @@ S: Maintained
 F: hw/mips/mips_malta.c
 
 Mipssim
-M: Aleksandar Markovic <aleksandar.markovic@mips.com>
+M: Yongbok Kim <yongbok.kim@mips.com>
 S: Odd Fixes
 F: hw/mips/mips_mipssim.c
 F: hw/net/mipsnet.c
@@ -729,11 +697,9 @@ S: Maintained
 F: hw/mips/mips_r4k.c
 
 Fulong 2E
-M: Aleksandar Markovic <aleksandar.markovic@mips.com>
+M: Yongbok Kim <yongbok.kim@mips.com>
 S: Odd Fixes
 F: hw/mips/mips_fulong2e.c
-F: hw/isa/vt82c686.c
-F: include/hw/isa/vt82c686.h
 
 Boston
 M: Paul Burton <paul.burton@mips.com>
@@ -788,11 +754,8 @@ F: hw/ppc/mac_newworld.c
 F: hw/pci-host/uninorth.c
 F: hw/pci-bridge/dec.[hc]
 F: hw/misc/macio/
-F: hw/misc/mos6522.c
-F: hw/nvram/mac_nvram.c
-F: include/hw/misc/macio/
-F: include/hw/misc/mos6522.h
 F: include/hw/ppc/mac_dbdma.h
+F: hw/nvram/mac_nvram.c
 
 Old World
 M: Alexander Graf <agraf@suse.de>
@@ -813,10 +776,9 @@ F: hw/ppc/prep_systemio.c
 F: hw/ppc/rs6000_mc.c
 F: hw/pci-host/prep.[hc]
 F: hw/isa/i82378.c
-F: hw/isa/pc87312.c
+F: hw/isa/pc87312.[hc]
 F: hw/dma/i82374.c
 F: hw/timer/m48t59-isa.c
-F: include/hw/isa/pc87312.h
 F: include/hw/timer/m48t59.h
 F: pc-bios/ppc_rom.bin
 
@@ -851,7 +813,6 @@ M: BALATON Zoltan <balaton@eik.bme.hu>
 L: qemu-ppc@nongnu.org
 S: Maintained
 F: hw/ide/sii3112.c
-F: hw/timer/m41t80.c
 
 SH4 Machines
 ------------
@@ -940,7 +901,7 @@ X86 Machines
 ------------
 PC
 M: Michael S. Tsirkin <mst@redhat.com>
-M: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
+M: Marcel Apfelbaum <marcel@redhat.com>
 S: Supported
 F: include/hw/i386/
 F: hw/i386/
@@ -963,7 +924,7 @@ M: Michael S. Tsirkin <mst@redhat.com>
 M: Paolo Bonzini <pbonzini@redhat.com>
 S: Supported
 F: hw/char/debugcon.c
-F: hw/char/parallel*
+F: hw/char/parallel.c
 F: hw/char/serial*
 F: hw/dma/i8257*
 F: hw/i2c/pm_smbus.c
@@ -971,7 +932,6 @@ F: hw/input/pckbd.c
 F: hw/intc/apic*
 F: hw/intc/ioapic*
 F: hw/intc/i8259*
-F: hw/isa/isa-superio.c
 F: hw/misc/debugexit.c
 F: hw/misc/pc-testdev.c
 F: hw/timer/hpet*
@@ -979,18 +939,15 @@ F: hw/timer/i8254*
 F: hw/timer/mc146818rtc*
 F: hw/watchdog/wdt_ib700.c
 F: include/hw/display/vga.h
-F: include/hw/char/parallel.h
-F: include/hw/dma/i8257.h
 F: include/hw/i2c/pm_smbus.h
-F: include/hw/input/i8042.h
-F: include/hw/isa/superio.h
+F: include/hw/isa/i8257.h
 F: include/hw/timer/hpet.h
 F: include/hw/timer/i8254*
 F: include/hw/timer/mc146818rtc*
 
 Machine core
 M: Eduardo Habkost <ehabkost@redhat.com>
-M: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
+M: Marcel Apfelbaum <marcel@redhat.com>
 S: Supported
 F: hw/core/machine.c
 F: hw/core/null-machine.c
@@ -1029,7 +986,6 @@ F: hw/block/cdrom.c
 F: hw/block/hd-geometry.c
 F: tests/ide-test.c
 F: tests/ahci-test.c
-F: tests/cdrom-test.c
 F: tests/libqos/ahci*
 T: git git://github.com/jnsnow/qemu.git ide
 
@@ -1065,7 +1021,7 @@ F: hw/ipack/
 
 PCI
 M: Michael S. Tsirkin <mst@redhat.com>
-M: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
+M: Marcel Apfelbaum <marcel@redhat.com>
 S: Supported
 F: include/hw/pci/*
 F: hw/misc/pci-testdev.c
@@ -1346,33 +1302,6 @@ S: Maintained
 F: include/hw/misc/unimp.h
 F: hw/misc/unimp.c
 
-Standard VGA
-M: Gerd Hoffmann <kraxel@redhat.com>
-S: Maintained
-F: hw/display/vga*
-F: hw/display/bochs-display.c
-F: include/hw/display/vga.h
-F: include/hw/display/bochs-vbe.h
-
-ramfb
-M: Gerd Hoffmann <kraxel@redhat.com>
-S: Maintained
-F: hw/display/ramfb*.c
-F: include/hw/display/ramfb.h
-
-virtio-gpu
-M: Gerd Hoffmann <kraxel@redhat.com>
-S: Maintained
-F: hw/display/virtio-gpu*
-F: hw/display/virtio-vga.c
-F: include/hw/virtio/virtio-gpu.h
-
-Cirrus VGA
-M: Gerd Hoffmann <kraxel@redhat.com>
-S: Odd Fixes
-W: https://www.kraxel.org/blog/2014/10/qemu-using-cirrus-considered-harmful/
-F: hw/display/cirrus*
-
 Subsystems
 ----------
 Audio
@@ -1398,8 +1327,6 @@ F: qemu-img*
 F: qemu-io*
 F: tests/qemu-iotests/
 F: util/qemu-progress.c
-F: qobject/block-qdict.c
-F: test/check-block-qdict.c
 T: git git://repo.or.cz/qemu/kevin.git block
 
 Block I/O path
@@ -1412,7 +1339,6 @@ F: util/aio-*.c
 F: block/io.c
 F: migration/block*
 F: include/block/aio.h
-F: include/block/aio-wait.h
 F: scripts/qemugdb/aio.py
 T: git git://github.com/stefanha/qemu.git block
 
@@ -1430,14 +1356,10 @@ L: qemu-block@nongnu.org
 S: Supported
 F: blockjob.c
 F: include/block/blockjob.h
-F: job.c
-F: job-qmp.c
-F: include/block/job.h
 F: block/backup.c
 F: block/commit.c
 F: block/stream.c
 F: block/mirror.c
-F: qapi/job.json
 T: git git://github.com/codyprime/qemu-kvm-jtc.git block
 
 Block QAPI, monitor, command line
@@ -1638,8 +1560,7 @@ F: tests/test-*-visitor.c
 F: tests/test-qapi-*.c
 F: tests/test-qmp-*.c
 F: tests/test-visitor-serialization.c
-F: scripts/qapi-gen.py
-F: scripts/qapi/*
+F: scripts/qapi*
 F: docs/devel/qapi*
 T: git git://repo.or.cz/qemu/armbru.git qapi-next
 
@@ -1711,7 +1632,6 @@ S: Maintained
 F: slirp/
 F: net/slirp.c
 F: include/net/slirp.h
-T: git https://people.debian.org/~sthibault/qemu.git slirp
 T: git git://git.kiszka.org/qemu.git queues/slirp
 
 Stubs
@@ -1723,8 +1643,6 @@ Tracing
 M: Stefan Hajnoczi <stefanha@redhat.com>
 S: Maintained
 F: trace/
-F: trace-events
-F: qemu-option-trace.texi
 F: scripts/tracetool.py
 F: scripts/tracetool/
 F: docs/devel/tracing.txt
@@ -1850,12 +1768,6 @@ F: include/sysemu/replay.h
 F: docs/replay.txt
 F: stubs/replay.c
 
-IOVA Tree
-M: Peter Xu <peterx@redhat.com>
-S: Maintained
-F: include/qemu/iova-tree.h
-F: util/iova-tree.c
-
 Usermode Emulation
 ------------------
 Overall
@@ -1996,7 +1908,6 @@ F: nbd/
 F: include/block/nbd*
 F: qemu-nbd.*
 F: blockdev-nbd.c
-F: docs/interop/nbd.txt
 T: git git://repo.or.cz/qemu/ericb.git nbd
 
 NFS
@@ -2052,12 +1963,6 @@ S: Supported
 F: block/quorum.c
 L: qemu-block@nongnu.org
 
-blklogwrites
-M: Ari Sundholm <ari@tuxera.com>
-L: qemu-block@nongnu.org
-S: Supported
-F: block/blklogwrites.c
-
 blkverify
 M: Stefan Hajnoczi <stefanha@redhat.com>
 L: qemu-block@nongnu.org
@@ -2157,7 +2062,7 @@ F: docs/block-replication.txt
 
 PVRDMA
 M: Yuval Shaia <yuval.shaia@oracle.com>
-M: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
+M: Marcel Apfelbaum <marcel@redhat.com>
 S: Maintained
 F: hw/rdma/*
 F: hw/rdma/vmw/*
@@ -2172,7 +2077,6 @@ R: Philippe Mathieu-Daudé <f4bug@amsat.org>
 L: qemu-devel@nongnu.org
 S: Maintained
 F: .travis.yml
-F: scripts/travis/
 F: .shippable.yml
 F: tests/docker/
 F: tests/vm/
@@ -2180,13 +2084,6 @@ W: https://travis-ci.org/qemu/qemu
 W: https://app.shippable.com/github/qemu/qemu
 W: http://patchew.org/QEMU/
 
-Guest Test Compilation Support
-M: Alex Bennée <alex.bennee@linaro.org>
-R: Philippe Mathieu-Daudé <f4bug@amsat.org>
-F: tests/tcg/Makefile
-F: tests/tcg/Makefile.include
-L: qemu-devel@nongnu.org
-
 Documentation
 -------------
 Build system architecture

Makefile

@@ -20,6 +20,8 @@ ifneq ($(wildcard config-host.mak),)
 all:
 include config-host.mak
 
+PYTHON_UTF8 = LC_ALL= LANG=C LC_CTYPE=en_US.UTF-8 $(PYTHON)
+
 git-submodule-update:
 
 .PHONY: git-submodule-update
@@ -96,7 +98,6 @@ GENERATED_FILES += qapi/qapi-types-char.h qapi/qapi-types-char.c
 GENERATED_FILES += qapi/qapi-types-common.h qapi/qapi-types-common.c
 GENERATED_FILES += qapi/qapi-types-crypto.h qapi/qapi-types-crypto.c
 GENERATED_FILES += qapi/qapi-types-introspect.h qapi/qapi-types-introspect.c
-GENERATED_FILES += qapi/qapi-types-job.h qapi/qapi-types-job.c
 GENERATED_FILES += qapi/qapi-types-migration.h qapi/qapi-types-migration.c
 GENERATED_FILES += qapi/qapi-types-misc.h qapi/qapi-types-misc.c
 GENERATED_FILES += qapi/qapi-types-net.h qapi/qapi-types-net.c
@@ -115,7 +116,6 @@ GENERATED_FILES += qapi/qapi-visit-char.h qapi/qapi-visit-char.c
 GENERATED_FILES += qapi/qapi-visit-common.h qapi/qapi-visit-common.c
 GENERATED_FILES += qapi/qapi-visit-crypto.h qapi/qapi-visit-crypto.c
 GENERATED_FILES += qapi/qapi-visit-introspect.h qapi/qapi-visit-introspect.c
-GENERATED_FILES += qapi/qapi-visit-job.h qapi/qapi-visit-job.c
 GENERATED_FILES += qapi/qapi-visit-migration.h qapi/qapi-visit-migration.c
 GENERATED_FILES += qapi/qapi-visit-misc.h qapi/qapi-visit-misc.c
 GENERATED_FILES += qapi/qapi-visit-net.h qapi/qapi-visit-net.c
@@ -133,7 +133,6 @@ GENERATED_FILES += qapi/qapi-commands-char.h qapi/qapi-commands-char.c
 GENERATED_FILES += qapi/qapi-commands-common.h qapi/qapi-commands-common.c
 GENERATED_FILES += qapi/qapi-commands-crypto.h qapi/qapi-commands-crypto.c
 GENERATED_FILES += qapi/qapi-commands-introspect.h qapi/qapi-commands-introspect.c
-GENERATED_FILES += qapi/qapi-commands-job.h qapi/qapi-commands-job.c
 GENERATED_FILES += qapi/qapi-commands-migration.h qapi/qapi-commands-migration.c
 GENERATED_FILES += qapi/qapi-commands-misc.h qapi/qapi-commands-misc.c
 GENERATED_FILES += qapi/qapi-commands-net.h qapi/qapi-commands-net.c
@@ -151,7 +150,6 @@ GENERATED_FILES += qapi/qapi-events-char.h qapi/qapi-events-char.c
 GENERATED_FILES += qapi/qapi-events-common.h qapi/qapi-events-common.c
 GENERATED_FILES += qapi/qapi-events-crypto.h qapi/qapi-events-crypto.c
 GENERATED_FILES += qapi/qapi-events-introspect.h qapi/qapi-events-introspect.c
-GENERATED_FILES += qapi/qapi-events-job.h qapi/qapi-events-job.c
 GENERATED_FILES += qapi/qapi-events-migration.h qapi/qapi-events-migration.c
 GENERATED_FILES += qapi/qapi-events-misc.h qapi/qapi-events-misc.c
 GENERATED_FILES += qapi/qapi-events-net.h qapi/qapi-events-net.c
@@ -320,7 +318,6 @@ KEYCODEMAP_FILES = \
 		 ui/input-keymap-xorgkbd-to-qcode.c \
 		 ui/input-keymap-xorgxquartz-to-qcode.c \
 		 ui/input-keymap-xorgxwin-to-qcode.c \
-		 ui/input-keymap-osx-to-qcode.c \
 		 $(NULL)
 
 GENERATED_FILES += $(KEYCODEMAP_FILES)
@@ -350,7 +347,7 @@ $(call set-vpath, $(SRC_PATH))
 
 LIBS+=-lz $(LIBS_TOOLS)
 
-HELPERS-$(call land,$(CONFIG_SOFTMMU),$(CONFIG_LINUX)) = qemu-bridge-helper$(EXESUF)
+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
@@ -441,23 +438,21 @@ 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 \
-			pkgvers="$(PKGVERSION)"; \
+			printf '"$(PKGVERSION)"\n'; \
 		else \
 			if test -d .git; then \
-				pkgvers=$$(git describe --match 'v*' 2>/dev/null | tr -d '\n');\
+				printf '" ('; \
+				git describe --match 'v*' 2>/dev/null | tr -d '\n'; \
 				if ! git diff-index --quiet HEAD &>/dev/null; then \
-					pkgvers="$${pkgvers}-dirty"; \
+					printf -- '-dirty'; \
 				fi; \
-			fi; \
-		fi; \
-		printf "#define QEMU_PKGVERSION \"$${pkgvers}\"\n"; \
-		if test -n "$${pkgvers}"; then \
-			printf '#define QEMU_FULL_VERSION QEMU_VERSION " (" QEMU_PKGVERSION ")"\n'; \
+				printf ')"\n'; \
 			else \
-			printf '#define QEMU_FULL_VERSION QEMU_VERSION\n'; \
+				printf '""\n'; \
 			fi; \
-		) > $@.tmp)
+		fi) > $@.tmp)
 	$(call quiet-command, if ! cmp -s $@ $@.tmp; then \
 	  mv $@.tmp $@; \
 	 else \
@@ -488,7 +483,7 @@ subdir-dtc: .git-submodule-status dtc/libfdt dtc/tests
 	$(call quiet-command,$(MAKE) $(DTC_MAKE_ARGS) CPPFLAGS="$(DTC_CPPFLAGS)" CFLAGS="$(DTC_CFLAGS)" LDFLAGS="$(LDFLAGS)" ARFLAGS="$(ARFLAGS)" CC="$(CC)" AR="$(AR)" LD="$(LD)" $(SUBDIR_MAKEFLAGS) libfdt/libfdt.a,)
 
 dtc/%: .git-submodule-status
-	@mkdir -p $@
+	mkdir -p $@
 
 # Overriding CFLAGS causes us to lose defines added in the sub-makefile.
 # Not overriding CFLAGS leads to mis-matches between compilation modes.
@@ -566,6 +561,7 @@ $(SRC_PATH)/scripts/qapi/types.py \
 $(SRC_PATH)/scripts/qapi/visit.py \
 $(SRC_PATH)/scripts/qapi/common.py \
 $(SRC_PATH)/scripts/qapi/doc.py \
+$(SRC_PATH)/scripts/ordereddict.py \
 $(SRC_PATH)/scripts/qapi-gen.py
 
 qga/qapi-generated/qga-qapi-types.c qga/qapi-generated/qga-qapi-types.h \
@@ -574,7 +570,7 @@ qga/qapi-generated/qga-qapi-commands.h qga/qapi-generated/qga-qapi-commands.c \
 qga/qapi-generated/qga-qapi-doc.texi: \
 qga/qapi-generated/qapi-gen-timestamp ;
 qga/qapi-generated/qapi-gen-timestamp: $(SRC_PATH)/qga/qapi-schema.json $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-gen.py \
+	$(call quiet-command,$(PYTHON_UTF8) $(SRC_PATH)/scripts/qapi-gen.py \
 		-o qga/qapi-generated -p "qga-" $<, \
 		"GEN","$(@:%-timestamp=%)")
 	@>$@
@@ -584,7 +580,6 @@ qapi-modules = $(SRC_PATH)/qapi/qapi-schema.json $(SRC_PATH)/qapi/common.json \
                $(SRC_PATH)/qapi/char.json \
                $(SRC_PATH)/qapi/crypto.json \
                $(SRC_PATH)/qapi/introspect.json \
-               $(SRC_PATH)/qapi/job.json \
                $(SRC_PATH)/qapi/migration.json \
                $(SRC_PATH)/qapi/misc.json \
                $(SRC_PATH)/qapi/net.json \
@@ -604,7 +599,6 @@ qapi/qapi-types-char.c qapi/qapi-types-char.h \
 qapi/qapi-types-common.c qapi/qapi-types-common.h \
 qapi/qapi-types-crypto.c qapi/qapi-types-crypto.h \
 qapi/qapi-types-introspect.c qapi/qapi-types-introspect.h \
-qapi/qapi-types-job.c qapi/qapi-types-job.h \
 qapi/qapi-types-migration.c qapi/qapi-types-migration.h \
 qapi/qapi-types-misc.c qapi/qapi-types-misc.h \
 qapi/qapi-types-net.c qapi/qapi-types-net.h \
@@ -623,7 +617,6 @@ qapi/qapi-visit-char.c qapi/qapi-visit-char.h \
 qapi/qapi-visit-common.c qapi/qapi-visit-common.h \
 qapi/qapi-visit-crypto.c qapi/qapi-visit-crypto.h \
 qapi/qapi-visit-introspect.c qapi/qapi-visit-introspect.h \
-qapi/qapi-visit-job.c qapi/qapi-visit-job.h \
 qapi/qapi-visit-migration.c qapi/qapi-visit-migration.h \
 qapi/qapi-visit-misc.c qapi/qapi-visit-misc.h \
 qapi/qapi-visit-net.c qapi/qapi-visit-net.h \
@@ -641,7 +634,6 @@ qapi/qapi-commands-char.c qapi/qapi-commands-char.h \
 qapi/qapi-commands-common.c qapi/qapi-commands-common.h \
 qapi/qapi-commands-crypto.c qapi/qapi-commands-crypto.h \
 qapi/qapi-commands-introspect.c qapi/qapi-commands-introspect.h \
-qapi/qapi-commands-job.c qapi/qapi-commands-job.h \
 qapi/qapi-commands-migration.c qapi/qapi-commands-migration.h \
 qapi/qapi-commands-misc.c qapi/qapi-commands-misc.h \
 qapi/qapi-commands-net.c qapi/qapi-commands-net.h \
@@ -659,7 +651,6 @@ qapi/qapi-events-char.c qapi/qapi-events-char.h \
 qapi/qapi-events-common.c qapi/qapi-events-common.h \
 qapi/qapi-events-crypto.c qapi/qapi-events-crypto.h \
 qapi/qapi-events-introspect.c qapi/qapi-events-introspect.h \
-qapi/qapi-events-job.c qapi/qapi-events-job.h \
 qapi/qapi-events-migration.c qapi/qapi-events-migration.h \
 qapi/qapi-events-misc.c qapi/qapi-events-misc.h \
 qapi/qapi-events-net.c qapi/qapi-events-net.h \
@@ -674,7 +665,7 @@ qapi/qapi-introspect.h qapi/qapi-introspect.c \
 qapi/qapi-doc.texi: \
 qapi-gen-timestamp ;
 qapi-gen-timestamp: $(qapi-modules) $(qapi-py)
-	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-gen.py \
+	$(call quiet-command,$(PYTHON_UTF8) $(SRC_PATH)/scripts/qapi-gen.py \
 		-o "qapi" -b $<, \
 		"GEN","$(@:%-timestamp=%)")
 	@>$@
@@ -723,14 +714,6 @@ module_block.h: $(SRC_PATH)/scripts/modules/module_block.py config-host.mak
 	$(addprefix $(SRC_PATH)/,$(patsubst %.mo,%.c,$(block-obj-m))), \
 	"GEN","$@")
 
-ifdef CONFIG_GCOV
-.PHONY: clean-coverage
-clean-coverage:
-	$(call quiet-command, \
-		find . \( -name '*.gcda' -o -name '*.gcov' \) -type f -exec rm {} +, \
-		"CLEAN", "coverage files")
-endif
-
 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
@@ -792,6 +775,7 @@ 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 \
 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 \
@@ -871,7 +855,7 @@ ifneq ($(BLOBS),)
 		$(INSTALL_DATA) $(SRC_PATH)/pc-bios/$$x "$(DESTDIR)$(qemu_datadir)"; \
 	done
 endif
-ifdef CONFIG_GTK
+ifeq ($(CONFIG_GTK),m)
 	$(MAKE) -C po $@
 endif
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)/keymaps"
@@ -986,16 +970,6 @@ docs/interop/qemu-qmp-ref.dvi docs/interop/qemu-qmp-ref.html \
     docs/interop/qemu-qmp-ref.txt docs/interop/qemu-qmp-ref.7: \
 	docs/interop/qemu-qmp-ref.texi docs/interop/qemu-qmp-qapi.texi
 
-# Reports/Analysis
-
-%/coverage-report.html:
-	@mkdir -p $*
-	$(call quiet-command,\
-		gcovr -p --html --html-details -o $@, \
-		"GEN", "coverage-report.html")
-
-.PHONY: coverage-report
-coverage-report: $(CURDIR)/reports/coverage/coverage-report.html
 
 ifdef CONFIG_WIN32
 
@@ -1076,9 +1050,6 @@ include $(SRC_PATH)/tests/vm/Makefile.include
 help:
 	@echo  'Generic targets:'
 	@echo  '  all             - Build all'
-ifdef CONFIG_MODULES
-	@echo  '  modules         - Build all modules'
-endif
 	@echo  '  dir/file.o      - Build specified target only'
 	@echo  '  install         - Install QEMU, documentation and tools'
 	@echo  '  ctags/TAGS      - Generate tags file for editors'
@@ -1091,9 +1062,6 @@ endif
 		echo '')
 	@echo  'Cleaning targets:'
 	@echo  '  clean           - Remove most generated files but keep the config'
-ifdef CONFIG_GCOV
-	@echo  '  clean-coverage  - Remove coverage files'
-endif
 	@echo  '  distclean       - Remove all generated files'
 	@echo  '  dist            - Build a distributable tarball'
 	@echo  ''
@@ -1105,9 +1073,6 @@ endif
 	@echo  'Documentation targets:'
 	@echo  '  html info pdf txt'
 	@echo  '                  - Build documentation in specified format'
-ifdef CONFIG_GCOV
-	@echo  '  coverage-report - Create code coverage report'
-endif
 	@echo  ''
 ifdef CONFIG_WIN32
 	@echo  'Windows targets:'

Makefile.objs

@@ -10,7 +10,6 @@ util-obj-y += qapi/qapi-types-char.o
 util-obj-y += qapi/qapi-types-common.o
 util-obj-y += qapi/qapi-types-crypto.o
 util-obj-y += qapi/qapi-types-introspect.o
-util-obj-y += qapi/qapi-types-job.o
 util-obj-y += qapi/qapi-types-migration.o
 util-obj-y += qapi/qapi-types-misc.o
 util-obj-y += qapi/qapi-types-net.o
@@ -29,7 +28,6 @@ util-obj-y += qapi/qapi-visit-char.o
 util-obj-y += qapi/qapi-visit-common.o
 util-obj-y += qapi/qapi-visit-crypto.o
 util-obj-y += qapi/qapi-visit-introspect.o
-util-obj-y += qapi/qapi-visit-job.o
 util-obj-y += qapi/qapi-visit-migration.o
 util-obj-y += qapi/qapi-visit-misc.o
 util-obj-y += qapi/qapi-visit-net.o
@@ -47,7 +45,6 @@ util-obj-y += qapi/qapi-events-char.o
 util-obj-y += qapi/qapi-events-common.o
 util-obj-y += qapi/qapi-events-crypto.o
 util-obj-y += qapi/qapi-events-introspect.o
-util-obj-y += qapi/qapi-events-job.o
 util-obj-y += qapi/qapi-events-migration.o
 util-obj-y += qapi/qapi-events-misc.o
 util-obj-y += qapi/qapi-events-net.o
@@ -66,7 +63,7 @@ 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 job.o
+block-obj-y += block.o blockjob.o
 block-obj-y += block/ scsi/
 block-obj-y += qemu-io-cmds.o
 block-obj-$(CONFIG_REPLICATION) += replication.o
@@ -97,7 +94,6 @@ io-obj-y = io/
 ifeq ($(CONFIG_SOFTMMU),y)
 common-obj-y = blockdev.o blockdev-nbd.o block/
 common-obj-y += bootdevice.o iothread.o
-common-obj-y += job-qmp.o
 common-obj-y += net/
 common-obj-y += qdev-monitor.o device-hotplug.o
 common-obj-$(CONFIG_WIN32) += os-win32.o
@@ -144,7 +140,6 @@ common-obj-y += qapi/qapi-commands-char.o
 common-obj-y += qapi/qapi-commands-common.o
 common-obj-y += qapi/qapi-commands-crypto.o
 common-obj-y += qapi/qapi-commands-introspect.o
-common-obj-y += qapi/qapi-commands-job.o
 common-obj-y += qapi/qapi-commands-migration.o
 common-obj-y += qapi/qapi-commands-misc.o
 common-obj-y += qapi/qapi-commands-net.o
@@ -196,67 +191,66 @@ vhost-user-blk-obj-y = contrib/vhost-user-blk/
 
 ######################################################################
 trace-events-subdirs =
-trace-events-subdirs += accel/kvm
-trace-events-subdirs += accel/tcg
-trace-events-subdirs += audio
+trace-events-subdirs += util
+trace-events-subdirs += crypto
+trace-events-subdirs += io
+trace-events-subdirs += migration
 trace-events-subdirs += block
 trace-events-subdirs += chardev
-trace-events-subdirs += crypto
-trace-events-subdirs += hw/9pfs
-trace-events-subdirs += hw/acpi
-trace-events-subdirs += hw/alpha
-trace-events-subdirs += hw/arm
-trace-events-subdirs += hw/audio
 trace-events-subdirs += hw/block
 trace-events-subdirs += hw/block/dataplane
 trace-events-subdirs += hw/char
-trace-events-subdirs += hw/display
-trace-events-subdirs += hw/dma
-trace-events-subdirs += hw/hppa
-trace-events-subdirs += hw/i2c
-trace-events-subdirs += hw/i386
-trace-events-subdirs += hw/i386/xen
-trace-events-subdirs += hw/ide
-trace-events-subdirs += hw/input
 trace-events-subdirs += hw/intc
-trace-events-subdirs += hw/isa
-trace-events-subdirs += hw/mem
-trace-events-subdirs += hw/misc
-trace-events-subdirs += hw/misc/macio
 trace-events-subdirs += hw/net
-trace-events-subdirs += hw/nvram
-trace-events-subdirs += hw/pci
-trace-events-subdirs += hw/pci-host
-trace-events-subdirs += hw/ppc
 trace-events-subdirs += hw/rdma
 trace-events-subdirs += hw/rdma/vmw
-trace-events-subdirs += hw/s390x
+trace-events-subdirs += hw/virtio
+trace-events-subdirs += hw/audio
+trace-events-subdirs += hw/misc
+trace-events-subdirs += hw/misc/macio
+trace-events-subdirs += hw/usb
 trace-events-subdirs += hw/scsi
-trace-events-subdirs += hw/sd
+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/sparc64
-trace-events-subdirs += hw/timer
-trace-events-subdirs += hw/tpm
-trace-events-subdirs += hw/usb
+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/pci-host
+trace-events-subdirs += hw/s390x
 trace-events-subdirs += hw/vfio
-trace-events-subdirs += hw/virtio
+trace-events-subdirs += hw/acpi
+trace-events-subdirs += hw/arm
+trace-events-subdirs += hw/alpha
+trace-events-subdirs += hw/hppa
 trace-events-subdirs += hw/xen
-trace-events-subdirs += io
-trace-events-subdirs += linux-user
-trace-events-subdirs += migration
-trace-events-subdirs += nbd
+trace-events-subdirs += hw/ide
+trace-events-subdirs += hw/tpm
+trace-events-subdirs += ui
+trace-events-subdirs += audio
 trace-events-subdirs += net
-trace-events-subdirs += qapi
-trace-events-subdirs += qom
-trace-events-subdirs += scsi
 trace-events-subdirs += target/arm
 trace-events-subdirs += target/i386
 trace-events-subdirs += target/mips
-trace-events-subdirs += target/ppc
-trace-events-subdirs += target/s390x
 trace-events-subdirs += target/sparc
-trace-events-subdirs += ui
-trace-events-subdirs += util
+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-subdirs += nbd
+trace-events-subdirs += scsi
 
 trace-events-files = $(SRC_PATH)/trace-events $(trace-events-subdirs:%=$(SRC_PATH)/%/trace-events)
 

Makefile.target

@@ -11,9 +11,9 @@ $(call set-vpath, $(SRC_PATH):$(BUILD_DIR))
 ifdef CONFIG_LINUX
 QEMU_CFLAGS += -I../linux-headers
 endif
-QEMU_CFLAGS += -iquote .. -iquote $(SRC_PATH)/target/$(TARGET_BASE_ARCH) -DNEED_CPU_H
+QEMU_CFLAGS += -I.. -I$(SRC_PATH)/target/$(TARGET_BASE_ARCH) -DNEED_CPU_H
 
-QEMU_CFLAGS+=-iquote $(SRC_PATH)/include
+QEMU_CFLAGS+=-I$(SRC_PATH)/include
 
 ifdef CONFIG_USER_ONLY
 # user emulator name
@@ -36,11 +36,6 @@ endif
 PROGS=$(QEMU_PROG) $(QEMU_PROGW)
 STPFILES=
 
-# Makefile Tests
-ifdef CONFIG_USER_ONLY
-include $(SRC_PATH)/tests/tcg/Makefile.include
-endif
-
 config-target.h: config-target.h-timestamp
 config-target.h-timestamp: config-target.mak
 
@@ -102,7 +97,7 @@ obj-$(CONFIG_TCG) += tcg/tcg.o tcg/tcg-op.o tcg/tcg-op-vec.o tcg/tcg-op-gvec.o
 obj-$(CONFIG_TCG) += tcg/tcg-common.o tcg/optimize.o
 obj-$(CONFIG_TCG_INTERPRETER) += tcg/tci.o
 obj-$(CONFIG_TCG_INTERPRETER) += disas/tci.o
-obj-$(CONFIG_TCG) += fpu/softfloat.o
+obj-y += fpu/softfloat.o
 obj-y += target/$(TARGET_BASE_ARCH)/
 obj-y += disas.o
 obj-$(call notempty,$(TARGET_XML_FILES)) += gdbstub-xml.o
@@ -143,7 +138,6 @@ obj-y += hw/
 obj-y += memory.o
 obj-y += memory_mapping.o
 obj-y += dump.o
-obj-$(TARGET_X86_64) += win_dump.o
 obj-y += migration/ram.o
 LIBS := $(libs_softmmu) $(LIBS)
 

VERSION

@@ -1 +1 @@
-2.12.90
+2.11.50

accel/Makefile.objs

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

accel/accel.c

@@ -70,8 +70,8 @@ static int accel_init_machine(AccelClass *acc, MachineState *ms)
 
 void configure_accelerator(MachineState *ms)
 {
-    const char *accel;
-    char **accel_list, **tmp;
+    const char *accel, *p;
+    char buf[10];
     int ret;
     bool accel_initialised = false;
     bool init_failed = false;
@@ -83,10 +83,13 @@ void configure_accelerator(MachineState *ms)
         accel = "tcg";
     }
 
-    accel_list = g_strsplit(accel, ":", 0);
-
-    for (tmp = accel_list; !accel_initialised && tmp && *tmp; tmp++) {
-        acc = accel_find(*tmp);
+    p = accel;
+    while (!accel_initialised && *p != '\0') {
+        if (*p == ':') {
+            p++;
+        }
+        p = get_opt_name(buf, sizeof(buf), p, ':');
+        acc = accel_find(buf);
         if (!acc) {
             continue;
         }
@@ -104,7 +107,6 @@ void configure_accelerator(MachineState *ms)
             accel_initialised = true;
         }
     }
-    g_strfreev(accel_list);
 
     if (!accel_initialised) {
         if (!init_failed) {
@@ -124,15 +126,6 @@ void accel_register_compat_props(AccelState *accel)
     register_compat_props_array(class->global_props);
 }
 
-void accel_setup_post(MachineState *ms)
-{
-    AccelState *accel = ms->accelerator;
-    AccelClass *acc = ACCEL_GET_CLASS(accel);
-    if (acc->setup_post) {
-        acc->setup_post(ms, accel);
-    }
-}
-
 static void register_accel_types(void)
 {
     type_register_static(&accel_type);

accel/kvm/Makefile.objs

@@ -1,2 +1 @@
-obj-y += kvm-all.o
-obj-$(call lnot,$(CONFIG_SEV)) += sev-stub.o
+obj-$(CONFIG_KVM) += kvm-all.o

accel/kvm/kvm-all.c

@@ -38,7 +38,6 @@
 #include "qemu/event_notifier.h"
 #include "trace.h"
 #include "hw/irq.h"
-#include "sysemu/sev.h"
 
 #include "hw/boards.h"
 
@@ -104,10 +103,6 @@ struct KVMState
 #endif
     KVMMemoryListener memory_listener;
     QLIST_HEAD(, KVMParkedVcpu) kvm_parked_vcpus;
-
-    /* memory encryption */
-    void *memcrypt_handle;
-    int (*memcrypt_encrypt_data)(void *handle, uint8_t *ptr, uint64_t len);
 };
 
 KVMState *kvm_state;
@@ -143,26 +138,6 @@ int kvm_get_max_memslots(void)
     return s->nr_slots;
 }
 
-bool kvm_memcrypt_enabled(void)
-{
-    if (kvm_state && kvm_state->memcrypt_handle) {
-        return true;
-    }
-
-    return false;
-}
-
-int kvm_memcrypt_encrypt_data(uint8_t *ptr, uint64_t len)
-{
-    if (kvm_state->memcrypt_handle &&
-        kvm_state->memcrypt_encrypt_data) {
-        return kvm_state->memcrypt_encrypt_data(kvm_state->memcrypt_handle,
-                                              ptr, len);
-    }
-
-    return 1;
-}
-
 static KVMSlot *kvm_get_free_slot(KVMMemoryListener *kml)
 {
     KVMState *s = kvm_state;
@@ -256,7 +231,7 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram,
     return 0;
 }
 
-static int kvm_set_user_memory_region(KVMMemoryListener *kml, KVMSlot *slot, bool new)
+static int kvm_set_user_memory_region(KVMMemoryListener *kml, KVMSlot *slot)
 {
     KVMState *s = kvm_state;
     struct kvm_userspace_memory_region mem;
@@ -267,7 +242,7 @@ static int kvm_set_user_memory_region(KVMMemoryListener *kml, KVMSlot *slot, boo
     mem.userspace_addr = (unsigned long)slot->ram;
     mem.flags = slot->flags;
 
-    if (slot->memory_size && !new && (mem.flags ^ slot->old_flags) & KVM_MEM_READONLY) {
+    if (slot->memory_size && mem.flags & KVM_MEM_READONLY) {
         /* Set the slot size to 0 before setting the slot to the desired
          * value. This is needed based on KVM commit 75d61fbc. */
         mem.memory_size = 0;
@@ -275,7 +250,6 @@ static int kvm_set_user_memory_region(KVMMemoryListener *kml, KVMSlot *slot, boo
     }
     mem.memory_size = slot->memory_size;
     ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
-    slot->old_flags = mem.flags;
     trace_kvm_set_user_memory(mem.slot, mem.flags, mem.guest_phys_addr,
                               mem.memory_size, mem.userspace_addr, ret);
     return ret;
@@ -392,14 +366,17 @@ static int kvm_mem_flags(MemoryRegion *mr)
 static int kvm_slot_update_flags(KVMMemoryListener *kml, KVMSlot *mem,
                                  MemoryRegion *mr)
 {
+    int old_flags;
+
+    old_flags = mem->flags;
     mem->flags = kvm_mem_flags(mr);
 
     /* If nothing changed effectively, no need to issue ioctl */
-    if (mem->flags == mem->old_flags) {
+    if (mem->flags == old_flags) {
         return 0;
     }
 
-    return kvm_set_user_memory_region(kml, mem, false);
+    return kvm_set_user_memory_region(kml, mem);
 }
 
 static int kvm_section_update_flags(KVMMemoryListener *kml,
@@ -753,8 +730,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
 
         /* unregister the slot */
         mem->memory_size = 0;
-        mem->flags = 0;
-        err = kvm_set_user_memory_region(kml, mem, false);
+        err = kvm_set_user_memory_region(kml, mem);
         if (err) {
             fprintf(stderr, "%s: error unregistering slot: %s\n",
                     __func__, strerror(-err));
@@ -770,7 +746,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
     mem->ram = ram;
     mem->flags = kvm_mem_flags(mr);
 
-    err = kvm_set_user_memory_region(kml, mem, true);
+    err = kvm_set_user_memory_region(kml, mem);
     if (err) {
         fprintf(stderr, "%s: error registering slot: %s\n", __func__,
                 strerror(-err));
@@ -1660,20 +1636,6 @@ static int kvm_init(MachineState *ms)
 
     kvm_state = s;
 
-    /*
-     * if memory encryption object is specified then initialize the memory
-     * encryption context.
-     */
-    if (ms->memory_encryption) {
-        kvm_state->memcrypt_handle = sev_guest_init(ms->memory_encryption);
-        if (!kvm_state->memcrypt_handle) {
-            ret = -1;
-            goto err;
-        }
-
-        kvm_state->memcrypt_encrypt_data = sev_encrypt_data;
-    }
-
     ret = kvm_arch_init(ms, s);
     if (ret < 0) {
         goto err;

accel/kvm/sev-stub.c

@@ -1,26 +0,0 @@
-/*
- * QEMU SEV stub
- *
- * Copyright Advanced Micro Devices 2018
- *
- * Authors:
- *      Brijesh Singh <brijesh.singh@amd.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
- */
-
-#include "qemu/osdep.h"
-#include "qemu-common.h"
-#include "sysemu/sev.h"
-
-int sev_encrypt_data(void *handle, uint8_t *ptr, uint64_t len)
-{
-    abort();
-}
-
-void *sev_guest_init(const char *id)
-{
-    return NULL;
-}

accel/stubs/kvm-stub.c

@@ -105,16 +105,6 @@ int kvm_on_sigbus(int code, void *addr)
     return 1;
 }
 
-bool kvm_memcrypt_enabled(void)
-{
-    return false;
-}
-
-int kvm_memcrypt_encrypt_data(uint8_t *ptr, uint64_t len)
-{
-  return 1;
-}
-
 #ifndef CONFIG_USER_ONLY
 int kvm_irqchip_add_msi_route(KVMState *s, int vector, PCIDevice *dev)
 {

accel/stubs/tcg-stub.c

@@ -21,6 +21,10 @@ void tb_flush(CPUState *cpu)
 {
 }
 
+void tb_unlock(void)
+{
+}
+
 void tlb_set_dirty(CPUState *cpu, target_ulong vaddr)
 {
 }

accel/tcg/atomic_template.h

@@ -18,37 +18,26 @@
  * License along with this library; if not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "trace/mem.h"
-
 #if DATA_SIZE == 16
 # define SUFFIX     o
 # define DATA_TYPE  Int128
 # define BSWAP      bswap128
-# define SHIFT      4
 #elif DATA_SIZE == 8
 # define SUFFIX     q
 # define DATA_TYPE  uint64_t
-# define SDATA_TYPE int64_t
 # define BSWAP      bswap64
-# define SHIFT      3
 #elif DATA_SIZE == 4
 # define SUFFIX     l
 # define DATA_TYPE  uint32_t
-# define SDATA_TYPE int32_t
 # define BSWAP      bswap32
-# define SHIFT      2
 #elif DATA_SIZE == 2
 # define SUFFIX     w
 # define DATA_TYPE  uint16_t
-# define SDATA_TYPE int16_t
 # define BSWAP      bswap16
-# define SHIFT      1
 #elif DATA_SIZE == 1
 # define SUFFIX     b
 # define DATA_TYPE  uint8_t
-# define SDATA_TYPE int8_t
 # define BSWAP
-# define SHIFT      0
 #else
 # error unsupported data size
 #endif
@@ -59,37 +48,14 @@
 # define ABI_TYPE  uint32_t
 #endif
 
-#define ATOMIC_TRACE_RMW do {                                           \
-        uint8_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, false); \
-                                                                        \
-        trace_guest_mem_before_exec(ENV_GET_CPU(env), addr, info);      \
-        trace_guest_mem_before_exec(ENV_GET_CPU(env), addr,             \
-                                    info | TRACE_MEM_ST);               \
-    } while (0)
-
-#define ATOMIC_TRACE_LD do {                                            \
-        uint8_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, false); \
-                                                                        \
-        trace_guest_mem_before_exec(ENV_GET_CPU(env), addr, info);      \
-    } while (0)
-
-# define ATOMIC_TRACE_ST do {                                           \
-        uint8_t info = glue(trace_mem_build_info_no_se, MEND)(SHIFT, true); \
-                                                                        \
-        trace_guest_mem_before_exec(ENV_GET_CPU(env), addr, info);      \
-    } while (0)
-
 /* Define host-endian atomic operations.  Note that END is used within
    the ATOMIC_NAME macro, and redefined below.  */
 #if DATA_SIZE == 1
 # define END
-# define MEND _be /* either le or be would be fine */
 #elif defined(HOST_WORDS_BIGENDIAN)
 # define END  _be
-# define MEND _be
 #else
 # define END  _le
-# define MEND _le
 #endif
 
 ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
@@ -97,10 +63,7 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
 {
     ATOMIC_MMU_DECLS;
     DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    DATA_TYPE ret;
-
-    ATOMIC_TRACE_RMW;
-    ret = atomic_cmpxchg__nocheck(haddr, cmpv, newv);
+    DATA_TYPE ret = atomic_cmpxchg__nocheck(haddr, cmpv, newv);
     ATOMIC_MMU_CLEANUP;
     return ret;
 }
@@ -110,8 +73,6 @@ ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr EXTRA_ARGS)
 {
     ATOMIC_MMU_DECLS;
     DATA_TYPE val, *haddr = ATOMIC_MMU_LOOKUP;
-
-    ATOMIC_TRACE_LD;
     __atomic_load(haddr, &val, __ATOMIC_RELAXED);
     ATOMIC_MMU_CLEANUP;
     return val;
@@ -122,8 +83,6 @@ void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr,
 {
     ATOMIC_MMU_DECLS;
     DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-
-    ATOMIC_TRACE_ST;
     __atomic_store(haddr, &val, __ATOMIC_RELAXED);
     ATOMIC_MMU_CLEANUP;
 }
@@ -133,10 +92,7 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr,
 {
     ATOMIC_MMU_DECLS;
     DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    DATA_TYPE ret;
-
-    ATOMIC_TRACE_RMW;
-    ret = atomic_xchg__nocheck(haddr, val);
+    DATA_TYPE ret = atomic_xchg__nocheck(haddr, val);
     ATOMIC_MMU_CLEANUP;
     return ret;
 }
@@ -147,10 +103,7 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
 {                                                                   \
     ATOMIC_MMU_DECLS;                                               \
     DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;                           \
-    DATA_TYPE ret;                                                  \
-                                                                    \
-    ATOMIC_TRACE_RMW;                                               \
-    ret = atomic_##X(haddr, val);                                   \
+    DATA_TYPE ret = atomic_##X(haddr, val);                         \
     ATOMIC_MMU_CLEANUP;                                             \
     return ret;                                                     \
 }
@@ -165,48 +118,9 @@ GEN_ATOMIC_HELPER(or_fetch)
 GEN_ATOMIC_HELPER(xor_fetch)
 
 #undef GEN_ATOMIC_HELPER
-
-/* These helpers are, as a whole, full barriers.  Within the helper,
- * the leading barrier is explicit and the trailing barrier is within
- * cmpxchg primitive.
- *
- * Trace this load + RMW loop as a single RMW op. This way, regardless
- * of CF_PARALLEL's value, we'll trace just a read and a write.
- */
-#define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET)                \
-ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
-                        ABI_TYPE xval EXTRA_ARGS)                   \
-{                                                                   \
-    ATOMIC_MMU_DECLS;                                               \
-    XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;                          \
-    XDATA_TYPE cmp, old, new, val = xval;                           \
-                                                                    \
-    ATOMIC_TRACE_RMW;                                               \
-    smp_mb();                                                       \
-    cmp = atomic_read__nocheck(haddr);                              \
-    do {                                                            \
-        old = cmp; new = FN(old, val);                              \
-        cmp = atomic_cmpxchg__nocheck(haddr, old, new);             \
-    } while (cmp != old);                                           \
-    ATOMIC_MMU_CLEANUP;                                             \
-    return RET;                                                     \
-}
-
-GEN_ATOMIC_HELPER_FN(fetch_smin, MIN, SDATA_TYPE, old)
-GEN_ATOMIC_HELPER_FN(fetch_umin, MIN,  DATA_TYPE, old)
-GEN_ATOMIC_HELPER_FN(fetch_smax, MAX, SDATA_TYPE, old)
-GEN_ATOMIC_HELPER_FN(fetch_umax, MAX,  DATA_TYPE, old)
-
-GEN_ATOMIC_HELPER_FN(smin_fetch, MIN, SDATA_TYPE, new)
-GEN_ATOMIC_HELPER_FN(umin_fetch, MIN,  DATA_TYPE, new)
-GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new)
-GEN_ATOMIC_HELPER_FN(umax_fetch, MAX,  DATA_TYPE, new)
-
-#undef GEN_ATOMIC_HELPER_FN
 #endif /* DATA SIZE >= 16 */
 
 #undef END
-#undef MEND
 
 #if DATA_SIZE > 1
 
@@ -214,10 +128,8 @@ GEN_ATOMIC_HELPER_FN(umax_fetch, MAX,  DATA_TYPE, new)
    within the ATOMIC_NAME macro.  */
 #ifdef HOST_WORDS_BIGENDIAN
 # define END  _le
-# define MEND _le
 #else
 # define END  _be
-# define MEND _be
 #endif
 
 ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
@@ -225,10 +137,7 @@ ABI_TYPE ATOMIC_NAME(cmpxchg)(CPUArchState *env, target_ulong addr,
 {
     ATOMIC_MMU_DECLS;
     DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    DATA_TYPE ret;
-
-    ATOMIC_TRACE_RMW;
-    ret = atomic_cmpxchg__nocheck(haddr, BSWAP(cmpv), BSWAP(newv));
+    DATA_TYPE ret = atomic_cmpxchg__nocheck(haddr, BSWAP(cmpv), BSWAP(newv));
     ATOMIC_MMU_CLEANUP;
     return BSWAP(ret);
 }
@@ -238,8 +147,6 @@ ABI_TYPE ATOMIC_NAME(ld)(CPUArchState *env, target_ulong addr EXTRA_ARGS)
 {
     ATOMIC_MMU_DECLS;
     DATA_TYPE val, *haddr = ATOMIC_MMU_LOOKUP;
-
-    ATOMIC_TRACE_LD;
     __atomic_load(haddr, &val, __ATOMIC_RELAXED);
     ATOMIC_MMU_CLEANUP;
     return BSWAP(val);
@@ -250,8 +157,6 @@ void ATOMIC_NAME(st)(CPUArchState *env, target_ulong addr,
 {
     ATOMIC_MMU_DECLS;
     DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-
-    ATOMIC_TRACE_ST;
     val = BSWAP(val);
     __atomic_store(haddr, &val, __ATOMIC_RELAXED);
     ATOMIC_MMU_CLEANUP;
@@ -262,10 +167,7 @@ ABI_TYPE ATOMIC_NAME(xchg)(CPUArchState *env, target_ulong addr,
 {
     ATOMIC_MMU_DECLS;
     DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
-    ABI_TYPE ret;
-
-    ATOMIC_TRACE_RMW;
-    ret = atomic_xchg__nocheck(haddr, BSWAP(val));
+    ABI_TYPE ret = atomic_xchg__nocheck(haddr, BSWAP(val));
     ATOMIC_MMU_CLEANUP;
     return BSWAP(ret);
 }
@@ -276,10 +178,7 @@ ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
 {                                                                   \
     ATOMIC_MMU_DECLS;                                               \
     DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;                           \
-    DATA_TYPE ret;                                                  \
-                                                                    \
-    ATOMIC_TRACE_RMW;                                               \
-    ret = atomic_##X(haddr, BSWAP(val));                            \
+    DATA_TYPE ret = atomic_##X(haddr, BSWAP(val));                  \
     ATOMIC_MMU_CLEANUP;                                             \
     return BSWAP(ret);                                              \
 }
@@ -293,64 +192,54 @@ GEN_ATOMIC_HELPER(xor_fetch)
 
 #undef GEN_ATOMIC_HELPER
 
-/* These helpers are, as a whole, full barriers.  Within the helper,
- * the leading barrier is explicit and the trailing barrier is within
- * cmpxchg primitive.
- *
- * Trace this load + RMW loop as a single RMW op. This way, regardless
- * of CF_PARALLEL's value, we'll trace just a read and a write.
- */
-#define GEN_ATOMIC_HELPER_FN(X, FN, XDATA_TYPE, RET)                \
-ABI_TYPE ATOMIC_NAME(X)(CPUArchState *env, target_ulong addr,       \
-                        ABI_TYPE xval EXTRA_ARGS)                   \
-{                                                                   \
-    ATOMIC_MMU_DECLS;                                               \
-    XDATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;                          \
-    XDATA_TYPE ldo, ldn, old, new, val = xval;                      \
-                                                                    \
-    ATOMIC_TRACE_RMW;                                               \
-    smp_mb();                                                       \
-    ldn = atomic_read__nocheck(haddr);                              \
-    do {                                                            \
-        ldo = ldn; old = BSWAP(ldo); new = FN(old, val);            \
-        ldn = atomic_cmpxchg__nocheck(haddr, ldo, BSWAP(new));      \
-    } while (ldo != ldn);                                           \
-    ATOMIC_MMU_CLEANUP;                                             \
-    return RET;                                                     \
-}
-
-GEN_ATOMIC_HELPER_FN(fetch_smin, MIN, SDATA_TYPE, old)
-GEN_ATOMIC_HELPER_FN(fetch_umin, MIN,  DATA_TYPE, old)
-GEN_ATOMIC_HELPER_FN(fetch_smax, MAX, SDATA_TYPE, old)
-GEN_ATOMIC_HELPER_FN(fetch_umax, MAX,  DATA_TYPE, old)
-
-GEN_ATOMIC_HELPER_FN(smin_fetch, MIN, SDATA_TYPE, new)
-GEN_ATOMIC_HELPER_FN(umin_fetch, MIN,  DATA_TYPE, new)
-GEN_ATOMIC_HELPER_FN(smax_fetch, MAX, SDATA_TYPE, new)
-GEN_ATOMIC_HELPER_FN(umax_fetch, MAX,  DATA_TYPE, new)
-
 /* Note that for addition, we need to use a separate cmpxchg loop instead
    of bswaps for the reverse-host-endian helpers.  */
-#define ADD(X, Y)   (X + Y)
-GEN_ATOMIC_HELPER_FN(fetch_add, ADD, DATA_TYPE, old)
-GEN_ATOMIC_HELPER_FN(add_fetch, ADD, DATA_TYPE, new)
-#undef ADD
+ABI_TYPE ATOMIC_NAME(fetch_add)(CPUArchState *env, target_ulong addr,
+                         ABI_TYPE val EXTRA_ARGS)
+{
+    ATOMIC_MMU_DECLS;
+    DATA_TYPE *haddr = ATOMIC_MMU_LOOKUP;
+    DATA_TYPE ldo, ldn, ret, sto;
 
-#undef GEN_ATOMIC_HELPER_FN
+    ldo = atomic_read__nocheck(haddr);
+    while (1) {
+        ret = BSWAP(ldo);
+        sto = BSWAP(ret + val);
+        ldn = atomic_cmpxchg__nocheck(haddr, ldo, sto);
+        if (ldn == ldo) {
+            ATOMIC_MMU_CLEANUP;
+            return ret;
+        }
+        ldo = ldn;
+    }
+}
+
+ABI_TYPE ATOMIC_NAME(add_fetch)(CPUArchState *env, target_ulong addr,
+                         ABI_TYPE val EXTRA_ARGS)
+{
+    ATOMIC_MMU_DECLS;
+    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) {
+            ATOMIC_MMU_CLEANUP;
+            return ret;
+        }
+        ldo = ldn;
+    }
+}
 #endif /* DATA_SIZE >= 16 */
 
 #undef END
-#undef MEND
 #endif /* DATA_SIZE > 1 */
 
-#undef ATOMIC_TRACE_ST
-#undef ATOMIC_TRACE_LD
-#undef ATOMIC_TRACE_RMW
-
 #undef BSWAP
 #undef ABI_TYPE
 #undef DATA_TYPE
-#undef SDATA_TYPE
 #undef SUFFIX
 #undef DATA_SIZE
-#undef SHIFT

accel/tcg/cpu-exec-common.c

@@ -27,8 +27,10 @@ bool tcg_allowed;
 /* exit the current TB, but without causing any exception to be raised */
 void cpu_loop_exit_noexc(CPUState *cpu)
 {
+    /* XXX: restore cpu registers saved in host registers */
+
     cpu->exception_index = -1;
-    cpu_loop_exit(cpu);
+    siglongjmp(cpu->jmp_env, 1);
 }
 
 #if defined(CONFIG_SOFTMMU)
@@ -63,17 +65,15 @@ void cpu_reloading_memory_map(void)
 
 void cpu_loop_exit(CPUState *cpu)
 {
-    /* Undo the setting in cpu_tb_exec.  */
-    cpu->can_do_io = 1;
     siglongjmp(cpu->jmp_env, 1);
 }
 
 void cpu_loop_exit_restore(CPUState *cpu, uintptr_t pc)
 {
     if (pc) {
-        cpu_restore_state(cpu, pc, true);
+        cpu_restore_state(cpu, pc);
     }
-    cpu_loop_exit(cpu);
+    siglongjmp(cpu->jmp_env, 1);
 }
 
 void cpu_loop_exit_atomic(CPUState *cpu, uintptr_t pc)

accel/tcg/cpu-exec.c

@@ -25,6 +25,7 @@
 #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/tb-lookup.h"
@@ -155,14 +156,11 @@ static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb)
     if (qemu_loglevel_mask(CPU_LOG_TB_CPU)
         && qemu_log_in_addr_range(itb->pc)) {
         qemu_log_lock();
-        int flags = 0;
-        if (qemu_loglevel_mask(CPU_LOG_TB_FPU)) {
-            flags |= CPU_DUMP_FPU;
-        }
 #if defined(TARGET_I386)
-        flags |= CPU_DUMP_CCOP;
+        log_cpu_state(cpu, CPU_DUMP_CCOP);
+#else
+        log_cpu_state(cpu, 0);
 #endif
-        log_cpu_state(cpu, flags);
         qemu_log_unlock();
     }
 #endif /* DEBUG_DISAS */
@@ -212,20 +210,20 @@ static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
        We only end up here when an existing TB is too long.  */
     cflags |= MIN(max_cycles, CF_COUNT_MASK);
 
-    mmap_lock();
+    tb_lock();
     tb = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base,
                      orig_tb->flags, cflags);
     tb->orig_tb = orig_tb;
-    mmap_unlock();
+    tb_unlock();
 
     /* execute the generated code */
     trace_exec_tb_nocache(tb, tb->pc);
     cpu_tb_exec(cpu, tb);
 
-    mmap_lock();
+    tb_lock();
     tb_phys_invalidate(tb, -1);
-    mmap_unlock();
-    tcg_tb_remove(tb);
+    tb_remove(tb);
+    tb_unlock();
 }
 #endif
 
@@ -244,7 +242,12 @@ void cpu_exec_step_atomic(CPUState *cpu)
         tb = tb_lookup__cpu_state(cpu, &pc, &cs_base, &flags, cf_mask);
         if (tb == NULL) {
             mmap_lock();
+            tb_lock();
+            tb = tb_htable_lookup(cpu, pc, cs_base, flags, cf_mask);
+            if (likely(tb == NULL)) {
                 tb = tb_gen_code(cpu, pc, cs_base, flags, cflags);
+            }
+            tb_unlock();
             mmap_unlock();
         }
 
@@ -259,14 +262,15 @@ void cpu_exec_step_atomic(CPUState *cpu)
         cpu_tb_exec(cpu, tb);
         cc->cpu_exec_exit(cpu);
     } 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
-        assert_no_pages_locked();
+        tb_lock_reset();
     }
 
     if (in_exclusive_region) {
@@ -289,7 +293,7 @@ struct tb_desc {
     uint32_t trace_vcpu_dstate;
 };
 
-static bool tb_lookup_cmp(const void *p, const void *d)
+static bool tb_cmp(const void *p, const void *d)
 {
     const TranslationBlock *tb = p;
     const struct tb_desc *desc = d;
@@ -334,7 +338,7 @@ TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong 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, cf_mask, *cpu->trace_dstate);
-    return qht_lookup_custom(&tb_ctx.htable, &desc, h, tb_lookup_cmp);
+    return qht_lookup(&tb_ctx.htable, tb_cmp, &desc, h);
 }
 
 void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr)
@@ -348,43 +352,28 @@ void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr)
     }
 }
 
+/* Called with tb_lock held.  */
 static inline void tb_add_jump(TranslationBlock *tb, int n,
                                TranslationBlock *tb_next)
 {
-    uintptr_t old;
-
     assert(n < ARRAY_SIZE(tb->jmp_list_next));
-    qemu_spin_lock(&tb_next->jmp_lock);
-
-    /* make sure the destination TB is valid */
-    if (tb_next->cflags & CF_INVALID) {
-        goto out_unlock_next;
+    if (tb->jmp_list_next[n]) {
+        /* Another thread has already done this while we were
+         * outside of the lock; nothing to do in this case */
+        return;
     }
-    /* Atomically claim the jump destination slot only if it was NULL */
-    old = atomic_cmpxchg(&tb->jmp_dest[n], (uintptr_t)NULL, (uintptr_t)tb_next);
-    if (old) {
-        goto out_unlock_next;
-    }
-
-    /* patch the native jump address */
-    tb_set_jmp_target(tb, n, (uintptr_t)tb_next->tc.ptr);
-
-    /* add in TB jmp list */
-    tb->jmp_list_next[n] = tb_next->jmp_list_head;
-    tb_next->jmp_list_head = (uintptr_t)tb | n;
-
-    qemu_spin_unlock(&tb_next->jmp_lock);
-
     qemu_log_mask_and_addr(CPU_LOG_EXEC, tb->pc,
                            "Linking TBs %p [" TARGET_FMT_lx
                            "] index %d -> %p [" TARGET_FMT_lx "]\n",
                            tb->tc.ptr, tb->pc, n,
                            tb_next->tc.ptr, tb_next->pc);
-    return;
 
- out_unlock_next:
-    qemu_spin_unlock(&tb_next->jmp_lock);
-    return;
+    /* patch the native jump address */
+    tb_set_jmp_target(tb, n, (uintptr_t)tb_next->tc.ptr);
+
+    /* add in TB jmp circular list */
+    tb->jmp_list_next[n] = tb_next->jmp_list_first;
+    tb_next->jmp_list_first = (uintptr_t)tb | n;
 }
 
 static inline TranslationBlock *tb_find(CPUState *cpu,
@@ -394,11 +383,27 @@ static inline TranslationBlock *tb_find(CPUState *cpu,
     TranslationBlock *tb;
     target_ulong cs_base, pc;
     uint32_t flags;
+    bool acquired_tb_lock = false;
 
     tb = tb_lookup__cpu_state(cpu, &pc, &cs_base, &flags, cf_mask);
     if (tb == NULL) {
+        /* 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();
+        acquired_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, cf_mask);
+        if (likely(tb == NULL)) {
+            /* if no translated code available, then translate it now */
             tb = tb_gen_code(cpu, pc, cs_base, flags, cf_mask);
+        }
+
         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);
@@ -414,8 +419,17 @@ static inline TranslationBlock *tb_find(CPUState *cpu,
 #endif
     /* See if we can patch the calling TB. */
     if (last_tb && !qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) {
+        if (!acquired_tb_lock) {
+            tb_lock();
+            acquired_tb_lock = true;
+        }
+        if (!(tb->cflags & CF_INVALID)) {
             tb_add_jump(last_tb, tb_exit, tb);
         }
+    }
+    if (acquired_tb_lock) {
+        tb_unlock();
+    }
     return tb;
 }
 
@@ -571,7 +585,6 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
         else {
             if (cc->cpu_exec_interrupt(cpu, interrupt_request)) {
                 replay_interrupt();
-                cpu->exception_index = -1;
                 *last_tb = NULL;
             }
             /* The target hook may have updated the 'cpu->interrupt_request';
@@ -593,9 +606,7 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
     if (unlikely(atomic_read(&cpu->exit_request)
         || (use_icount && cpu->icount_decr.u16.low + cpu->icount_extra == 0))) {
         atomic_set(&cpu->exit_request, 0);
-        if (cpu->exception_index == -1) {
         cpu->exception_index = EXCP_INTERRUPT;
-        }
         return true;
     }
 
@@ -690,9 +701,8 @@ int cpu_exec(CPUState *cpu)
         g_assert(cpu == current_cpu);
         g_assert(cc == CPU_GET_CLASS(cpu));
 #endif /* buggy compiler */
-#ifndef CONFIG_SOFTMMU
-        tcg_debug_assert(!have_mmap_lock());
-#endif
+        cpu->can_do_io = 1;
+        tb_lock_reset();
         if (qemu_mutex_iothread_locked()) {
             qemu_mutex_unlock_iothread();
         }

accel/tcg/cputlb.c

@@ -125,6 +125,8 @@ static void tlb_flush_nocheck(CPUState *cpu)
     atomic_set(&env->tlb_flush_count, env->tlb_flush_count + 1);
     tlb_debug("(count: %zu)\n", tlb_flush_count());
 
+    tb_lock();
+
     memset(env->tlb_table, -1, sizeof(env->tlb_table));
     memset(env->tlb_v_table, -1, sizeof(env->tlb_v_table));
     cpu_tb_jmp_cache_clear(cpu);
@@ -133,6 +135,8 @@ static void tlb_flush_nocheck(CPUState *cpu)
     env->tlb_flush_addr = -1;
     env->tlb_flush_mask = 0;
 
+    tb_unlock();
+
     atomic_mb_set(&cpu->pending_tlb_flush, 0);
 }
 
@@ -176,6 +180,8 @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data)
 
     assert_cpu_is_self(cpu);
 
+    tb_lock();
+
     tlb_debug("start: mmu_idx:0x%04lx\n", mmu_idx_bitmask);
 
     for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
@@ -191,6 +197,8 @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data)
     cpu_tb_jmp_cache_clear(cpu);
 
     tlb_debug("done\n");
+
+    tb_unlock();
 }
 
 void tlb_flush_by_mmuidx(CPUState *cpu, uint16_t idxmap)
@@ -235,30 +243,20 @@ void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *src_cpu,
     async_safe_run_on_cpu(src_cpu, fn, RUN_ON_CPU_HOST_INT(idxmap));
 }
 
-static inline bool tlb_hit_page_anyprot(CPUTLBEntry *tlb_entry,
-                                        target_ulong page)
-{
-    return tlb_hit_page(tlb_entry->addr_read, page) ||
-           tlb_hit_page(tlb_entry->addr_write, page) ||
-           tlb_hit_page(tlb_entry->addr_code, page);
-}
 
-static inline void tlb_flush_entry(CPUTLBEntry *tlb_entry, target_ulong page)
+
+static inline void tlb_flush_entry(CPUTLBEntry *tlb_entry, target_ulong addr)
 {
-    if (tlb_hit_page_anyprot(tlb_entry, page)) {
+    if (addr == (tlb_entry->addr_read &
+                 (TARGET_PAGE_MASK | TLB_INVALID_MASK)) ||
+        addr == (tlb_entry->addr_write &
+                 (TARGET_PAGE_MASK | TLB_INVALID_MASK)) ||
+        addr == (tlb_entry->addr_code &
+                 (TARGET_PAGE_MASK | TLB_INVALID_MASK))) {
         memset(tlb_entry, -1, sizeof(*tlb_entry));
     }
 }
 
-static inline void tlb_flush_vtlb_page(CPUArchState *env, int mmu_idx,
-                                       target_ulong page)
-{
-    int k;
-    for (k = 0; k < CPU_VTLB_SIZE; k++) {
-        tlb_flush_entry(&env->tlb_v_table[mmu_idx][k], page);
-    }
-}
-
 static void tlb_flush_page_async_work(CPUState *cpu, run_on_cpu_data data)
 {
     CPUArchState *env = cpu->env_ptr;
@@ -284,7 +282,14 @@ static void tlb_flush_page_async_work(CPUState *cpu, run_on_cpu_data data)
     i = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
     for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
         tlb_flush_entry(&env->tlb_table[mmu_idx][i], addr);
-        tlb_flush_vtlb_page(env, mmu_idx, addr);
+    }
+
+    /* check whether there are entries that need to be flushed in the vtlb */
+    for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
+        int k;
+        for (k = 0; k < CPU_VTLB_SIZE; k++) {
+            tlb_flush_entry(&env->tlb_v_table[mmu_idx][k], addr);
+        }
     }
 
     tb_flush_jmp_cache(cpu, addr);
@@ -316,6 +321,7 @@ static void tlb_flush_page_by_mmuidx_async_work(CPUState *cpu,
     unsigned long mmu_idx_bitmap = addr_and_mmuidx & ALL_MMUIDX_BITS;
     int page = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
     int mmu_idx;
+    int i;
 
     assert_cpu_is_self(cpu);
 
@@ -325,7 +331,11 @@ static void tlb_flush_page_by_mmuidx_async_work(CPUState *cpu,
     for (mmu_idx = 0; mmu_idx < NB_MMU_MODES; mmu_idx++) {
         if (test_bit(mmu_idx, &mmu_idx_bitmap)) {
             tlb_flush_entry(&env->tlb_table[mmu_idx][page], addr);
-            tlb_flush_vtlb_page(env, mmu_idx, addr);
+
+            /* check whether there are vltb entries that need to be flushed */
+            for (i = 0; i < CPU_VTLB_SIZE; i++) {
+                tlb_flush_entry(&env->tlb_v_table[mmu_idx][i], addr);
+            }
         }
     }
 
@@ -610,42 +620,27 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
     target_ulong address;
     target_ulong code_address;
     uintptr_t addend;
-    CPUTLBEntry *te, tn;
-    hwaddr iotlb, xlat, sz, paddr_page;
-    target_ulong vaddr_page;
+    CPUTLBEntry *te, *tv, tn;
+    hwaddr iotlb, xlat, sz;
+    unsigned vidx = env->vtlb_index++ % CPU_VTLB_SIZE;
     int asidx = cpu_asidx_from_attrs(cpu, attrs);
 
     assert_cpu_is_self(cpu);
-
-    if (size < TARGET_PAGE_SIZE) {
-        sz = TARGET_PAGE_SIZE;
-    } else {
-        if (size > TARGET_PAGE_SIZE) {
+    assert(size >= TARGET_PAGE_SIZE);
+    if (size != TARGET_PAGE_SIZE) {
         tlb_add_large_page(env, vaddr, size);
     }
-        sz = size;
-    }
-    vaddr_page = vaddr & TARGET_PAGE_MASK;
-    paddr_page = paddr & TARGET_PAGE_MASK;
 
-    section = address_space_translate_for_iotlb(cpu, asidx, paddr_page,
-                                                &xlat, &sz, attrs, &prot);
+    sz = size;
+    section = address_space_translate_for_iotlb(cpu, asidx, paddr, &xlat, &sz);
     assert(sz >= TARGET_PAGE_SIZE);
 
     tlb_debug("vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx
               " prot=%x idx=%d\n",
               vaddr, paddr, prot, mmu_idx);
 
-    address = vaddr_page;
-    if (size < TARGET_PAGE_SIZE) {
-        /*
-         * Slow-path the TLB entries; we will repeat the MMU check and TLB
-         * fill on every access.
-         */
-        address |= TLB_RECHECK;
-    }
-    if (!memory_region_is_ram(section->mr) &&
-        !memory_region_is_romd(section->mr)) {
+    address = vaddr;
+    if (!memory_region_is_ram(section->mr) && !memory_region_is_romd(section->mr)) {
         /* IO memory case */
         address |= TLB_MMIO;
         addend = 0;
@@ -654,47 +649,26 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
         addend = (uintptr_t)memory_region_get_ram_ptr(section->mr) + xlat;
     }
 
-    /* Make sure there's no cached translation for the new page.  */
-    tlb_flush_vtlb_page(env, mmu_idx, vaddr_page);
-
     code_address = address;
-    iotlb = memory_region_section_get_iotlb(cpu, section, vaddr_page,
-                                            paddr_page, xlat, prot, &address);
+    iotlb = memory_region_section_get_iotlb(cpu, section, vaddr, paddr, xlat,
+                                            prot, &address);
 
-    index = (vaddr_page >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
+    index = (vaddr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
     te = &env->tlb_table[mmu_idx][index];
+    /* do not discard the translation in te, evict it into a victim tlb */
+    tv = &env->tlb_v_table[mmu_idx][vidx];
 
-    /*
-     * Only evict the old entry to the victim tlb if it's for a
-     * different page; otherwise just overwrite the stale data.
-     */
-    if (!tlb_hit_page_anyprot(te, vaddr_page)) {
-        unsigned vidx = env->vtlb_index++ % CPU_VTLB_SIZE;
-        CPUTLBEntry *tv = &env->tlb_v_table[mmu_idx][vidx];
-
-        /* Evict the old entry into the victim tlb.  */
+    /* addr_write can race with tlb_reset_dirty_range */
     copy_tlb_helper(tv, te, true);
+
     env->iotlb_v[mmu_idx][vidx] = env->iotlb[mmu_idx][index];
-    }
 
     /* refill the tlb */
-    /*
-     * At this point iotlb contains a physical section number in the lower
-     * TARGET_PAGE_BITS, and either
-     *  + the ram_addr_t of the page base of the target RAM (if NOTDIRTY or ROM)
-     *  + the offset within section->mr of the page base (otherwise)
-     * We subtract the vaddr_page (which is page aligned and thus won't
-     * disturb the low bits) to give an offset which can be added to the
-     * (non-page-aligned) vaddr of the eventual memory access to get
-     * the MemoryRegion offset for the access. Note that the vaddr we
-     * subtract here is that of the page base, and not the same as the
-     * vaddr we add back in io_readx()/io_writex()/get_page_addr_code().
-     */
-    env->iotlb[mmu_idx][index].addr = iotlb - vaddr_page;
+    env->iotlb[mmu_idx][index].addr = iotlb - vaddr;
     env->iotlb[mmu_idx][index].attrs = attrs;
 
     /* Now calculate the new entry */
-    tn.addend = addend - vaddr_page;
+    tn.addend = addend - vaddr;
     if (prot & PAGE_READ) {
         tn.addr_read = address;
     } else {
@@ -788,43 +762,16 @@ static inline ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr)
 
 static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
                          int mmu_idx,
-                         target_ulong addr, uintptr_t retaddr,
-                         bool recheck, int size)
+                         target_ulong addr, uintptr_t retaddr, int size)
 {
     CPUState *cpu = ENV_GET_CPU(env);
-    hwaddr mr_offset;
-    MemoryRegionSection *section;
-    MemoryRegion *mr;
+    hwaddr physaddr = iotlbentry->addr;
+    MemoryRegion *mr = iotlb_to_region(cpu, physaddr, iotlbentry->attrs);
     uint64_t val;
     bool locked = false;
     MemTxResult r;
 
-    if (recheck) {
-        /*
-         * This is a TLB_RECHECK access, where the MMU protection
-         * covers a smaller range than a target page, and we must
-         * repeat the MMU check here. This tlb_fill() call might
-         * longjump out if this access should cause a guest exception.
-         */
-        int index;
-        target_ulong tlb_addr;
-
-        tlb_fill(cpu, addr, size, MMU_DATA_LOAD, mmu_idx, retaddr);
-
-        index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
-        tlb_addr = env->tlb_table[mmu_idx][index].addr_read;
-        if (!(tlb_addr & ~(TARGET_PAGE_MASK | TLB_RECHECK))) {
-            /* RAM access */
-            uintptr_t haddr = addr + env->tlb_table[mmu_idx][index].addend;
-
-            return ldn_p((void *)haddr, size);
-        }
-        /* Fall through for handling IO accesses */
-    }
-
-    section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs);
-    mr = section->mr;
-    mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
+    physaddr = (physaddr & TARGET_PAGE_MASK) + addr;
     cpu->mem_io_pc = retaddr;
     if (mr != &io_mem_rom && mr != &io_mem_notdirty && !cpu->can_do_io) {
         cpu_io_recompile(cpu, retaddr);
@@ -836,13 +783,9 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
         qemu_mutex_lock_iothread();
         locked = true;
     }
-    r = memory_region_dispatch_read(mr, mr_offset,
+    r = memory_region_dispatch_read(mr, physaddr,
                                     &val, size, iotlbentry->attrs);
     if (r != MEMTX_OK) {
-        hwaddr physaddr = mr_offset +
-            section->offset_within_address_space -
-            section->offset_within_region;
-
         cpu_transaction_failed(cpu, physaddr, addr, size, MMU_DATA_LOAD,
                                mmu_idx, iotlbentry->attrs, r, retaddr);
     }
@@ -856,42 +799,15 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
 static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
                       int mmu_idx,
                       uint64_t val, target_ulong addr,
-                      uintptr_t retaddr, bool recheck, int size)
+                      uintptr_t retaddr, int size)
 {
     CPUState *cpu = ENV_GET_CPU(env);
-    hwaddr mr_offset;
-    MemoryRegionSection *section;
-    MemoryRegion *mr;
+    hwaddr physaddr = iotlbentry->addr;
+    MemoryRegion *mr = iotlb_to_region(cpu, physaddr, iotlbentry->attrs);
     bool locked = false;
     MemTxResult r;
 
-    if (recheck) {
-        /*
-         * This is a TLB_RECHECK access, where the MMU protection
-         * covers a smaller range than a target page, and we must
-         * repeat the MMU check here. This tlb_fill() call might
-         * longjump out if this access should cause a guest exception.
-         */
-        int index;
-        target_ulong tlb_addr;
-
-        tlb_fill(cpu, addr, size, MMU_DATA_STORE, mmu_idx, retaddr);
-
-        index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
-        tlb_addr = env->tlb_table[mmu_idx][index].addr_write;
-        if (!(tlb_addr & ~(TARGET_PAGE_MASK | TLB_RECHECK))) {
-            /* RAM access */
-            uintptr_t haddr = addr + env->tlb_table[mmu_idx][index].addend;
-
-            stn_p((void *)haddr, size, val);
-            return;
-        }
-        /* Fall through for handling IO accesses */
-    }
-
-    section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs);
-    mr = section->mr;
-    mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
+    physaddr = (physaddr & TARGET_PAGE_MASK) + addr;
     if (mr != &io_mem_rom && mr != &io_mem_notdirty && !cpu->can_do_io) {
         cpu_io_recompile(cpu, retaddr);
     }
@@ -902,13 +818,9 @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
         qemu_mutex_lock_iothread();
         locked = true;
     }
-    r = memory_region_dispatch_write(mr, mr_offset,
+    r = memory_region_dispatch_write(mr, physaddr,
                                      val, size, iotlbentry->attrs);
     if (r != MEMTX_OK) {
-        hwaddr physaddr = mr_offset +
-            section->offset_within_address_space -
-            section->offset_within_region;
-
         cpu_transaction_failed(cpu, physaddr, addr, size, MMU_DATA_STORE,
                                mmu_idx, iotlbentry->attrs, r, retaddr);
     }
@@ -956,51 +868,24 @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index,
  */
 tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr)
 {
-    int mmu_idx, index;
+    int mmu_idx, index, pd;
     void *p;
     MemoryRegion *mr;
-    MemoryRegionSection *section;
     CPUState *cpu = ENV_GET_CPU(env);
     CPUIOTLBEntry *iotlbentry;
-    hwaddr physaddr, mr_offset;
+    hwaddr physaddr;
 
     index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
     mmu_idx = cpu_mmu_index(env, true);
-    if (unlikely(!tlb_hit(env->tlb_table[mmu_idx][index].addr_code, addr))) {
+    if (unlikely(env->tlb_table[mmu_idx][index].addr_code !=
+                 (addr & (TARGET_PAGE_MASK | TLB_INVALID_MASK)))) {
         if (!VICTIM_TLB_HIT(addr_read, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, 0, MMU_INST_FETCH, mmu_idx, 0);
         }
     }
-
-    if (unlikely((env->tlb_table[mmu_idx][index].addr_code &
-                  (TLB_RECHECK | TLB_INVALID_MASK)) == TLB_RECHECK)) {
-        /*
-         * This is a TLB_RECHECK access, where the MMU protection
-         * covers a smaller range than a target page, and we must
-         * repeat the MMU check here. This tlb_fill() call might
-         * longjump out if this access should cause a guest exception.
-         */
-        int index;
-        target_ulong tlb_addr;
-
-        tlb_fill(cpu, addr, 0, MMU_INST_FETCH, mmu_idx, 0);
-
-        index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
-        tlb_addr = env->tlb_table[mmu_idx][index].addr_code;
-        if (!(tlb_addr & ~(TARGET_PAGE_MASK | TLB_RECHECK))) {
-            /* RAM access. We can't handle this, so for now just stop */
-            cpu_abort(cpu, "Unable to handle guest executing from RAM within "
-                      "a small MPU region at 0x" TARGET_FMT_lx, addr);
-        }
-        /*
-         * Fall through to handle IO accesses (which will almost certainly
-         * also result in failure)
-         */
-    }
-
     iotlbentry = &env->iotlb[mmu_idx][index];
-    section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs);
-    mr = section->mr;
+    pd = iotlbentry->addr & ~TARGET_PAGE_MASK;
+    mr = iotlb_to_region(cpu, pd, iotlbentry->attrs);
     if (memory_region_is_unassigned(mr)) {
         qemu_mutex_lock_iothread();
         if (memory_region_request_mmio_ptr(mr, addr)) {
@@ -1021,10 +906,7 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr)
          * and use the MemTXResult it produced). However it is the
          * simplest place we have currently available for the check.
          */
-        mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
-        physaddr = mr_offset +
-            section->offset_within_address_space -
-            section->offset_within_region;
+        physaddr = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
         cpu_transaction_failed(cpu, physaddr, addr, 0, MMU_INST_FETCH, mmu_idx,
                                iotlbentry->attrs, MEMTX_DECODE_ERROR, 0);
 
@@ -1052,7 +934,8 @@ void probe_write(CPUArchState *env, target_ulong addr, int size, int mmu_idx,
     int index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
     target_ulong tlb_addr = env->tlb_table[mmu_idx][index].addr_write;
 
-    if (!tlb_hit(tlb_addr, addr)) {
+    if ((addr & TARGET_PAGE_MASK)
+        != (tlb_addr & (TARGET_PAGE_MASK | TLB_INVALID_MASK))) {
         /* TLB entry is for a different page */
         if (!VICTIM_TLB_HIT(addr_write, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, size, MMU_DATA_STORE,
@@ -1096,7 +979,8 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
     }
 
     /* Check TLB entry and enforce page permissions.  */
-    if (!tlb_hit(tlb_addr, addr)) {
+    if ((addr & TARGET_PAGE_MASK)
+        != (tlb_addr & (TARGET_PAGE_MASK | TLB_INVALID_MASK))) {
         if (!VICTIM_TLB_HIT(addr_write, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, 1 << s_bits, MMU_DATA_STORE,
                      mmu_idx, retaddr);
@@ -1104,8 +988,8 @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
         tlb_addr = tlbe->addr_write & ~TLB_INVALID_MASK;
     }
 
-    /* Notice an IO access or a needs-MMU-lookup access */
-    if (unlikely(tlb_addr & (TLB_MMIO | TLB_RECHECK))) {
+    /* Notice an IO access  */
+    if (unlikely(tlb_addr & TLB_MMIO)) {
         /* There's really nothing that can be done to
            support this apart from stop-the-world.  */
         goto stop_the_world;

accel/tcg/softmmu_template.h

@@ -98,12 +98,10 @@
 static inline DATA_TYPE glue(io_read, SUFFIX)(CPUArchState *env,
                                               size_t mmu_idx, size_t index,
                                               target_ulong addr,
-                                              uintptr_t retaddr,
-                                              bool recheck)
+                                              uintptr_t retaddr)
 {
     CPUIOTLBEntry *iotlbentry = &env->iotlb[mmu_idx][index];
-    return io_readx(env, iotlbentry, mmu_idx, addr, retaddr, recheck,
-                    DATA_SIZE);
+    return io_readx(env, iotlbentry, mmu_idx, addr, retaddr, DATA_SIZE);
 }
 #endif
 
@@ -123,7 +121,8 @@ WORD_TYPE helper_le_ld_name(CPUArchState *env, target_ulong addr,
     }
 
     /* If the TLB entry is for a different page, reload and try again.  */
-    if (!tlb_hit(tlb_addr, addr)) {
+    if ((addr & TARGET_PAGE_MASK)
+         != (tlb_addr & (TARGET_PAGE_MASK | TLB_INVALID_MASK))) {
         if (!VICTIM_TLB_HIT(ADDR_READ, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, DATA_SIZE, READ_ACCESS_TYPE,
                      mmu_idx, retaddr);
@@ -139,8 +138,7 @@ WORD_TYPE helper_le_ld_name(CPUArchState *env, target_ulong addr,
 
         /* ??? Note that the io helpers always read data in the target
            byte ordering.  We should push the LE/BE request down into io.  */
-        res = glue(io_read, SUFFIX)(env, mmu_idx, index, addr, retaddr,
-                                    tlb_addr & TLB_RECHECK);
+        res = glue(io_read, SUFFIX)(env, mmu_idx, index, addr, retaddr);
         res = TGT_LE(res);
         return res;
     }
@@ -190,7 +188,8 @@ WORD_TYPE helper_be_ld_name(CPUArchState *env, target_ulong addr,
     }
 
     /* If the TLB entry is for a different page, reload and try again.  */
-    if (!tlb_hit(tlb_addr, addr)) {
+    if ((addr & TARGET_PAGE_MASK)
+         != (tlb_addr & (TARGET_PAGE_MASK | TLB_INVALID_MASK))) {
         if (!VICTIM_TLB_HIT(ADDR_READ, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, DATA_SIZE, READ_ACCESS_TYPE,
                      mmu_idx, retaddr);
@@ -206,8 +205,7 @@ WORD_TYPE helper_be_ld_name(CPUArchState *env, target_ulong addr,
 
         /* ??? Note that the io helpers always read data in the target
            byte ordering.  We should push the LE/BE request down into io.  */
-        res = glue(io_read, SUFFIX)(env, mmu_idx, index, addr, retaddr,
-                                    tlb_addr & TLB_RECHECK);
+        res = glue(io_read, SUFFIX)(env, mmu_idx, index, addr, retaddr);
         res = TGT_BE(res);
         return res;
     }
@@ -261,12 +259,10 @@ static inline void glue(io_write, SUFFIX)(CPUArchState *env,
                                           size_t mmu_idx, size_t index,
                                           DATA_TYPE val,
                                           target_ulong addr,
-                                          uintptr_t retaddr,
-                                          bool recheck)
+                                          uintptr_t retaddr)
 {
     CPUIOTLBEntry *iotlbentry = &env->iotlb[mmu_idx][index];
-    return io_writex(env, iotlbentry, mmu_idx, val, addr, retaddr,
-                     recheck, DATA_SIZE);
+    return io_writex(env, iotlbentry, mmu_idx, val, addr, retaddr, DATA_SIZE);
 }
 
 void helper_le_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
@@ -284,7 +280,8 @@ void helper_le_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
     }
 
     /* If the TLB entry is for a different page, reload and try again.  */
-    if (!tlb_hit(tlb_addr, addr)) {
+    if ((addr & TARGET_PAGE_MASK)
+        != (tlb_addr & (TARGET_PAGE_MASK | TLB_INVALID_MASK))) {
         if (!VICTIM_TLB_HIT(addr_write, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, DATA_SIZE, MMU_DATA_STORE,
                      mmu_idx, retaddr);
@@ -301,8 +298,7 @@ void helper_le_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
         /* ??? Note that the io helpers always read data in the target
            byte ordering.  We should push the LE/BE request down into io.  */
         val = TGT_LE(val);
-        glue(io_write, SUFFIX)(env, mmu_idx, index, val, addr,
-                               retaddr, tlb_addr & TLB_RECHECK);
+        glue(io_write, SUFFIX)(env, mmu_idx, index, val, addr, retaddr);
         return;
     }
 
@@ -319,7 +315,7 @@ void helper_le_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
         page2 = (addr + DATA_SIZE) & TARGET_PAGE_MASK;
         index2 = (page2 >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
         tlb_addr2 = env->tlb_table[mmu_idx][index2].addr_write;
-        if (!tlb_hit_page(tlb_addr2, page2)
+        if (page2 != (tlb_addr2 & (TARGET_PAGE_MASK | TLB_INVALID_MASK))
             && !VICTIM_TLB_HIT(addr_write, page2)) {
             tlb_fill(ENV_GET_CPU(env), page2, DATA_SIZE, MMU_DATA_STORE,
                      mmu_idx, retaddr);
@@ -361,7 +357,8 @@ void helper_be_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
     }
 
     /* If the TLB entry is for a different page, reload and try again.  */
-    if (!tlb_hit(tlb_addr, addr)) {
+    if ((addr & TARGET_PAGE_MASK)
+        != (tlb_addr & (TARGET_PAGE_MASK | TLB_INVALID_MASK))) {
         if (!VICTIM_TLB_HIT(addr_write, addr)) {
             tlb_fill(ENV_GET_CPU(env), addr, DATA_SIZE, MMU_DATA_STORE,
                      mmu_idx, retaddr);
@@ -378,8 +375,7 @@ void helper_be_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
         /* ??? Note that the io helpers always read data in the target
            byte ordering.  We should push the LE/BE request down into io.  */
         val = TGT_BE(val);
-        glue(io_write, SUFFIX)(env, mmu_idx, index, val, addr, retaddr,
-                               tlb_addr & TLB_RECHECK);
+        glue(io_write, SUFFIX)(env, mmu_idx, index, val, addr, retaddr);
         return;
     }
 
@@ -396,7 +392,7 @@ void helper_be_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val,
         page2 = (addr + DATA_SIZE) & TARGET_PAGE_MASK;
         index2 = (page2 >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
         tlb_addr2 = env->tlb_table[mmu_idx][index2].addr_write;
-        if (!tlb_hit_page(tlb_addr2, page2)
+        if (page2 != (tlb_addr2 & (TARGET_PAGE_MASK | TLB_INVALID_MASK))
             && !VICTIM_TLB_HIT(addr_write, page2)) {
             tlb_fill(ENV_GET_CPU(env), page2, DATA_SIZE, MMU_DATA_STORE,
                      mmu_idx, retaddr);

accel/tcg/tcg-runtime-gvec.c

@@ -705,7 +705,7 @@ void HELPER(NAME)(void *d, void *a, void *b, uint32_t desc)                \
 {                                                                          \
     intptr_t oprsz = simd_oprsz(desc);                                     \
     intptr_t i;                                                            \
-    for (i = 0; i < oprsz; i += sizeof(TYPE)) {                            \
+    for (i = 0; i < oprsz; i += sizeof(vec64)) {                           \
         *(TYPE *)(d + i) = DO_CMP0(*(TYPE *)(a + i) OP *(TYPE *)(b + i));  \
     }                                                                      \
     clear_high(d, oprsz, desc);                                            \

accel/tcg/tcg-runtime.h

@@ -125,19 +125,11 @@ GEN_ATOMIC_HELPERS(fetch_add)
 GEN_ATOMIC_HELPERS(fetch_and)
 GEN_ATOMIC_HELPERS(fetch_or)
 GEN_ATOMIC_HELPERS(fetch_xor)
-GEN_ATOMIC_HELPERS(fetch_smin)
-GEN_ATOMIC_HELPERS(fetch_umin)
-GEN_ATOMIC_HELPERS(fetch_smax)
-GEN_ATOMIC_HELPERS(fetch_umax)
 
 GEN_ATOMIC_HELPERS(add_fetch)
 GEN_ATOMIC_HELPERS(and_fetch)
 GEN_ATOMIC_HELPERS(or_fetch)
 GEN_ATOMIC_HELPERS(xor_fetch)
-GEN_ATOMIC_HELPERS(smin_fetch)
-GEN_ATOMIC_HELPERS(umin_fetch)
-GEN_ATOMIC_HELPERS(smax_fetch)
-GEN_ATOMIC_HELPERS(umax_fetch)
 
 GEN_ATOMIC_HELPERS(xchg)
 

accel/tcg/translate-all.h

@@ -23,13 +23,10 @@
 
 
 /* translate-all.c */
-struct page_collection *page_collection_lock(tb_page_addr_t start,
-                                             tb_page_addr_t end);
-void page_collection_unlock(struct page_collection *set);
-void tb_invalidate_phys_page_fast(struct page_collection *pages,
-                                  tb_page_addr_t start, int len);
+void tb_invalidate_phys_page_fast(tb_page_addr_t start, int len);
 void tb_invalidate_phys_page_range(tb_page_addr_t start, tb_page_addr_t end,
                                    int is_cpu_write_access);
+void tb_invalidate_phys_range(tb_page_addr_t start, tb_page_addr_t end);
 void tb_check_watchpoint(CPUState *cpu);
 
 #ifdef CONFIG_USER_ONLY

accel/tcg/translator.c

@@ -34,6 +34,8 @@ void translator_loop_temp_check(DisasContextBase *db)
 void translator_loop(const TranslatorOps *ops, DisasContextBase *db,
                      CPUState *cpu, TranslationBlock *tb)
 {
+    int max_insns;
+
     /* Initialize DisasContext */
     db->tb = tb;
     db->pc_first = tb->pc;
@@ -43,18 +45,18 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db,
     db->singlestep_enabled = cpu->singlestep_enabled;
 
     /* Instruction counting */
-    db->max_insns = tb_cflags(db->tb) & CF_COUNT_MASK;
-    if (db->max_insns == 0) {
-        db->max_insns = CF_COUNT_MASK;
+    max_insns = tb_cflags(db->tb) & CF_COUNT_MASK;
+    if (max_insns == 0) {
+        max_insns = CF_COUNT_MASK;
     }
-    if (db->max_insns > TCG_MAX_INSNS) {
-        db->max_insns = TCG_MAX_INSNS;
+    if (max_insns > TCG_MAX_INSNS) {
+        max_insns = TCG_MAX_INSNS;
     }
     if (db->singlestep_enabled || singlestep) {
-        db->max_insns = 1;
+        max_insns = 1;
     }
 
-    ops->init_disas_context(db, cpu);
+    max_insns = ops->init_disas_context(db, cpu, max_insns);
     tcg_debug_assert(db->is_jmp == DISAS_NEXT);  /* no early exit */
 
     /* Reset the temp count so that we can identify leaks */
@@ -93,8 +95,7 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db,
            update db->pc_next and db->is_jmp to indicate what should be
            done next -- either exiting this loop or locate the start of
            the next instruction.  */
-        if (db->num_insns == db->max_insns
-            && (tb_cflags(db->tb) & CF_LAST_IO)) {
+        if (db->num_insns == max_insns && (tb_cflags(db->tb) & CF_LAST_IO)) {
             /* Accept I/O on the last instruction.  */
             gen_io_start();
             ops->translate_insn(db, cpu);
@@ -110,7 +111,7 @@ void translator_loop(const TranslatorOps *ops, DisasContextBase *db,
 
         /* Stop translation if the output buffer is full,
            or we have executed all of the allowed instructions.  */
-        if (tcg_op_buf_full() || db->num_insns >= db->max_insns) {
+        if (tcg_op_buf_full() || db->num_insns >= max_insns) {
             db->is_jmp = DISAS_TOO_MANY;
             break;
         }

accel/tcg/user-exec-stub.c

@@ -2,9 +2,6 @@
 #include "qemu-common.h"
 #include "qom/cpu.h"
 #include "sysemu/replay.h"
-#include "sysemu/sysemu.h"
-
-bool enable_cpu_pm = false;
 
 void cpu_resume(CPUState *cpu)
 {

accel/tcg/user-exec.c

@@ -168,7 +168,7 @@ static inline int handle_cpu_signal(uintptr_t pc, siginfo_t *info,
     }
 
     /* Now we have a real cpu fault.  */
-    cpu_restore_state(cpu, pc, true);
+    cpu_restore_state(cpu, pc);
 
     sigprocmask(SIG_SETMASK, old_set, NULL);
     cpu_loop_exit(cpu);

arch_init.c

@@ -29,7 +29,6 @@
 #include "hw/pci/pci.h"
 #include "hw/audio/soundhw.h"
 #include "qapi/qapi-commands-misc.h"
-#include "qapi/error.h"
 #include "qemu/config-file.h"
 #include "qemu/error-report.h"
 #include "hw/acpi/acpi.h"
@@ -52,14 +51,14 @@ int graphic_depth = 32;
 #define QEMU_ARCH QEMU_ARCH_ARM
 #elif defined(TARGET_CRIS)
 #define QEMU_ARCH QEMU_ARCH_CRIS
-#elif defined(TARGET_HPPA)
-#define QEMU_ARCH QEMU_ARCH_HPPA
 #elif defined(TARGET_I386)
 #define QEMU_ARCH QEMU_ARCH_I386
-#elif defined(TARGET_LM32)
-#define QEMU_ARCH QEMU_ARCH_LM32
+#elif defined(TARGET_HPPA)
+#define QEMU_ARCH QEMU_ARCH_HPPA
 #elif defined(TARGET_M68K)
 #define QEMU_ARCH QEMU_ARCH_M68K
+#elif defined(TARGET_LM32)
+#define QEMU_ARCH QEMU_ARCH_LM32
 #elif defined(TARGET_MICROBLAZE)
 #define QEMU_ARCH QEMU_ARCH_MICROBLAZE
 #elif defined(TARGET_MIPS)
@@ -80,12 +79,12 @@ int graphic_depth = 32;
 #define QEMU_ARCH QEMU_ARCH_SH4
 #elif defined(TARGET_SPARC)
 #define QEMU_ARCH QEMU_ARCH_SPARC
-#elif defined(TARGET_TRICORE)
-#define QEMU_ARCH QEMU_ARCH_TRICORE
-#elif defined(TARGET_UNICORE32)
-#define QEMU_ARCH QEMU_ARCH_UNICORE32
 #elif defined(TARGET_XTENSA)
 #define QEMU_ARCH QEMU_ARCH_XTENSA
+#elif defined(TARGET_UNICORE32)
+#define QEMU_ARCH QEMU_ARCH_UNICORE32
+#elif defined(TARGET_TRICORE)
+#define QEMU_ARCH QEMU_ARCH_TRICORE
 #endif
 
 const uint32_t arch_type = QEMU_ARCH;
@@ -113,8 +112,7 @@ TargetInfo *qmp_query_target(Error **errp)
 {
     TargetInfo *info = g_malloc0(sizeof(*info));
 
-    info->arch = qapi_enum_parse(&SysEmuTarget_lookup, TARGET_NAME, -1,
-                                 &error_abort);
+    info->arch = g_strdup(TARGET_NAME);
 
     return info;
 }

audio/audio.c

@@ -29,7 +29,6 @@
 #include "sysemu/sysemu.h"
 #include "qemu/cutils.h"
 #include "sysemu/replay.h"
-#include "trace.h"
 
 #define AUDIO_CAP "audio"
 #include "audio_int.h"
@@ -336,8 +335,9 @@ static int audio_get_conf_int (const char *key, int defval, int *defaultp)
     char *strval;
 
     strval = getenv (key);
-    if (strval && !qemu_strtoi(strval, NULL, 10, &val)) {
+    if (strval) {
         *defaultp = 0;
+        val = atoi (strval);
         return val;
     }
     else {
@@ -1130,10 +1130,6 @@ static void audio_pcm_print_info (const char *cap, struct audio_pcm_info *info)
 /*
  * Timer
  */
-
-static bool audio_timer_running;
-static uint64_t audio_timer_last;
-
 static int audio_is_timer_needed (void)
 {
     HWVoiceIn *hwi = NULL;
@@ -1153,31 +1149,14 @@ static void audio_reset_timer (AudioState *s)
     if (audio_is_timer_needed ()) {
         timer_mod_anticipate_ns(s->ts,
             qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + conf.period.ticks);
-        if (!audio_timer_running) {
-            audio_timer_running = true;
-            audio_timer_last = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
-            trace_audio_timer_start(conf.period.ticks / SCALE_MS);
     }
-    } else {
+    else {
         timer_del (s->ts);
-        if (audio_timer_running) {
-            audio_timer_running = false;
-            trace_audio_timer_stop();
-        }
     }
 }
 
 static void audio_timer (void *opaque)
 {
-    int64_t now, diff;
-
-    now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
-    diff = now - audio_timer_last;
-    if (diff > conf.period.ticks * 3 / 2) {
-        trace_audio_timer_delayed(diff / SCALE_MS);
-    }
-    audio_timer_last = now;
-
     audio_run ("timer");
     audio_reset_timer (opaque);
 }

audio/trace-events

@@ -15,8 +15,3 @@ alsa_no_frames(int state) "No frames available and ALSA state is %d"
 # audio/ossaudio.c
 oss_version(int version) "OSS version = 0x%x"
 oss_invalid_available_size(int size, int bufsize) "Invalid available size, size=%d bufsize=%d"
-
-# audio/audio.c
-audio_timer_start(int interval) "interval %d ms"
-audio_timer_stop(void) ""
-audio_timer_delayed(int interval) "interval %d ms"

backends/cryptodev-vhost-user.c

@@ -26,7 +26,6 @@
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/error-report.h"
-#include "hw/virtio/vhost-user.h"
 #include "standard-headers/linux/virtio_crypto.h"
 #include "sysemu/cryptodev-vhost.h"
 #include "chardev/char-fe.h"
@@ -47,7 +46,6 @@
 typedef struct CryptoDevBackendVhostUser {
     CryptoDevBackend parent_obj;
 
-    VhostUserState *vhost_user;
     CharBackend chr;
     char *chr_name;
     bool opened;
@@ -104,7 +102,7 @@ cryptodev_vhost_user_start(int queues,
             continue;
         }
 
-        options.opaque = s->vhost_user;
+        options.opaque = &s->chr;
         options.backend_type = VHOST_BACKEND_TYPE_USER;
         options.cc = b->conf.peers.ccs[i];
         s->vhost_crypto[i] = cryptodev_vhost_init(&options);
@@ -187,7 +185,6 @@ static void cryptodev_vhost_user_init(
     size_t i;
     Error *local_err = NULL;
     Chardev *chr;
-    VhostUserState *user;
     CryptoDevBackendClient *cc;
     CryptoDevBackendVhostUser *s =
                       CRYPTODEV_BACKEND_VHOST_USER(backend);
@@ -218,15 +215,6 @@ static void cryptodev_vhost_user_init(
         }
     }
 
-    user = vhost_user_init();
-    if (!user) {
-        error_setg(errp, "Failed to init vhost_user");
-        return;
-    }
-
-    user->chr = &s->chr;
-    s->vhost_user = user;
-
     qemu_chr_fe_set_handlers(&s->chr, NULL, NULL,
                      cryptodev_vhost_user_event, NULL, s, NULL, true);
 
@@ -311,12 +299,6 @@ static void cryptodev_vhost_user_cleanup(
             backend->conf.peers.ccs[i] = NULL;
         }
     }
-
-    if (s->vhost_user) {
-        vhost_user_cleanup(s->vhost_user);
-        g_free(s->vhost_user);
-        s->vhost_user = NULL;
-    }
 }
 
 static void cryptodev_vhost_user_set_chardev(Object *obj,

backends/hostmem.c

@@ -18,7 +18,6 @@
 #include "qapi/visitor.h"
 #include "qemu/config-file.h"
 #include "qom/object_interfaces.h"
-#include "qemu/mmap-alloc.h"
 
 #ifdef CONFIG_NUMA
 #include <numaif.h>
@@ -247,7 +246,8 @@ bool host_memory_backend_mr_inited(HostMemoryBackend *backend)
     return memory_region_size(&backend->mr) != 0;
 }
 
-MemoryRegion *host_memory_backend_get_memory(HostMemoryBackend *backend)
+MemoryRegion *
+host_memory_backend_get_memory(HostMemoryBackend *backend, Error **errp)
 {
     return host_memory_backend_mr_inited(backend) ? &backend->mr : NULL;
 }
@@ -262,23 +262,6 @@ bool host_memory_backend_is_mapped(HostMemoryBackend *backend)
     return backend->is_mapped;
 }
 
-#ifdef __linux__
-size_t host_memory_backend_pagesize(HostMemoryBackend *memdev)
-{
-    Object *obj = OBJECT(memdev);
-    char *path = object_property_get_str(obj, "mem-path", NULL);
-    size_t pagesize = qemu_mempath_getpagesize(path);
-
-    g_free(path);
-    return pagesize;
-}
-#else
-size_t host_memory_backend_pagesize(HostMemoryBackend *memdev)
-{
-    return getpagesize();
-}
-#endif
-
 static void
 host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
 {
@@ -368,6 +351,24 @@ host_memory_backend_can_be_deleted(UserCreatable *uc)
     }
 }
 
+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 bool host_memory_backend_get_share(Object *o, Error **errp)
 {
     HostMemoryBackend *backend = MEMORY_BACKEND(o);
@@ -415,11 +416,18 @@ host_memory_backend_class_init(ObjectClass *oc, void *data)
         &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);
     object_class_property_add_bool(oc, "share",
         host_memory_backend_get_share, host_memory_backend_set_share,
         &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 = {
     .name = TYPE_MEMORY_BACKEND,
     .parent = TYPE_OBJECT,
@@ -428,6 +436,7 @@ 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 },
         { }

block.c

@@ -27,14 +27,12 @@
 #include "block/block_int.h"
 #include "block/blockjob.h"
 #include "block/nbd.h"
-#include "block/qdict.h"
 #include "qemu/error-report.h"
 #include "module_block.h"
 #include "qemu/module.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qjson.h"
-#include "qapi/qmp/qnull.h"
 #include "qapi/qmp/qstring.h"
 #include "qapi/qobject-output-visitor.h"
 #include "qapi/qapi-visit-block-core.h"
@@ -333,10 +331,6 @@ BlockDriverState *bdrv_new(void)
 
     qemu_co_queue_init(&bs->flush_queue);
 
-    for (i = 0; i < bdrv_drain_all_count; i++) {
-        bdrv_drained_begin(bs);
-    }
-
     QTAILQ_INSERT_TAIL(&all_bdrv_states, bs, bs_list);
 
     return bs;
@@ -725,7 +719,7 @@ static int find_image_format(BlockBackend *file, const char *filename,
  * Set the current 'total_sectors' value
  * Return 0 on success, -errno on error.
  */
-int refresh_total_sectors(BlockDriverState *bs, int64_t hint)
+static int refresh_total_sectors(BlockDriverState *bs, int64_t hint)
 {
     BlockDriver *drv = bs->drv;
 
@@ -822,13 +816,7 @@ static char *bdrv_child_get_parent_desc(BdrvChild *c)
 static void bdrv_child_cb_drained_begin(BdrvChild *child)
 {
     BlockDriverState *bs = child->opaque;
-    bdrv_do_drained_begin_quiesce(bs, NULL, false);
-}
-
-static bool bdrv_child_cb_drained_poll(BdrvChild *child)
-{
-    BlockDriverState *bs = child->opaque;
-    return bdrv_drain_poll(bs, false, NULL, false);
+    bdrv_drained_begin(bs);
 }
 
 static void bdrv_child_cb_drained_end(BdrvChild *child)
@@ -912,11 +900,9 @@ static void bdrv_inherited_options(int *child_flags, QDict *child_options,
 }
 
 const BdrvChildRole child_file = {
-    .parent_is_bds   = true,
     .get_parent_desc = bdrv_child_get_parent_desc,
     .inherit_options = bdrv_inherited_options,
     .drained_begin   = bdrv_child_cb_drained_begin,
-    .drained_poll    = bdrv_child_cb_drained_poll,
     .drained_end     = bdrv_child_cb_drained_end,
     .attach          = bdrv_child_cb_attach,
     .detach          = bdrv_child_cb_detach,
@@ -938,11 +924,9 @@ static void bdrv_inherited_fmt_options(int *child_flags, QDict *child_options,
 }
 
 const BdrvChildRole child_format = {
-    .parent_is_bds   = true,
     .get_parent_desc = bdrv_child_get_parent_desc,
     .inherit_options = bdrv_inherited_fmt_options,
     .drained_begin   = bdrv_child_cb_drained_begin,
-    .drained_poll    = bdrv_child_cb_drained_poll,
     .drained_end     = bdrv_child_cb_drained_end,
     .attach          = bdrv_child_cb_attach,
     .detach          = bdrv_child_cb_detach,
@@ -1057,13 +1041,11 @@ static int bdrv_backing_update_filename(BdrvChild *c, BlockDriverState *base,
 }
 
 const BdrvChildRole child_backing = {
-    .parent_is_bds   = true,
     .get_parent_desc = bdrv_child_get_parent_desc,
     .attach          = bdrv_backing_attach,
     .detach          = bdrv_backing_detach,
     .inherit_options = bdrv_backing_options,
     .drained_begin   = bdrv_child_cb_drained_begin,
-    .drained_poll    = bdrv_child_cb_drained_poll,
     .drained_end     = bdrv_child_cb_drained_end,
     .inactivate      = bdrv_child_cb_inactivate,
     .update_filename = bdrv_backing_update_filename,
@@ -1156,12 +1138,6 @@ static void bdrv_assign_node_name(BlockDriverState *bs,
         goto out;
     }
 
-    /* Make sure that the node name isn't truncated */
-    if (strlen(node_name) >= sizeof(bs->node_name)) {
-        error_setg(errp, "Node name too long");
-        goto out;
-    }
-
     /* copy node name into the bs and insert it into the graph list */
     pstrcpy(bs->node_name, sizeof(bs->node_name), node_name);
     QTAILQ_INSERT_TAIL(&graph_bdrv_states, bs, node_list);
@@ -1174,7 +1150,7 @@ static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv,
                             int open_flags, Error **errp)
 {
     Error *local_err = NULL;
-    int i, ret;
+    int ret;
 
     bdrv_assign_node_name(bs, node_name, &local_err);
     if (local_err) {
@@ -1222,12 +1198,6 @@ static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv,
     assert(bdrv_min_mem_align(bs) != 0);
     assert(is_power_of_2(bs->bl.request_alignment));
 
-    for (i = 0; i < bs->quiesce_counter; i++) {
-        if (drv->bdrv_co_drain_begin) {
-            drv->bdrv_co_drain_begin(bs);
-        }
-    }
-
     return 0;
 open_failed:
     bs->drv = NULL;
@@ -1256,9 +1226,9 @@ BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name,
 
     ret = bdrv_open_driver(bs, drv, node_name, bs->options, flags, errp);
     if (ret < 0) {
-        qobject_unref(bs->explicit_options);
+        QDECREF(bs->explicit_options);
         bs->explicit_options = NULL;
-        qobject_unref(bs->options);
+        QDECREF(bs->options);
         bs->options = NULL;
         bdrv_unref(bs);
         return NULL;
@@ -1487,9 +1457,9 @@ static QDict *parse_json_filename(const char *filename, Error **errp)
         return NULL;
     }
 
-    options = qobject_to(QDict, options_obj);
+    options = qobject_to_qdict(options_obj);
     if (!options) {
-        qobject_unref(options_obj);
+        qobject_decref(options_obj);
         error_setg(errp, "Invalid JSON object given");
         return NULL;
     }
@@ -1519,7 +1489,7 @@ static void parse_json_protocol(QDict *options, const char **pfilename,
     /* Options given in the filename have lower priority than options
      * specified directly */
     qdict_join(options, json_options, false);
-    qobject_unref(json_options);
+    QDECREF(json_options);
     *pfilename = NULL;
 }
 
@@ -1649,24 +1619,13 @@ static int bdrv_reopen_get_flags(BlockReopenQueue *q, BlockDriverState *bs)
 
 /* Returns whether the image file can be written to after the reopen queue @q
  * has been successfully applied, or right now if @q is NULL. */
-static bool bdrv_is_writable_after_reopen(BlockDriverState *bs,
-                                          BlockReopenQueue *q)
+static bool bdrv_is_writable(BlockDriverState *bs, BlockReopenQueue *q)
 {
     int flags = bdrv_reopen_get_flags(q, bs);
 
     return (flags & (BDRV_O_RDWR | BDRV_O_INACTIVE)) == BDRV_O_RDWR;
 }
 
-/*
- * Return whether the BDS can be written to.  This is not necessarily
- * the same as !bdrv_is_read_only(bs), as inactivated images may not
- * be written to but do not count as read-only images.
- */
-bool bdrv_is_writable(BlockDriverState *bs)
-{
-    return bdrv_is_writable_after_reopen(bs, NULL);
-}
-
 static void bdrv_child_perm(BlockDriverState *bs, BlockDriverState *child_bs,
                             BdrvChild *c, const BdrvChildRole *role,
                             BlockReopenQueue *reopen_queue,
@@ -1704,7 +1663,7 @@ static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q,
 
     /* Write permissions never work with read-only images */
     if ((cumulative_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) &&
-        !bdrv_is_writable_after_reopen(bs, q))
+        !bdrv_is_writable(bs, q))
     {
         error_setg(errp, "Block node is read-only");
         return -EPERM;
@@ -1954,6 +1913,12 @@ int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
     return 0;
 }
 
+#define DEFAULT_PERM_PASSTHROUGH (BLK_PERM_CONSISTENT_READ \
+                                 | BLK_PERM_WRITE \
+                                 | BLK_PERM_WRITE_UNCHANGED \
+                                 | BLK_PERM_RESIZE)
+#define DEFAULT_PERM_UNCHANGED (BLK_PERM_ALL & ~DEFAULT_PERM_PASSTHROUGH)
+
 void bdrv_filter_default_perms(BlockDriverState *bs, BdrvChild *c,
                                const BdrvChildRole *role,
                                BlockReopenQueue *reopen_queue,
@@ -1990,7 +1955,7 @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c,
                                   &perm, &shared);
 
         /* Format drivers may touch metadata even if the guest doesn't write */
-        if (bdrv_is_writable_after_reopen(bs, reopen_queue)) {
+        if (bdrv_is_writable(bs, reopen_queue)) {
             perm |= BLK_PERM_WRITE | BLK_PERM_RESIZE;
         }
 
@@ -2043,12 +2008,7 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
             child->role->detach(child);
         }
         if (old_bs->quiesce_counter && child->role->drained_end) {
-            int num = old_bs->quiesce_counter;
-            if (child->role->parent_is_bds) {
-                num -= bdrv_drain_all_count;
-            }
-            assert(num >= 0);
-            for (i = 0; i < num; i++) {
+            for (i = 0; i < old_bs->quiesce_counter; i++) {
                 child->role->drained_end(child);
             }
         }
@@ -2060,13 +2020,8 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
     if (new_bs) {
         QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent);
         if (new_bs->quiesce_counter && child->role->drained_begin) {
-            int num = new_bs->quiesce_counter;
-            if (child->role->parent_is_bds) {
-                num -= bdrv_drain_all_count;
-            }
-            assert(num >= 0);
-            for (i = 0; i < num; i++) {
-                bdrv_parent_drained_begin_single(child, true);
+            for (i = 0; i < new_bs->quiesce_counter; i++) {
+                child->role->drained_begin(child);
             }
         }
 
@@ -2226,6 +2181,16 @@ static void bdrv_parent_cb_change_media(BlockDriverState *bs, bool load)
     }
 }
 
+static void bdrv_parent_cb_resize(BlockDriverState *bs)
+{
+    BdrvChild *c;
+    QLIST_FOREACH(c, &bs->parents, next_parent) {
+        if (c->role->resize) {
+            c->role->resize(c);
+        }
+    }
+}
+
 /*
  * Sets the backing file link of a BDS. A new reference is created; callers
  * which don't need their own reference any more must call bdrv_unref().
@@ -2307,7 +2272,7 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
     if (reference || qdict_haskey(options, "file.filename")) {
         backing_filename[0] = '\0';
     } else if (bs->backing_file[0] == '\0' && qdict_size(options) == 0) {
-        qobject_unref(options);
+        QDECREF(options);
         goto free_exit;
     } else {
         bdrv_get_full_backing_filename(bs, backing_filename, PATH_MAX,
@@ -2315,7 +2280,7 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
         if (local_err) {
             ret = -EINVAL;
             error_propagate(errp, local_err);
-            qobject_unref(options);
+            QDECREF(options);
             goto free_exit;
         }
     }
@@ -2323,7 +2288,7 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
     if (!bs->drv || !bs->drv->supports_backing) {
         ret = -EINVAL;
         error_setg(errp, "Driver doesn't support backing files");
-        qobject_unref(options);
+        QDECREF(options);
         goto free_exit;
     }
 
@@ -2357,7 +2322,7 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
 
 free_exit:
     g_free(backing_filename);
-    qobject_unref(tmp_parent_options);
+    QDECREF(tmp_parent_options);
     return ret;
 }
 
@@ -2390,7 +2355,7 @@ bdrv_open_child_bs(const char *filename, QDict *options, const char *bdref_key,
             error_setg(errp, "A block device must be specified for \"%s\"",
                        bdref_key);
         }
-        qobject_unref(image_options);
+        QDECREF(image_options);
         goto done;
     }
 
@@ -2468,7 +2433,7 @@ BlockDriverState *bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp)
         }
         visit_complete(v, &obj);
 
-        qdict = qobject_to(QDict, obj);
+        qdict = qobject_to_qdict(obj);
         qdict_flatten(qdict);
 
         /* bdrv_open_inherit() defaults to the values in bdrv_flags (for
@@ -2483,7 +2448,7 @@ BlockDriverState *bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp)
     obj = NULL;
 
 fail:
-    qobject_unref(obj);
+    qobject_decref(obj);
     visit_free(v);
     return bs;
 }
@@ -2553,7 +2518,7 @@ static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
     }
 
 out:
-    qobject_unref(snapshot_options);
+    QDECREF(snapshot_options);
     g_free(tmp_filename);
     return bs_snapshot;
 }
@@ -2564,7 +2529,7 @@ out:
  * options is a QDict of options to pass to the block drivers, or NULL for an
  * empty set of options. The reference to the QDict belongs to the block layer
  * after the call (even on failure), so if the caller intends to reuse the
- * dictionary, it needs to use qobject_ref() before calling bdrv_open.
+ * dictionary, it needs to use QINCREF() before calling bdrv_open.
  *
  * If *pbs is NULL, a new BDS will be created with a pointer to it stored there.
  * If it is not NULL, the referenced BDS will be reused.
@@ -2595,7 +2560,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
 
     if (reference) {
         bool options_non_empty = options ? qdict_size(options) : false;
-        qobject_unref(options);
+        QDECREF(options);
 
         if (filename || options_non_empty) {
             error_setg(errp, "Cannot reference an existing block device with "
@@ -2680,13 +2645,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
 
     /* See cautionary note on accessing @options above */
     backing = qdict_get_try_str(options, "backing");
-    if (qobject_to(QNull, qdict_get(options, "backing")) != NULL ||
-        (backing && *backing == '\0'))
-    {
-        if (backing) {
-            warn_report("Use of \"backing\": \"\" is deprecated; "
-                        "use \"backing\": null instead");
-        }
+    if (backing && *backing == '\0') {
         flags |= BDRV_O_NO_BACKING;
         qdict_del(options, "backing");
     }
@@ -2786,7 +2745,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
 
     bdrv_parent_cb_change_media(bs, true);
 
-    qobject_unref(options);
+    QDECREF(options);
 
     /* For snapshot=on, create a temporary qcow2 overlay. bs points to the
      * temporary snapshot afterwards. */
@@ -2810,10 +2769,10 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
 
 fail:
     blk_unref(file);
-    qobject_unref(snapshot_options);
-    qobject_unref(bs->explicit_options);
-    qobject_unref(bs->options);
-    qobject_unref(options);
+    QDECREF(snapshot_options);
+    QDECREF(bs->explicit_options);
+    QDECREF(bs->options);
+    QDECREF(options);
     bs->options = NULL;
     bs->explicit_options = NULL;
     bdrv_unref(bs);
@@ -2822,8 +2781,8 @@ fail:
 
 close_and_fail:
     bdrv_unref(bs);
-    qobject_unref(snapshot_options);
-    qobject_unref(options);
+    QDECREF(snapshot_options);
+    QDECREF(options);
     error_propagate(errp, local_err);
     return NULL;
 }
@@ -2918,28 +2877,20 @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
         old_options = qdict_clone_shallow(bs->explicit_options);
     }
     bdrv_join_options(bs, options, old_options);
-    qobject_unref(old_options);
+    QDECREF(old_options);
 
     explicit_options = qdict_clone_shallow(options);
 
     /* Inherit from parent node */
     if (parent_options) {
-        QemuOpts *opts;
-        QDict *options_copy;
         assert(!flags);
         role->inherit_options(&flags, options, parent_flags, parent_options);
-        options_copy = qdict_clone_shallow(options);
-        opts = qemu_opts_create(&bdrv_runtime_opts, NULL, 0, &error_abort);
-        qemu_opts_absorb_qdict(opts, options_copy, NULL);
-        update_flags_from_options(&flags, opts);
-        qemu_opts_del(opts);
-        qobject_unref(options_copy);
     }
 
     /* Old values are used for options that aren't set yet */
     old_options = qdict_clone_shallow(bs->options);
     bdrv_join_options(bs, options, old_options);
-    qobject_unref(old_options);
+    QDECREF(old_options);
 
     /* bdrv_open_inherit() sets and clears some additional flags internally */
     flags &= ~BDRV_O_PROTOCOL;
@@ -2951,8 +2902,8 @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
         bs_entry = g_new0(BlockReopenQueueEntry, 1);
         QSIMPLEQ_INSERT_TAIL(bs_queue, bs_entry, entry);
     } else {
-        qobject_unref(bs_entry->state.options);
-        qobject_unref(bs_entry->state.explicit_options);
+        QDECREF(bs_entry->state.options);
+        QDECREF(bs_entry->state.explicit_options);
     }
 
     bs_entry->state.bs = bs;
@@ -3042,9 +2993,9 @@ cleanup:
         if (ret && bs_entry->prepared) {
             bdrv_reopen_abort(&bs_entry->state);
         } else if (ret) {
-            qobject_unref(bs_entry->state.explicit_options);
+            QDECREF(bs_entry->state.explicit_options);
         }
-        qobject_unref(bs_entry->state.options);
+        QDECREF(bs_entry->state.options);
         g_free(bs_entry);
     }
     g_free(bs_queue);
@@ -3287,7 +3238,7 @@ void bdrv_reopen_commit(BDRVReopenState *reopen_state)
     }
 
     /* set BDS specific flags now */
-    qobject_unref(bs->explicit_options);
+    QDECREF(bs->explicit_options);
 
     bs->explicit_options   = reopen_state->explicit_options;
     bs->open_flags         = reopen_state->flags;
@@ -3330,7 +3281,7 @@ void bdrv_reopen_abort(BDRVReopenState *reopen_state)
         drv->bdrv_reopen_abort(reopen_state);
     }
 
-    qobject_unref(reopen_state->explicit_options);
+    QDECREF(reopen_state->explicit_options);
 
     bdrv_abort_perm_update(reopen_state->bs);
 }
@@ -3377,11 +3328,11 @@ static void bdrv_close(BlockDriverState *bs)
     bs->total_sectors = 0;
     bs->encrypted = false;
     bs->sg = false;
-    qobject_unref(bs->options);
-    qobject_unref(bs->explicit_options);
+    QDECREF(bs->options);
+    QDECREF(bs->explicit_options);
     bs->options = NULL;
     bs->explicit_options = NULL;
-    qobject_unref(bs->full_open_options);
+    QDECREF(bs->full_open_options);
     bs->full_open_options = NULL;
 
     bdrv_release_named_dirty_bitmaps(bs);
@@ -3396,7 +3347,7 @@ static void bdrv_close(BlockDriverState *bs)
 
 void bdrv_close_all(void)
 {
-    assert(job_next(NULL) == NULL);
+    block_job_cancel_sync_all();
     nbd_export_close_all();
 
     /* Drop references from requests still in flight, such as canceled block
@@ -3417,39 +3368,16 @@ static bool should_update_child(BdrvChild *c, BlockDriverState *to)
         return false;
     }
 
-    /* If the child @c belongs to the BDS @to, replacing the current
-     * c->bs by @to would mean to create a loop.
-     *
-     * Such a case occurs when appending a BDS to a backing chain.
-     * For instance, imagine the following chain:
-     *
-     *   guest device -> node A -> further backing chain...
-     *
-     * Now we create a new BDS B which we want to put on top of this
-     * chain, so we first attach A as its backing node:
-     *
-     *                   node B
-     *                     |
-     *                     v
-     *   guest device -> node A -> further backing chain...
-     *
-     * Finally we want to replace A by B.  When doing that, we want to
-     * replace all pointers to A by pointers to B -- except for the
-     * pointer from B because (1) that would create a loop, and (2)
-     * that pointer should simply stay intact:
-     *
-     *   guest device -> node B
-     *                     |
-     *                     v
-     *                   node A -> further backing chain...
-     *
-     * In general, when replacing a node A (c->bs) by a node B (@to),
-     * if A is a child of B, that means we cannot replace A by B there
-     * because that would create a loop.  Silently detaching A from B
-     * is also not really an option.  So overall just leaving A in
-     * place there is the most sensible choice. */
+    if (c->role == &child_backing) {
+        /* If @from is a backing file of @to, ignore the child to avoid
+         * creating a loop. We only want to change the pointer of other
+         * parents. */
         QLIST_FOREACH(to_c, &to->children, next) {
             if (to_c == c) {
+                break;
+            }
+        }
+        if (to_c) {
             return false;
         }
     }
@@ -3475,7 +3403,6 @@ void bdrv_replace_node(BlockDriverState *from, BlockDriverState *to,
 
     /* Put all parents into @list and calculate their cumulative permissions */
     QLIST_FOREACH_SAFE(c, &from->parents, next_parent, next) {
-        assert(c->bs == from);
         if (!should_update_child(c, to)) {
             continue;
         }
@@ -3744,12 +3671,12 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base,
         GSList *ignore_children = g_slist_prepend(NULL, c);
         bdrv_check_update_perm(base, NULL, c->perm, c->shared_perm,
                                ignore_children, &local_err);
-        g_slist_free(ignore_children);
         if (local_err) {
             ret = -EPERM;
             error_report_err(local_err);
             goto exit;
         }
+        g_slist_free(ignore_children);
 
         /* If so, update the backing file path in the image file */
         if (c->role->update_filename) {
@@ -3775,6 +3702,58 @@ exit:
     return ret;
 }
 
+/**
+ * Truncate file to 'offset' bytes (needed only for file protocols)
+ */
+int bdrv_truncate(BdrvChild *child, int64_t offset, PreallocMode prealloc,
+                  Error **errp)
+{
+    BlockDriverState *bs = child->bs;
+    BlockDriver *drv = bs->drv;
+    int ret;
+
+    assert(child->perm & BLK_PERM_RESIZE);
+
+    /* if bs->drv == NULL, bs is closed, so there's nothing to do here */
+    if (!drv) {
+        error_setg(errp, "No medium inserted");
+        return -ENOMEDIUM;
+    }
+    if (offset < 0) {
+        error_setg(errp, "Image size cannot be negative");
+        return -EINVAL;
+    }
+
+    if (!drv->bdrv_truncate) {
+        if (bs->file && drv->is_filter) {
+            return bdrv_truncate(bs->file, offset, prealloc, errp);
+        }
+        error_setg(errp, "Image format driver does not support resize");
+        return -ENOTSUP;
+    }
+    if (bs->read_only) {
+        error_setg(errp, "Image is read-only");
+        return -EACCES;
+    }
+
+    assert(!(bs->open_flags & BDRV_O_INACTIVE));
+
+    ret = drv->bdrv_truncate(bs, offset, prealloc, errp);
+    if (ret < 0) {
+        return ret;
+    }
+    ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Could not refresh total sector count");
+    } else {
+        offset = bs->total_sectors * BDRV_SECTOR_SIZE;
+    }
+    bdrv_dirty_bitmap_truncate(bs, offset);
+    bdrv_parent_cb_resize(bs);
+    atomic_inc(&bs->write_gen);
+    return ret;
+}
+
 /**
  * Length of a allocated file in bytes. Sparse files are counted by actual
  * allocated space. Return < 0 if error or unknown.
@@ -4031,14 +4010,6 @@ BlockDriverState *bdrv_next_node(BlockDriverState *bs)
     return QTAILQ_NEXT(bs, node_list);
 }
 
-BlockDriverState *bdrv_next_all_states(BlockDriverState *bs)
-{
-    if (!bs) {
-        return QTAILQ_FIRST(&all_bdrv_states);
-    }
-    return QTAILQ_NEXT(bs, bs_list);
-}
-
 const char *bdrv_get_node_name(const BlockDriverState *bs)
 {
     return bs->node_name;
@@ -4950,7 +4921,7 @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context)
     AioContext *ctx = bdrv_get_aio_context(bs);
 
     aio_disable_external(ctx);
-    bdrv_parent_drained_begin(bs, NULL, false);
+    bdrv_parent_drained_begin(bs, NULL);
     bdrv_drain(bs); /* ensure there are no in-flight requests */
 
     while (aio_poll(ctx, false)) {
@@ -4964,7 +4935,7 @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context)
      */
     aio_context_acquire(new_context);
     bdrv_attach_aio_context(bs, new_context);
-    bdrv_parent_drained_end(bs, NULL, false);
+    bdrv_parent_drained_end(bs, NULL);
     aio_enable_external(ctx);
     aio_context_release(new_context);
 }
@@ -5010,19 +4981,15 @@ void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
 }
 
 int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts,
-                       BlockDriverAmendStatusCB *status_cb, void *cb_opaque,
-                       Error **errp)
+                       BlockDriverAmendStatusCB *status_cb, void *cb_opaque)
 {
     if (!bs->drv) {
-        error_setg(errp, "Node is ejected");
         return -ENOMEDIUM;
     }
     if (!bs->drv->bdrv_amend_options) {
-        error_setg(errp, "Block driver '%s' does not support option amendment",
-                   bs->drv->format_name);
         return -ENOTSUP;
     }
-    return bs->drv->bdrv_amend_options(bs, opts, status_cb, cb_opaque, errp);
+    return bs->drv->bdrv_amend_options(bs, opts, status_cb, cb_opaque);
 }
 
 /* This function will be called by the bdrv_recurse_is_first_non_filter method
@@ -5152,8 +5119,8 @@ static bool append_open_options(QDict *d, BlockDriverState *bs)
             continue;
         }
 
-        qdict_put_obj(d, qdict_entry_key(entry),
-                      qobject_ref(qdict_entry_value(entry)));
+        qobject_incref(qdict_entry_value(entry));
+        qdict_put_obj(d, qdict_entry_key(entry), qdict_entry_value(entry));
         found_any = true;
     }
 
@@ -5192,21 +5159,21 @@ void bdrv_refresh_filename(BlockDriverState *bs)
          * information before refreshing it */
         bs->exact_filename[0] = '\0';
         if (bs->full_open_options) {
-            qobject_unref(bs->full_open_options);
+            QDECREF(bs->full_open_options);
             bs->full_open_options = NULL;
         }
 
         opts = qdict_new();
         append_open_options(opts, bs);
         drv->bdrv_refresh_filename(bs, opts);
-        qobject_unref(opts);
+        QDECREF(opts);
     } else if (bs->file) {
         /* Try to reconstruct valid information from the underlying file */
         bool has_open_options;
 
         bs->exact_filename[0] = '\0';
         if (bs->full_open_options) {
-            qobject_unref(bs->full_open_options);
+            QDECREF(bs->full_open_options);
             bs->full_open_options = NULL;
         }
 
@@ -5225,12 +5192,12 @@ void bdrv_refresh_filename(BlockDriverState *bs)
          * suffices without querying the (exact_)filename of this BDS. */
         if (bs->file->bs->full_open_options) {
             qdict_put_str(opts, "driver", drv->format_name);
-            qdict_put(opts, "file",
-                      qobject_ref(bs->file->bs->full_open_options));
+            QINCREF(bs->file->bs->full_open_options);
+            qdict_put(opts, "file", bs->file->bs->full_open_options);
 
             bs->full_open_options = opts;
         } else {
-            qobject_unref(opts);
+            QDECREF(opts);
         }
     } else if (!bs->full_open_options && qdict_size(bs->options)) {
         /* There is no underlying file BDS (at least referenced by BDS.file),
@@ -5264,7 +5231,7 @@ void bdrv_refresh_filename(BlockDriverState *bs)
         QString *json = qobject_to_json(QOBJECT(bs->full_open_options));
         snprintf(bs->filename, sizeof(bs->filename), "json:%s",
                  qstring_get_str(json));
-        qobject_unref(json);
+        QDECREF(json);
     }
 }
 

block/Makefile.objs

@@ -5,7 +5,6 @@ block-obj-y += qed-check.o
 block-obj-y += 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 += blklogwrites.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
@@ -27,7 +26,7 @@ block-obj-y += accounting.o dirty-bitmap.o
 block-obj-y += write-threshold.o
 block-obj-y += backup.o
 block-obj-$(CONFIG_REPLICATION) += replication.o
-block-obj-y += throttle.o copy-on-read.o
+block-obj-y += throttle.o
 
 block-obj-y += crypto.o
 

block/accounting.c

@@ -94,94 +94,6 @@ void block_acct_start(BlockAcctStats *stats, BlockAcctCookie *cookie,
     cookie->type = type;
 }
 
-/* block_latency_histogram_compare_func:
- * Compare @key with interval [@it[0], @it[1]).
- * Return: -1 if @key < @it[0]
- *          0 if @key in [@it[0], @it[1])
- *         +1 if @key >= @it[1]
- */
-static int block_latency_histogram_compare_func(const void *key, const void *it)
-{
-    uint64_t k = *(uint64_t *)key;
-    uint64_t a = ((uint64_t *)it)[0];
-    uint64_t b = ((uint64_t *)it)[1];
-
-    return k < a ? -1 : (k < b ? 0 : 1);
-}
-
-static void block_latency_histogram_account(BlockLatencyHistogram *hist,
-                                            int64_t latency_ns)
-{
-    uint64_t *pos;
-
-    if (hist->bins == NULL) {
-        /* histogram disabled */
-        return;
-    }
-
-
-    if (latency_ns < hist->boundaries[0]) {
-        hist->bins[0]++;
-        return;
-    }
-
-    if (latency_ns >= hist->boundaries[hist->nbins - 2]) {
-        hist->bins[hist->nbins - 1]++;
-        return;
-    }
-
-    pos = bsearch(&latency_ns, hist->boundaries, hist->nbins - 2,
-                  sizeof(hist->boundaries[0]),
-                  block_latency_histogram_compare_func);
-    assert(pos != NULL);
-
-    hist->bins[pos - hist->boundaries + 1]++;
-}
-
-int block_latency_histogram_set(BlockAcctStats *stats, enum BlockAcctType type,
-                                uint64List *boundaries)
-{
-    BlockLatencyHistogram *hist = &stats->latency_histogram[type];
-    uint64List *entry;
-    uint64_t *ptr;
-    uint64_t prev = 0;
-    int new_nbins = 1;
-
-    for (entry = boundaries; entry; entry = entry->next) {
-        if (entry->value <= prev) {
-            return -EINVAL;
-        }
-        new_nbins++;
-        prev = entry->value;
-    }
-
-    hist->nbins = new_nbins;
-    g_free(hist->boundaries);
-    hist->boundaries = g_new(uint64_t, hist->nbins - 1);
-    for (entry = boundaries, ptr = hist->boundaries; entry;
-         entry = entry->next, ptr++)
-    {
-        *ptr = entry->value;
-    }
-
-    g_free(hist->bins);
-    hist->bins = g_new0(uint64_t, hist->nbins);
-
-    return 0;
-}
-
-void block_latency_histograms_clear(BlockAcctStats *stats)
-{
-    int i;
-
-    for (i = 0; i < BLOCK_MAX_IOTYPE; i++) {
-        BlockLatencyHistogram *hist = &stats->latency_histogram[i];
-        g_free(hist->bins);
-        g_free(hist->boundaries);
-        memset(hist, 0, sizeof(*hist));
-    }
-}
-
 static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,
                                  bool failed)
 {
@@ -204,9 +116,6 @@ static void block_account_one_io(BlockAcctStats *stats, BlockAcctCookie *cookie,
         stats->nr_ops[cookie->type]++;
     }
 
-    block_latency_histogram_account(&stats->latency_histogram[cookie->type],
-                                    latency_ns);
-
     if (!failed || stats->account_failed) {
         stats->total_time_ns[cookie->type] += latency_ns;
         stats->last_access_time_ns = time_ns;

block/backup.c

@@ -27,6 +27,7 @@
 #include "qemu/error-report.h"
 
 #define BACKUP_CLUSTER_SIZE_DEFAULT (1 << 16)
+#define SLICE_TIME 100000000ULL /* ns */
 
 typedef struct BackupBlockJob {
     BlockJob common;
@@ -34,10 +35,10 @@ typedef struct BackupBlockJob {
     /* bitmap for sync=incremental */
     BdrvDirtyBitmap *sync_bitmap;
     MirrorSyncMode sync_mode;
+    RateLimit limit;
     BlockdevOnError on_source_error;
     BlockdevOnError on_target_error;
     CoRwlock flush_rwlock;
-    uint64_t len;
     uint64_t bytes_read;
     int64_t cluster_size;
     bool compress;
@@ -45,14 +46,8 @@ typedef struct BackupBlockJob {
     QLIST_HEAD(, CowRequest) inflight_reqs;
 
     HBitmap *copy_bitmap;
-    bool use_copy_range;
-    int64_t copy_range_size;
-
-    bool serialize_target_writes;
 } BackupBlockJob;
 
-static const BlockJobDriver backup_job_driver;
-
 /* 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,
@@ -90,104 +85,19 @@ static void cow_request_end(CowRequest *req)
     qemu_co_queue_restart_all(&req->wait_queue);
 }
 
-/* Copy range to target with a bounce buffer and return the bytes copied. If
- * error occured, return a negative error number */
-static int coroutine_fn backup_cow_with_bounce_buffer(BackupBlockJob *job,
-                                                      int64_t start,
-                                                      int64_t end,
-                                                      bool is_write_notifier,
-                                                      bool *error_is_read,
-                                                      void **bounce_buffer)
-{
-    int ret;
-    struct iovec iov;
-    QEMUIOVector qiov;
-    BlockBackend *blk = job->common.blk;
-    int nbytes;
-    int read_flags = is_write_notifier ? BDRV_REQ_NO_SERIALISING : 0;
-    int write_flags = job->serialize_target_writes ? BDRV_REQ_SERIALISING : 0;
-
-    hbitmap_reset(job->copy_bitmap, start / job->cluster_size, 1);
-    nbytes = MIN(job->cluster_size, job->len - start);
-    if (!*bounce_buffer) {
-        *bounce_buffer = blk_blockalign(blk, job->cluster_size);
-    }
-    iov.iov_base = *bounce_buffer;
-    iov.iov_len = nbytes;
-    qemu_iovec_init_external(&qiov, &iov, 1);
-
-    ret = blk_co_preadv(blk, start, qiov.size, &qiov, read_flags);
-    if (ret < 0) {
-        trace_backup_do_cow_read_fail(job, start, ret);
-        if (error_is_read) {
-            *error_is_read = true;
-        }
-        goto fail;
-    }
-
-    if (qemu_iovec_is_zero(&qiov)) {
-        ret = blk_co_pwrite_zeroes(job->target, start,
-                                   qiov.size, write_flags | BDRV_REQ_MAY_UNMAP);
-    } else {
-        ret = blk_co_pwritev(job->target, start,
-                             qiov.size, &qiov, write_flags |
-                             (job->compress ? BDRV_REQ_WRITE_COMPRESSED : 0));
-    }
-    if (ret < 0) {
-        trace_backup_do_cow_write_fail(job, start, ret);
-        if (error_is_read) {
-            *error_is_read = false;
-        }
-        goto fail;
-    }
-
-    return nbytes;
-fail:
-    hbitmap_set(job->copy_bitmap, start / job->cluster_size, 1);
-    return ret;
-
-}
-
-/* Copy range to target and return the bytes copied. If error occured, return a
- * negative error number. */
-static int coroutine_fn backup_cow_with_offload(BackupBlockJob *job,
-                                                int64_t start,
-                                                int64_t end,
-                                                bool is_write_notifier)
-{
-    int ret;
-    int nr_clusters;
-    BlockBackend *blk = job->common.blk;
-    int nbytes;
-    int read_flags = is_write_notifier ? BDRV_REQ_NO_SERIALISING : 0;
-    int write_flags = job->serialize_target_writes ? BDRV_REQ_SERIALISING : 0;
-
-    assert(QEMU_IS_ALIGNED(job->copy_range_size, job->cluster_size));
-    nbytes = MIN(job->copy_range_size, end - start);
-    nr_clusters = DIV_ROUND_UP(nbytes, job->cluster_size);
-    hbitmap_reset(job->copy_bitmap, start / job->cluster_size,
-                  nr_clusters);
-    ret = blk_co_copy_range(blk, start, job->target, start, nbytes,
-                            read_flags, write_flags);
-    if (ret < 0) {
-        trace_backup_do_cow_copy_range_fail(job, start, ret);
-        hbitmap_set(job->copy_bitmap, start / job->cluster_size,
-                    nr_clusters);
-        return ret;
-    }
-
-    return nbytes;
-}
-
 static int coroutine_fn backup_do_cow(BackupBlockJob *job,
                                       int64_t offset, uint64_t bytes,
                                       bool *error_is_read,
                                       bool is_write_notifier)
 {
+    BlockBackend *blk = job->common.blk;
     CowRequest cow_request;
+    struct iovec iov;
+    QEMUIOVector bounce_qiov;
+    void *bounce_buffer = NULL;
     int ret = 0;
     int64_t start, end; /* bytes */
-    void *bounce_buffer = NULL;
+    int n; /* bytes */
 
     qemu_co_rwlock_rdlock(&job->flush_rwlock);
 
@@ -199,38 +109,60 @@ static int coroutine_fn backup_do_cow(BackupBlockJob *job,
     wait_for_overlapping_requests(job, start, end);
     cow_request_begin(&cow_request, job, start, end);
 
-    while (start < end) {
+    for (; start < end; start += job->cluster_size) {
         if (!hbitmap_get(job->copy_bitmap, start / job->cluster_size)) {
             trace_backup_do_cow_skip(job, start);
-            start += job->cluster_size;
             continue; /* already copied */
         }
+        hbitmap_reset(job->copy_bitmap, start / job->cluster_size, 1);
 
         trace_backup_do_cow_process(job, start);
 
-        if (job->use_copy_range) {
-            ret = backup_cow_with_offload(job, start, end, is_write_notifier);
+        n = MIN(job->cluster_size, job->common.len - start);
+
+        if (!bounce_buffer) {
+            bounce_buffer = blk_blockalign(blk, job->cluster_size);
+        }
+        iov.iov_base = bounce_buffer;
+        iov.iov_len = n;
+        qemu_iovec_init_external(&bounce_qiov, &iov, 1);
+
+        ret = blk_co_preadv(blk, start, bounce_qiov.size, &bounce_qiov,
+                            is_write_notifier ? BDRV_REQ_NO_SERIALISING : 0);
         if (ret < 0) {
-                job->use_copy_range = false;
+            trace_backup_do_cow_read_fail(job, start, ret);
+            if (error_is_read) {
+                *error_is_read = true;
             }
+            hbitmap_set(job->copy_bitmap, start / job->cluster_size, 1);
+            goto out;
         }
-        if (!job->use_copy_range) {
-            ret = backup_cow_with_bounce_buffer(job, start, end, is_write_notifier,
-                                                error_is_read, &bounce_buffer);
+
+        if (buffer_is_zero(iov.iov_base, iov.iov_len)) {
+            ret = blk_co_pwrite_zeroes(job->target, start,
+                                       bounce_qiov.size, BDRV_REQ_MAY_UNMAP);
+        } else {
+            ret = blk_co_pwritev(job->target, start,
+                                 bounce_qiov.size, &bounce_qiov,
+                                 job->compress ? BDRV_REQ_WRITE_COMPRESSED : 0);
         }
         if (ret < 0) {
-            break;
+            trace_backup_do_cow_write_fail(job, start, ret);
+            if (error_is_read) {
+                *error_is_read = false;
+            }
+            hbitmap_set(job->copy_bitmap, start / job->cluster_size, 1);
+            goto out;
         }
 
         /* 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.
          */
-        start += ret;
-        job->bytes_read += ret;
-        job_progress_update(&job->common.job, ret);
-        ret = 0;
+        job->bytes_read += n;
+        job->common.offset += n;
     }
 
+out:
     if (bounce_buffer) {
         qemu_vfree(bounce_buffer);
     }
@@ -258,12 +190,23 @@ static int coroutine_fn backup_before_write_notify(
     return backup_do_cow(job, req->offset, req->bytes, NULL, true);
 }
 
+static void backup_set_speed(BlockJob *job, int64_t speed, Error **errp)
+{
+    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
+
+    if (speed < 0) {
+        error_setg(errp, QERR_INVALID_PARAMETER, "speed");
+        return;
+    }
+    ratelimit_set_speed(&s->limit, speed, SLICE_TIME);
+}
+
 static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
 {
     BdrvDirtyBitmap *bm;
     BlockDriverState *bs = blk_bs(job->common.blk);
 
-    if (ret < 0) {
+    if (ret < 0 || block_job_is_cancelled(&job->common)) {
         /* Merge the successor back into the parent, delete nothing. */
         bm = bdrv_reclaim_dirty_bitmap(bs, job->sync_bitmap, NULL);
         assert(bm);
@@ -274,25 +217,25 @@ static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
     }
 }
 
-static void backup_commit(Job *job)
+static void backup_commit(BlockJob *job)
 {
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
+    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
     if (s->sync_bitmap) {
         backup_cleanup_sync_bitmap(s, 0);
     }
 }
 
-static void backup_abort(Job *job)
+static void backup_abort(BlockJob *job)
 {
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
+    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
     if (s->sync_bitmap) {
         backup_cleanup_sync_bitmap(s, -1);
     }
 }
 
-static void backup_clean(Job *job)
+static void backup_clean(BlockJob *job)
 {
-    BackupBlockJob *s = container_of(job, BackupBlockJob, common.job);
+    BackupBlockJob *s = container_of(job, BackupBlockJob, common);
     assert(s->target);
     blk_unref(s->target);
     s->target = NULL;
@@ -310,7 +253,7 @@ void backup_do_checkpoint(BlockJob *job, Error **errp)
     BackupBlockJob *backup_job = container_of(job, BackupBlockJob, common);
     int64_t len;
 
-    assert(block_job_driver(job) == &backup_job_driver);
+    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"
@@ -318,7 +261,7 @@ void backup_do_checkpoint(BlockJob *job, Error **errp)
         return;
     }
 
-    len = DIV_ROUND_UP(backup_job->len, backup_job->cluster_size);
+    len = DIV_ROUND_UP(backup_job->common.len, backup_job->cluster_size);
     hbitmap_set(backup_job->copy_bitmap, 0, len);
 }
 
@@ -328,7 +271,7 @@ void backup_wait_for_overlapping_requests(BlockJob *job, int64_t offset,
     BackupBlockJob *backup_job = container_of(job, BackupBlockJob, common);
     int64_t start, end;
 
-    assert(block_job_driver(job) == &backup_job_driver);
+    assert(job->driver->job_type == BLOCK_JOB_TYPE_BACKUP);
 
     start = QEMU_ALIGN_DOWN(offset, backup_job->cluster_size);
     end = QEMU_ALIGN_UP(offset + bytes, backup_job->cluster_size);
@@ -341,7 +284,7 @@ void backup_cow_request_begin(CowRequest *req, BlockJob *job,
     BackupBlockJob *backup_job = container_of(job, BackupBlockJob, common);
     int64_t start, end;
 
-    assert(block_job_driver(job) == &backup_job_driver);
+    assert(job->driver->job_type == BLOCK_JOB_TYPE_BACKUP);
 
     start = QEMU_ALIGN_DOWN(offset, backup_job->cluster_size);
     end = QEMU_ALIGN_UP(offset + bytes, backup_job->cluster_size);
@@ -384,29 +327,33 @@ typedef struct {
     int ret;
 } BackupCompleteData;
 
-static void backup_complete(Job *job, void *opaque)
+static void backup_complete(BlockJob *job, void *opaque)
 {
     BackupCompleteData *data = opaque;
 
-    job_completed(job, data->ret, NULL);
+    block_job_completed(job, data->ret);
     g_free(data);
 }
 
 static bool coroutine_fn yield_and_check(BackupBlockJob *job)
 {
-    uint64_t delay_ns;
-
-    if (job_is_cancelled(&job->common.job)) {
+    if (block_job_is_cancelled(&job->common)) {
         return true;
     }
 
-    /* We need to yield even for delay_ns = 0 so that bdrv_drain_all() can
-     * return. Without a yield, the VM would not reboot. */
-    delay_ns = block_job_ratelimit_get_delay(&job->common, job->bytes_read);
+    /* we need to yield so that bdrv_drain_all() returns.
+     * (without, VM does not reboot)
+     */
+    if (job->common.speed) {
+        uint64_t delay_ns = ratelimit_calculate_delay(&job->limit,
+                                                      job->bytes_read);
         job->bytes_read = 0;
-    job_sleep_ns(&job->common.job, delay_ns);
+        block_job_sleep_ns(&job->common, delay_ns);
+    } else {
+        block_job_sleep_ns(&job->common, 0);
+    }
 
-    if (job_is_cancelled(&job->common.job)) {
+    if (block_job_is_cancelled(&job->common)) {
         return true;
     }
 
@@ -421,7 +368,7 @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
     HBitmapIter hbi;
 
     hbitmap_iter_init(&hbi, job->copy_bitmap, 0);
-    while ((cluster = hbitmap_iter_next(&hbi, true)) != -1) {
+    while ((cluster = hbitmap_iter_next(&hbi)) != -1) {
         do {
             if (yield_and_check(job)) {
                 return 0;
@@ -473,9 +420,8 @@ static void backup_incremental_init_copy_bitmap(BackupBlockJob *job)
         bdrv_set_dirty_iter(dbi, next_cluster * job->cluster_size);
     }
 
-    /* TODO job_progress_set_remaining() would make more sense */
-    job_progress_update(&job->common.job,
-        job->len - hbitmap_count(job->copy_bitmap) * job->cluster_size);
+    job->common.offset = job->common.len -
+                         hbitmap_count(job->copy_bitmap) * job->cluster_size;
 
     bdrv_dirty_iter_free(dbi);
 }
@@ -491,9 +437,7 @@ static void coroutine_fn backup_run(void *opaque)
     QLIST_INIT(&job->inflight_reqs);
     qemu_co_rwlock_init(&job->flush_rwlock);
 
-    nb_clusters = DIV_ROUND_UP(job->len, job->cluster_size);
-    job_progress_set_remaining(&job->common.job, job->len);
-
+    nb_clusters = DIV_ROUND_UP(job->common.len, job->cluster_size);
     job->copy_bitmap = hbitmap_alloc(nb_clusters, 0);
     if (job->sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
         backup_incremental_init_copy_bitmap(job);
@@ -508,16 +452,16 @@ static void coroutine_fn backup_run(void *opaque)
     if (job->sync_mode == MIRROR_SYNC_MODE_NONE) {
         /* All bits are set in copy_bitmap to allow any cluster to be copied.
          * This does not actually require them to be copied. */
-        while (!job_is_cancelled(&job->common.job)) {
+        while (!block_job_is_cancelled(&job->common)) {
             /* Yield until the job is cancelled.  We just let our before_write
              * notify callback service CoW requests. */
-            job_yield(&job->common.job);
+            block_job_yield(&job->common);
         }
     } else if (job->sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
         ret = backup_run_incremental(job);
     } else {
         /* Both FULL and TOP SYNC_MODE's require copying.. */
-        for (offset = 0; offset < job->len;
+        for (offset = 0; offset < job->common.len;
              offset += job->cluster_size) {
             bool error_is_read;
             int alloced = 0;
@@ -586,21 +530,17 @@ static void coroutine_fn backup_run(void *opaque)
 
     data = g_malloc(sizeof(*data));
     data->ret = ret;
-    job_defer_to_main_loop(&job->common.job, backup_complete, data);
+    block_job_defer_to_main_loop(&job->common, backup_complete, data);
 }
 
 static const BlockJobDriver backup_job_driver = {
-    .job_driver = {
     .instance_size          = sizeof(BackupBlockJob),
-        .job_type               = JOB_TYPE_BACKUP,
-        .free                   = block_job_free,
-        .user_resume            = block_job_user_resume,
-        .drain                  = block_job_drain,
+    .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,
 };
@@ -613,7 +553,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
                   BlockdevOnError on_target_error,
                   int creation_flags,
                   BlockCompletionFunc *cb, void *opaque,
-                  JobTxn *txn, Error **errp)
+                  BlockJobTxn *txn, Error **errp)
 {
     int64_t len;
     BlockDriverInfo bdi;
@@ -680,8 +620,8 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
         goto error;
     }
 
-    /* job->len is fixed, so we can't allow resize */
-    job = block_job_create(job_id, &backup_job_driver, txn, bs,
+    /* 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,
@@ -706,9 +646,6 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
                        sync_bitmap : NULL;
     job->compress = compress;
 
-    /* Detect image-fleecing (and similar) schemes */
-    job->serialize_target_writes = bdrv_chain_contains(target, bs);
-
     /* 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. */
@@ -735,17 +672,12 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
     } else {
         job->cluster_size = MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
     }
-    job->use_copy_range = true;
-    job->copy_range_size = MIN_NON_ZERO(blk_get_max_transfer(job->common.blk),
-                                        blk_get_max_transfer(job->target));
-    job->copy_range_size = MAX(job->cluster_size,
-                               QEMU_ALIGN_UP(job->copy_range_size,
-                                             job->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->len = len;
+    job->common.len = len;
+    block_job_txn_add_job(txn, &job->common);
 
     return &job->common;
 
@@ -754,8 +686,8 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
         bdrv_reclaim_dirty_bitmap(bs, sync_bitmap, NULL);
     }
     if (job) {
-        backup_clean(&job->common.job);
-        job_early_fail(&job->common.job);
+        backup_clean(&job->common);
+        block_job_early_fail(&job->common);
     }
 
     return NULL;

block/blkdebug.c

@@ -398,11 +398,10 @@ static int blkdebug_open(BlockDriverState *bs, QDict *options, int flags,
         goto out;
     }
 
-    bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED |
-        (BDRV_REQ_FUA & bs->file->bs->supported_write_flags);
-    bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED |
-        ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP) &
-            bs->file->bs->supported_zero_flags);
+    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 */
@@ -625,7 +624,7 @@ static int coroutine_fn blkdebug_co_pdiscard(BlockDriverState *bs,
         return err;
     }
 
-    return bdrv_co_pdiscard(bs->file, offset, bytes);
+    return bdrv_co_pdiscard(bs->file->bs, offset, bytes);
 }
 
 static int coroutine_fn blkdebug_co_block_status(BlockDriverState *bs,
@@ -846,12 +845,13 @@ static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
     opts = qdict_new();
     qdict_put_str(opts, "driver", "blkdebug");
 
-    qdict_put(opts, "image", qobject_ref(bs->file->bs->full_open_options));
+    QINCREF(bs->file->bs->full_open_options);
+    qdict_put(opts, "image", 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")) {
-            qdict_put_obj(opts, qdict_entry_key(e),
-                          qobject_ref(qdict_entry_value(e)));
+            qobject_incref(qdict_entry_value(e));
+            qdict_put_obj(opts, qdict_entry_key(e), qdict_entry_value(e));
         }
     }
 

block/blklogwrites.c

@@ -1,550 +0,0 @@
-/*
- * Write logging blk driver based on blkverify and blkdebug.
- *
- * Copyright (c) 2017 Tuomas Tynkkynen <tuomas@tuxera.com>
- * Copyright (c) 2018 Aapo Vienamo <aapo@tuxera.com>
- * Copyright (c) 2018 Ari Sundholm <ari@tuxera.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- */
-
-#include "qemu/osdep.h"
-#include "qapi/error.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"
-#include "qemu/option.h"
-
-/* Disk format stuff - taken from Linux drivers/md/dm-log-writes.c */
-
-#define LOG_FLUSH_FLAG   (1 << 0)
-#define LOG_FUA_FLAG     (1 << 1)
-#define LOG_DISCARD_FLAG (1 << 2)
-#define LOG_MARK_FLAG    (1 << 3)
-#define LOG_FLAG_MASK    (LOG_FLUSH_FLAG \
-                         | LOG_FUA_FLAG \
-                         | LOG_DISCARD_FLAG \
-                         | LOG_MARK_FLAG)
-
-#define WRITE_LOG_VERSION 1ULL
-#define WRITE_LOG_MAGIC 0x6a736677736872ULL
-
-/* All fields are little-endian. */
-struct log_write_super {
-    uint64_t magic;
-    uint64_t version;
-    uint64_t nr_entries;
-    uint32_t sectorsize;
-} QEMU_PACKED;
-
-struct log_write_entry {
-    uint64_t sector;
-    uint64_t nr_sectors;
-    uint64_t flags;
-    uint64_t data_len;
-} QEMU_PACKED;
-
-/* End of disk format structures. */
-
-typedef struct {
-    BdrvChild *log_file;
-    uint32_t sectorsize;
-    uint32_t sectorbits;
-    uint64_t cur_log_sector;
-    uint64_t nr_entries;
-    uint64_t update_interval;
-} BDRVBlkLogWritesState;
-
-static QemuOptsList runtime_opts = {
-    .name = "blklogwrites",
-    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
-    .desc = {
-        {
-            .name = "log-append",
-            .type = QEMU_OPT_BOOL,
-            .help = "Append to an existing log",
-        },
-        {
-            .name = "log-sector-size",
-            .type = QEMU_OPT_SIZE,
-            .help = "Log sector size",
-        },
-        {
-            .name = "log-super-update-interval",
-            .type = QEMU_OPT_NUMBER,
-            .help = "Log superblock update interval (# of write requests)",
-        },
-        { /* end of list */ }
-    },
-};
-
-static inline uint32_t blk_log_writes_log2(uint32_t value)
-{
-    assert(value > 0);
-    return 31 - clz32(value);
-}
-
-static inline bool blk_log_writes_sector_size_valid(uint32_t sector_size)
-{
-    return is_power_of_2(sector_size) &&
-        sector_size >= sizeof(struct log_write_super) &&
-        sector_size >= sizeof(struct log_write_entry) &&
-        sector_size < (1ull << 24);
-}
-
-static uint64_t blk_log_writes_find_cur_log_sector(BdrvChild *log,
-                                                   uint32_t sector_size,
-                                                   uint64_t nr_entries,
-                                                   Error **errp)
-{
-    uint64_t cur_sector = 1;
-    uint64_t cur_idx = 0;
-    uint32_t sector_bits = blk_log_writes_log2(sector_size);
-    struct log_write_entry cur_entry;
-
-    while (cur_idx < nr_entries) {
-        int read_ret = bdrv_pread(log, cur_sector << sector_bits, &cur_entry,
-                                  sizeof(cur_entry));
-        if (read_ret < 0) {
-            error_setg_errno(errp, -read_ret,
-                             "Failed to read log entry %"PRIu64, cur_idx);
-            return (uint64_t)-1ull;
-        }
-
-        if (cur_entry.flags & ~cpu_to_le64(LOG_FLAG_MASK)) {
-            error_setg(errp, "Invalid flags 0x%"PRIx64" in log entry %"PRIu64,
-                       le64_to_cpu(cur_entry.flags), cur_idx);
-            return (uint64_t)-1ull;
-        }
-
-        /* Account for the sector of the entry itself */
-        ++cur_sector;
-
-        /*
-         * Account for the data of the write.
-         * For discards, this data is not present.
-         */
-        if (!(cur_entry.flags & cpu_to_le64(LOG_DISCARD_FLAG))) {
-            cur_sector += le64_to_cpu(cur_entry.nr_sectors);
-        }
-
-        ++cur_idx;
-    }
-
-    return cur_sector;
-}
-
-static int blk_log_writes_open(BlockDriverState *bs, QDict *options, int flags,
-                               Error **errp)
-{
-    BDRVBlkLogWritesState *s = bs->opaque;
-    QemuOpts *opts;
-    Error *local_err = NULL;
-    int ret;
-    uint64_t log_sector_size;
-    bool log_append;
-
-    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
-    qemu_opts_absorb_qdict(opts, options, &local_err);
-    if (local_err) {
-        ret = -EINVAL;
-        error_propagate(errp, local_err);
-        goto fail;
-    }
-
-    /* Open the file */
-    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, false,
-                               &local_err);
-    if (local_err) {
-        ret = -EINVAL;
-        error_propagate(errp, local_err);
-        goto fail;
-    }
-
-    /* Open the log file */
-    s->log_file = bdrv_open_child(NULL, options, "log", bs, &child_file, false,
-                                  &local_err);
-    if (local_err) {
-        ret = -EINVAL;
-        error_propagate(errp, local_err);
-        goto fail;
-    }
-
-    log_append = qemu_opt_get_bool(opts, "log-append", false);
-
-    if (log_append) {
-        struct log_write_super log_sb = { 0, 0, 0, 0 };
-
-        if (qemu_opt_find(opts, "log-sector-size")) {
-            ret = -EINVAL;
-            error_setg(errp, "log-append and log-sector-size are mutually "
-                       "exclusive");
-            goto fail_log;
-        }
-
-        /* Read log superblock or fake one for an empty log */
-        if (!bdrv_getlength(s->log_file->bs)) {
-            log_sb.magic      = cpu_to_le64(WRITE_LOG_MAGIC);
-            log_sb.version    = cpu_to_le64(WRITE_LOG_VERSION);
-            log_sb.nr_entries = cpu_to_le64(0);
-            log_sb.sectorsize = cpu_to_le32(BDRV_SECTOR_SIZE);
-        } else {
-            ret = bdrv_pread(s->log_file, 0, &log_sb, sizeof(log_sb));
-            if (ret < 0) {
-                error_setg_errno(errp, -ret, "Could not read log superblock");
-                goto fail_log;
-            }
-        }
-
-        if (log_sb.magic != cpu_to_le64(WRITE_LOG_MAGIC)) {
-            ret = -EINVAL;
-            error_setg(errp, "Invalid log superblock magic");
-            goto fail_log;
-        }
-
-        if (log_sb.version != cpu_to_le64(WRITE_LOG_VERSION)) {
-            ret = -EINVAL;
-            error_setg(errp, "Unsupported log version %"PRIu64,
-                       le64_to_cpu(log_sb.version));
-            goto fail_log;
-        }
-
-        log_sector_size = le32_to_cpu(log_sb.sectorsize);
-        s->cur_log_sector = 1;
-        s->nr_entries = 0;
-
-        if (blk_log_writes_sector_size_valid(log_sector_size)) {
-            s->cur_log_sector =
-                blk_log_writes_find_cur_log_sector(s->log_file, log_sector_size,
-                                    le64_to_cpu(log_sb.nr_entries), &local_err);
-            if (local_err) {
-                ret = -EINVAL;
-                error_propagate(errp, local_err);
-                goto fail_log;
-            }
-
-            s->nr_entries = le64_to_cpu(log_sb.nr_entries);
-        }
-    } else {
-        log_sector_size = qemu_opt_get_size(opts, "log-sector-size",
-                                            BDRV_SECTOR_SIZE);
-        s->cur_log_sector = 1;
-        s->nr_entries = 0;
-    }
-
-    if (!blk_log_writes_sector_size_valid(log_sector_size)) {
-        ret = -EINVAL;
-        error_setg(errp, "Invalid log sector size %"PRIu64, log_sector_size);
-        goto fail_log;
-    }
-
-    s->sectorsize = log_sector_size;
-    s->sectorbits = blk_log_writes_log2(log_sector_size);
-    s->update_interval = qemu_opt_get_number(opts, "log-super-update-interval",
-                                             4096);
-    if (!s->update_interval) {
-        ret = -EINVAL;
-        error_setg(errp, "Invalid log superblock update interval %"PRIu64,
-                   s->update_interval);
-        goto fail_log;
-    }
-
-    ret = 0;
-fail_log:
-    if (ret < 0) {
-        bdrv_unref_child(bs, s->log_file);
-        s->log_file = NULL;
-    }
-fail:
-    if (ret < 0) {
-        bdrv_unref_child(bs, bs->file);
-        bs->file = NULL;
-    }
-    qemu_opts_del(opts);
-    return ret;
-}
-
-static void blk_log_writes_close(BlockDriverState *bs)
-{
-    BDRVBlkLogWritesState *s = bs->opaque;
-
-    bdrv_unref_child(bs, s->log_file);
-    s->log_file = NULL;
-}
-
-static int64_t blk_log_writes_getlength(BlockDriverState *bs)
-{
-    return bdrv_getlength(bs->file->bs);
-}
-
-static void blk_log_writes_refresh_filename(BlockDriverState *bs,
-                                            QDict *options)
-{
-    BDRVBlkLogWritesState *s = bs->opaque;
-
-    /* bs->file->bs has already been refreshed */
-    bdrv_refresh_filename(s->log_file->bs);
-
-    if (bs->file->bs->full_open_options
-        && s->log_file->bs->full_open_options)
-    {
-        QDict *opts = qdict_new();
-        qdict_put_str(opts, "driver", "blklogwrites");
-
-        qobject_ref(bs->file->bs->full_open_options);
-        qdict_put_obj(opts, "file", QOBJECT(bs->file->bs->full_open_options));
-        qobject_ref(s->log_file->bs->full_open_options);
-        qdict_put_obj(opts, "log",
-                      QOBJECT(s->log_file->bs->full_open_options));
-        qdict_put_int(opts, "log-sector-size", s->sectorsize);
-
-        bs->full_open_options = opts;
-    }
-}
-
-static void blk_log_writes_child_perm(BlockDriverState *bs, BdrvChild *c,
-                                      const BdrvChildRole *role,
-                                      BlockReopenQueue *ro_q,
-                                      uint64_t perm, uint64_t shrd,
-                                      uint64_t *nperm, uint64_t *nshrd)
-{
-    if (!c) {
-        *nperm = perm & DEFAULT_PERM_PASSTHROUGH;
-        *nshrd = (shrd & DEFAULT_PERM_PASSTHROUGH) | DEFAULT_PERM_UNCHANGED;
-        return;
-    }
-
-    if (!strcmp(c->name, "log")) {
-        bdrv_format_default_perms(bs, c, role, ro_q, perm, shrd, nperm, nshrd);
-    } else {
-        bdrv_filter_default_perms(bs, c, role, ro_q, perm, shrd, nperm, nshrd);
-    }
-}
-
-static void blk_log_writes_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    BDRVBlkLogWritesState *s = bs->opaque;
-    bs->bl.request_alignment = s->sectorsize;
-}
-
-static int coroutine_fn
-blk_log_writes_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
-                         QEMUIOVector *qiov, int flags)
-{
-    return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
-}
-
-typedef struct BlkLogWritesFileReq {
-    BlockDriverState *bs;
-    uint64_t offset;
-    uint64_t bytes;
-    int file_flags;
-    QEMUIOVector *qiov;
-    int (*func)(struct BlkLogWritesFileReq *r);
-    int file_ret;
-} BlkLogWritesFileReq;
-
-typedef struct {
-    BlockDriverState *bs;
-    QEMUIOVector *qiov;
-    struct log_write_entry entry;
-    uint64_t zero_size;
-    int log_ret;
-} BlkLogWritesLogReq;
-
-static void coroutine_fn blk_log_writes_co_do_log(BlkLogWritesLogReq *lr)
-{
-    BDRVBlkLogWritesState *s = lr->bs->opaque;
-    uint64_t cur_log_offset = s->cur_log_sector << s->sectorbits;
-
-    s->nr_entries++;
-    s->cur_log_sector +=
-            ROUND_UP(lr->qiov->size, s->sectorsize) >> s->sectorbits;
-
-    lr->log_ret = bdrv_co_pwritev(s->log_file, cur_log_offset, lr->qiov->size,
-                                  lr->qiov, 0);
-
-    /* Logging for the "write zeroes" operation */
-    if (lr->log_ret == 0 && lr->zero_size) {
-        cur_log_offset = s->cur_log_sector << s->sectorbits;
-        s->cur_log_sector +=
-                ROUND_UP(lr->zero_size, s->sectorsize) >> s->sectorbits;
-
-        lr->log_ret = bdrv_co_pwrite_zeroes(s->log_file, cur_log_offset,
-                                            lr->zero_size, 0);
-    }
-
-    /* Update super block on flush or every update interval */
-    if (lr->log_ret == 0 && ((lr->entry.flags & LOG_FLUSH_FLAG)
-        || (s->nr_entries % s->update_interval == 0)))
-    {
-        struct log_write_super super = {
-            .magic      = cpu_to_le64(WRITE_LOG_MAGIC),
-            .version    = cpu_to_le64(WRITE_LOG_VERSION),
-            .nr_entries = cpu_to_le64(s->nr_entries),
-            .sectorsize = cpu_to_le32(s->sectorsize),
-        };
-        void *zeroes = g_malloc0(s->sectorsize - sizeof(super));
-        QEMUIOVector qiov;
-
-        qemu_iovec_init(&qiov, 2);
-        qemu_iovec_add(&qiov, &super, sizeof(super));
-        qemu_iovec_add(&qiov, zeroes, s->sectorsize - sizeof(super));
-
-        lr->log_ret =
-            bdrv_co_pwritev(s->log_file, 0, s->sectorsize, &qiov, 0);
-        if (lr->log_ret == 0) {
-            lr->log_ret = bdrv_co_flush(s->log_file->bs);
-        }
-        qemu_iovec_destroy(&qiov);
-        g_free(zeroes);
-    }
-}
-
-static void coroutine_fn blk_log_writes_co_do_file(BlkLogWritesFileReq *fr)
-{
-    fr->file_ret = fr->func(fr);
-}
-
-static int coroutine_fn
-blk_log_writes_co_log(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
-                      QEMUIOVector *qiov, int flags,
-                      int (*file_func)(BlkLogWritesFileReq *r),
-                      uint64_t entry_flags, bool is_zero_write)
-{
-    QEMUIOVector log_qiov;
-    size_t niov = qiov ? qiov->niov : 0;
-    BDRVBlkLogWritesState *s = bs->opaque;
-    BlkLogWritesFileReq fr = {
-        .bs         = bs,
-        .offset     = offset,
-        .bytes      = bytes,
-        .file_flags = flags,
-        .qiov       = qiov,
-        .func       = file_func,
-    };
-    BlkLogWritesLogReq lr = {
-        .bs             = bs,
-        .qiov           = &log_qiov,
-        .entry = {
-            .sector     = cpu_to_le64(offset >> s->sectorbits),
-            .nr_sectors = cpu_to_le64(bytes >> s->sectorbits),
-            .flags      = cpu_to_le64(entry_flags),
-            .data_len   = 0,
-        },
-        .zero_size = is_zero_write ? bytes : 0,
-    };
-    void *zeroes = g_malloc0(s->sectorsize - sizeof(lr.entry));
-
-    assert((1 << s->sectorbits) == s->sectorsize);
-    assert(bs->bl.request_alignment == s->sectorsize);
-    assert(QEMU_IS_ALIGNED(offset, bs->bl.request_alignment));
-    assert(QEMU_IS_ALIGNED(bytes, bs->bl.request_alignment));
-
-    qemu_iovec_init(&log_qiov, niov + 2);
-    qemu_iovec_add(&log_qiov, &lr.entry, sizeof(lr.entry));
-    qemu_iovec_add(&log_qiov, zeroes, s->sectorsize - sizeof(lr.entry));
-    if (qiov) {
-        qemu_iovec_concat(&log_qiov, qiov, 0, qiov->size);
-    }
-
-    blk_log_writes_co_do_file(&fr);
-    blk_log_writes_co_do_log(&lr);
-
-    qemu_iovec_destroy(&log_qiov);
-    g_free(zeroes);
-
-    if (lr.log_ret < 0) {
-        return lr.log_ret;
-    }
-
-    return fr.file_ret;
-}
-
-static int coroutine_fn
-blk_log_writes_co_do_file_pwritev(BlkLogWritesFileReq *fr)
-{
-    return bdrv_co_pwritev(fr->bs->file, fr->offset, fr->bytes,
-                           fr->qiov, fr->file_flags);
-}
-
-static int coroutine_fn
-blk_log_writes_co_do_file_pwrite_zeroes(BlkLogWritesFileReq *fr)
-{
-    return bdrv_co_pwrite_zeroes(fr->bs->file, fr->offset, fr->bytes,
-                                 fr->file_flags);
-}
-
-static int coroutine_fn blk_log_writes_co_do_file_flush(BlkLogWritesFileReq *fr)
-{
-    return bdrv_co_flush(fr->bs->file->bs);
-}
-
-static int coroutine_fn
-blk_log_writes_co_do_file_pdiscard(BlkLogWritesFileReq *fr)
-{
-    return bdrv_co_pdiscard(fr->bs->file, fr->offset, fr->bytes);
-}
-
-static int coroutine_fn
-blk_log_writes_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
-                          QEMUIOVector *qiov, int flags)
-{
-    return blk_log_writes_co_log(bs, offset, bytes, qiov, flags,
-                                 blk_log_writes_co_do_file_pwritev, 0, false);
-}
-
-static int coroutine_fn
-blk_log_writes_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes,
-                                BdrvRequestFlags flags)
-{
-    return blk_log_writes_co_log(bs, offset, bytes, NULL, flags,
-                                 blk_log_writes_co_do_file_pwrite_zeroes, 0,
-                                 true);
-}
-
-static int coroutine_fn blk_log_writes_co_flush_to_disk(BlockDriverState *bs)
-{
-    return blk_log_writes_co_log(bs, 0, 0, NULL, 0,
-                                 blk_log_writes_co_do_file_flush,
-                                 LOG_FLUSH_FLAG, false);
-}
-
-static int coroutine_fn
-blk_log_writes_co_pdiscard(BlockDriverState *bs, int64_t offset, int count)
-{
-    return blk_log_writes_co_log(bs, offset, count, NULL, 0,
-                                 blk_log_writes_co_do_file_pdiscard,
-                                 LOG_DISCARD_FLAG, false);
-}
-
-static BlockDriver bdrv_blk_log_writes = {
-    .format_name            = "blklogwrites",
-    .instance_size          = sizeof(BDRVBlkLogWritesState),
-
-    .bdrv_open              = blk_log_writes_open,
-    .bdrv_close             = blk_log_writes_close,
-    .bdrv_getlength         = blk_log_writes_getlength,
-    .bdrv_refresh_filename  = blk_log_writes_refresh_filename,
-    .bdrv_child_perm        = blk_log_writes_child_perm,
-    .bdrv_refresh_limits    = blk_log_writes_refresh_limits,
-
-    .bdrv_co_preadv         = blk_log_writes_co_preadv,
-    .bdrv_co_pwritev        = blk_log_writes_co_pwritev,
-    .bdrv_co_pwrite_zeroes  = blk_log_writes_co_pwrite_zeroes,
-    .bdrv_co_flush_to_disk  = blk_log_writes_co_flush_to_disk,
-    .bdrv_co_pdiscard       = blk_log_writes_co_pdiscard,
-    .bdrv_co_block_status   = bdrv_co_block_status_from_file,
-
-    .is_filter              = true,
-};
-
-static void bdrv_blk_log_writes_init(void)
-{
-    bdrv_register(&bdrv_blk_log_writes);
-}
-
-block_init(bdrv_blk_log_writes_init);

block/blkreplay.c

@@ -35,9 +35,6 @@ static int blkreplay_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED;
-    bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED;
-
     ret = 0;
 fail:
     return ret;
@@ -113,7 +110,7 @@ static int coroutine_fn blkreplay_co_pdiscard(BlockDriverState *bs,
                                               int64_t offset, int bytes)
 {
     uint64_t reqid = blkreplay_next_id();
-    int ret = bdrv_co_pdiscard(bs->file, offset, bytes);
+    int ret = bdrv_co_pdiscard(bs->file->bs, offset, bytes);
     block_request_create(reqid, bs, qemu_coroutine_self());
     qemu_coroutine_yield();
 

block/blkverify.c

@@ -141,9 +141,6 @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED;
-    bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED;
-
     ret = 0;
 fail:
     qemu_opts_del(opts);
@@ -294,10 +291,10 @@ static void blkverify_refresh_filename(BlockDriverState *bs, QDict *options)
         QDict *opts = qdict_new();
         qdict_put_str(opts, "driver", "blkverify");
 
-        qdict_put(opts, "raw",
-                  qobject_ref(bs->file->bs->full_open_options));
-        qdict_put(opts, "test",
-                  qobject_ref(s->test_file->bs->full_open_options));
+        QINCREF(bs->file->bs->full_open_options);
+        qdict_put(opts, "raw", 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);
 
         bs->full_open_options = opts;
     }

block/block-backend.c

@@ -31,13 +31,6 @@
 
 static AioContext *blk_aiocb_get_aio_context(BlockAIOCB *acb);
 
-typedef struct BlockBackendAioNotifier {
-    void (*attached_aio_context)(AioContext *new_context, void *opaque);
-    void (*detach_aio_context)(void *opaque);
-    void *opaque;
-    QLIST_ENTRY(BlockBackendAioNotifier) list;
-} BlockBackendAioNotifier;
-
 struct BlockBackend {
     char *name;
     int refcnt;
@@ -76,7 +69,6 @@ struct BlockBackend {
     bool allow_write_beyond_eof;
 
     NotifierList remove_bs_notifiers, insert_bs_notifiers;
-    QLIST_HEAD(, BlockBackendAioNotifier) aio_notifiers;
 
     int quiesce_counter;
     VMChangeStateEntry *vmsh;
@@ -255,36 +247,6 @@ static int blk_root_inactivate(BdrvChild *child)
     return 0;
 }
 
-static void blk_root_attach(BdrvChild *child)
-{
-    BlockBackend *blk = child->opaque;
-    BlockBackendAioNotifier *notifier;
-
-    trace_blk_root_attach(child, blk, child->bs);
-
-    QLIST_FOREACH(notifier, &blk->aio_notifiers, list) {
-        bdrv_add_aio_context_notifier(child->bs,
-                notifier->attached_aio_context,
-                notifier->detach_aio_context,
-                notifier->opaque);
-    }
-}
-
-static void blk_root_detach(BdrvChild *child)
-{
-    BlockBackend *blk = child->opaque;
-    BlockBackendAioNotifier *notifier;
-
-    trace_blk_root_detach(child, blk, child->bs);
-
-    QLIST_FOREACH(notifier, &blk->aio_notifiers, list) {
-        bdrv_remove_aio_context_notifier(child->bs,
-                notifier->attached_aio_context,
-                notifier->detach_aio_context,
-                notifier->opaque);
-    }
-}
-
 static const BdrvChildRole child_root = {
     .inherit_options    = blk_root_inherit_options,
 
@@ -298,9 +260,6 @@ static const BdrvChildRole child_root = {
 
     .activate           = blk_root_activate,
     .inactivate         = blk_root_inactivate,
-
-    .attach             = blk_root_attach,
-    .detach             = blk_root_detach,
 };
 
 /*
@@ -328,7 +287,6 @@ BlockBackend *blk_new(uint64_t perm, uint64_t shared_perm)
 
     notifier_list_init(&blk->remove_bs_notifiers);
     notifier_list_init(&blk->insert_bs_notifiers);
-    QLIST_INIT(&blk->aio_notifiers);
 
     QTAILQ_INSERT_TAIL(&block_backends, blk, link);
     return blk;
@@ -406,7 +364,6 @@ static void blk_delete(BlockBackend *blk)
     }
     assert(QLIST_EMPTY(&blk->remove_bs_notifiers.notifiers));
     assert(QLIST_EMPTY(&blk->insert_bs_notifiers.notifiers));
-    assert(QLIST_EMPTY(&blk->aio_notifiers));
     QTAILQ_REMOVE(&block_backends, blk, link);
     drive_info_del(blk->legacy_dinfo);
     block_acct_cleanup(&blk->stats);
@@ -768,11 +725,6 @@ void blk_remove_bs(BlockBackend *blk)
 
     blk_update_root_state(blk);
 
-    /* bdrv_root_unref_child() will cause blk->root to become stale and may
-     * switch to a completion coroutine later on. Let's drain all I/O here
-     * to avoid that and a potential QEMU crash.
-     */
-    blk_drain(blk);
     bdrv_root_unref_child(blk->root);
     blk->root = NULL;
 }
@@ -1560,7 +1512,7 @@ int blk_co_pdiscard(BlockBackend *blk, int64_t offset, int bytes)
         return ret;
     }
 
-    return bdrv_co_pdiscard(blk->root, offset, bytes);
+    return bdrv_co_pdiscard(blk_bs(blk), offset, bytes);
 }
 
 int blk_co_flush(BlockBackend *blk)
@@ -1870,7 +1822,13 @@ void blk_op_unblock_all(BlockBackend *blk, Error *reason)
 
 AioContext *blk_get_aio_context(BlockBackend *blk)
 {
-    return bdrv_get_aio_context(blk_bs(blk));
+    BlockDriverState *bs = blk_bs(blk);
+
+    if (bs) {
+        return bdrv_get_aio_context(bs);
+    } else {
+        return qemu_get_aio_context();
+    }
 }
 
 static AioContext *blk_aiocb_get_aio_context(BlockAIOCB *acb)
@@ -1899,15 +1857,8 @@ void blk_add_aio_context_notifier(BlockBackend *blk,
         void (*attached_aio_context)(AioContext *new_context, void *opaque),
         void (*detach_aio_context)(void *opaque), void *opaque)
 {
-    BlockBackendAioNotifier *notifier;
     BlockDriverState *bs = blk_bs(blk);
 
-    notifier = g_new(BlockBackendAioNotifier, 1);
-    notifier->attached_aio_context = attached_aio_context;
-    notifier->detach_aio_context = detach_aio_context;
-    notifier->opaque = opaque;
-    QLIST_INSERT_HEAD(&blk->aio_notifiers, notifier, list);
-
     if (bs) {
         bdrv_add_aio_context_notifier(bs, attached_aio_context,
                                       detach_aio_context, opaque);
@@ -1920,25 +1871,12 @@ void blk_remove_aio_context_notifier(BlockBackend *blk,
                                      void (*detach_aio_context)(void *),
                                      void *opaque)
 {
-    BlockBackendAioNotifier *notifier;
     BlockDriverState *bs = blk_bs(blk);
 
     if (bs) {
         bdrv_remove_aio_context_notifier(bs, attached_aio_context,
                                          detach_aio_context, opaque);
     }
-
-    QLIST_FOREACH(notifier, &blk->aio_notifiers, list) {
-        if (notifier->attached_aio_context == attached_aio_context &&
-            notifier->detach_aio_context == detach_aio_context &&
-            notifier->opaque == opaque) {
-            QLIST_REMOVE(notifier, list);
-            g_free(notifier);
-            return;
-        }
-    }
-
-    abort();
 }
 
 void blk_add_remove_bs_notifier(BlockBackend *blk, Notifier *notify)
@@ -2216,22 +2154,3 @@ void blk_unregister_buf(BlockBackend *blk, void *host)
 {
     bdrv_unregister_buf(blk_bs(blk), host);
 }
-
-int coroutine_fn blk_co_copy_range(BlockBackend *blk_in, int64_t off_in,
-                                   BlockBackend *blk_out, int64_t off_out,
-                                   int bytes, BdrvRequestFlags read_flags,
-                                   BdrvRequestFlags write_flags)
-{
-    int r;
-    r = blk_check_byte_request(blk_in, off_in, bytes);
-    if (r) {
-        return r;
-    }
-    r = blk_check_byte_request(blk_out, off_out, bytes);
-    if (r) {
-        return r;
-    }
-    return bdrv_co_copy_range(blk_in->root, off_in,
-                              blk_out->root, off_out,
-                              bytes, read_flags, write_flags);
-}

block/commit.c

@@ -31,8 +31,11 @@ enum {
     COMMIT_BUFFER_SIZE = 512 * 1024, /* in bytes */
 };
 
+#define SLICE_TIME 100000000ULL /* ns */
+
 typedef struct CommitBlockJob {
     BlockJob common;
+    RateLimit limit;
     BlockDriverState *commit_top_bs;
     BlockBackend *top;
     BlockBackend *base;
@@ -72,10 +75,9 @@ typedef struct {
     int ret;
 } CommitCompleteData;
 
-static void commit_complete(Job *job, void *opaque)
+static void commit_complete(BlockJob *job, void *opaque)
 {
-    CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
-    BlockJob *bjob = &s->common;
+    CommitBlockJob *s = container_of(job, CommitBlockJob, common);
     CommitCompleteData *data = opaque;
     BlockDriverState *top = blk_bs(s->top);
     BlockDriverState *base = blk_bs(s->base);
@@ -91,7 +93,7 @@ static void commit_complete(Job *job, void *opaque)
      * the normal backing chain can be restored. */
     blk_unref(s->base);
 
-    if (!job_is_cancelled(job) && ret == 0) {
+    if (!block_job_is_cancelled(&s->common) && ret == 0) {
         /* success */
         ret = bdrv_drop_intermediate(s->commit_top_bs, base,
                                      s->backing_file_str);
@@ -112,12 +114,12 @@ static void commit_complete(Job *job, void *opaque)
     blk_unref(s->top);
 
     /* If there is more than one reference to the job (e.g. if called from
-     * job_finish_sync()), job_completed() won't free it and therefore the
-     * blockers on the intermediate nodes remain. This would cause
-     * bdrv_set_backing_hd() to fail. */
-    block_job_remove_all_bdrv(bjob);
+     * block_job_finish_sync()), block_job_completed() won't free it and
+     * therefore the blockers on the intermediate nodes remain. This would
+     * cause bdrv_set_backing_hd() to fail. */
+    block_job_remove_all_bdrv(job);
 
-    job_completed(job, ret, NULL);
+    block_job_completed(&s->common, ret);
     g_free(data);
 
     /* If bdrv_drop_intermediate() didn't already do that, remove the commit
@@ -144,21 +146,21 @@ static void coroutine_fn commit_run(void *opaque)
     int64_t n = 0; /* bytes */
     void *buf = NULL;
     int bytes_written = 0;
-    int64_t len, base_len;
+    int64_t base_len;
 
-    ret = len = blk_getlength(s->top);
-    if (len < 0) {
+    ret = s->common.len = blk_getlength(s->top);
+
+    if (s->common.len < 0) {
         goto out;
     }
-    job_progress_set_remaining(&s->common.job, len);
 
     ret = base_len = blk_getlength(s->base);
     if (base_len < 0) {
         goto out;
     }
 
-    if (base_len < len) {
-        ret = blk_truncate(s->base, len, PREALLOC_MODE_OFF, NULL);
+    if (base_len < s->common.len) {
+        ret = blk_truncate(s->base, s->common.len, PREALLOC_MODE_OFF, NULL);
         if (ret) {
             goto out;
         }
@@ -166,14 +168,14 @@ static void coroutine_fn commit_run(void *opaque)
 
     buf = blk_blockalign(s->top, COMMIT_BUFFER_SIZE);
 
-    for (offset = 0; offset < len; offset += n) {
+    for (offset = 0; offset < s->common.len; offset += n) {
         bool copy;
 
         /* 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.
          */
-        job_sleep_ns(&s->common.job, delay_ns);
-        if (job_is_cancelled(&s->common.job)) {
+        block_job_sleep_ns(&s->common, delay_ns);
+        if (block_job_is_cancelled(&s->common)) {
             break;
         }
         /* Copy if allocated above the base */
@@ -196,12 +198,10 @@ static void coroutine_fn commit_run(void *opaque)
             }
         }
         /* Publish progress */
-        job_progress_update(&s->common.job, n);
+        s->common.offset += n;
 
-        if (copy) {
-            delay_ns = block_job_ratelimit_get_delay(&s->common, n);
-        } else {
-            delay_ns = 0;
+        if (copy && s->common.speed) {
+            delay_ns = ratelimit_calculate_delay(&s->limit, n);
         }
     }
 
@@ -212,18 +212,25 @@ out:
 
     data = g_malloc(sizeof(*data));
     data->ret = ret;
-    job_defer_to_main_loop(&s->common.job, commit_complete, data);
+    block_job_defer_to_main_loop(&s->common, commit_complete, data);
+}
+
+static void commit_set_speed(BlockJob *job, int64_t speed, Error **errp)
+{
+    CommitBlockJob *s = container_of(job, CommitBlockJob, common);
+
+    if (speed < 0) {
+        error_setg(errp, QERR_INVALID_PARAMETER, "speed");
+        return;
+    }
+    ratelimit_set_speed(&s->limit, speed, SLICE_TIME);
 }
 
 static const BlockJobDriver commit_job_driver = {
-    .job_driver = {
     .instance_size = sizeof(CommitBlockJob),
-        .job_type      = JOB_TYPE_COMMIT,
-        .free          = block_job_free,
-        .user_resume   = block_job_user_resume,
-        .drain         = block_job_drain,
+    .job_type      = BLOCK_JOB_TYPE_COMMIT,
+    .set_speed     = commit_set_speed,
     .start         = commit_run,
-    },
 };
 
 static int coroutine_fn bdrv_commit_top_preadv(BlockDriverState *bs,
@@ -282,8 +289,8 @@ void commit_start(const char *job_id, BlockDriverState *bs,
         return;
     }
 
-    s = block_job_create(job_id, &commit_job_driver, NULL, bs, 0, BLK_PERM_ALL,
-                         speed, JOB_DEFAULT, NULL, NULL, errp);
+    s = block_job_create(job_id, &commit_job_driver, bs, 0, BLK_PERM_ALL,
+                         speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp);
     if (!s) {
         return;
     }
@@ -373,7 +380,7 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     s->on_error = on_error;
 
     trace_commit_start(bs, base, top, s);
-    job_start(&s->common.job);
+    block_job_start(&s->common);
     return;
 
 fail:
@@ -386,7 +393,7 @@ fail:
     if (commit_top_bs) {
         bdrv_replace_node(commit_top_bs, top, &error_abort);
     }
-    job_early_fail(&s->common.job);
+    block_job_early_fail(&s->common);
 }
 
 

block/copy-on-read.c

@@ -1,173 +0,0 @@
-/*
- * Copy-on-read filter block driver
- *
- * Copyright (c) 2018 Red Hat, Inc.
- *
- * Author:
- *   Max Reitz <mreitz@redhat.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 or
- * (at your option) version 3 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "qemu/osdep.h"
-#include "block/block_int.h"
-
-
-static int cor_open(BlockDriverState *bs, QDict *options, int flags,
-                    Error **errp)
-{
-    bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, false,
-                               errp);
-    if (!bs->file) {
-        return -EINVAL;
-    }
-
-    bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED |
-                                (BDRV_REQ_FUA &
-                                    bs->file->bs->supported_write_flags);
-
-    bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED |
-                               ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP) &
-                                    bs->file->bs->supported_zero_flags);
-
-    return 0;
-}
-
-
-static void cor_close(BlockDriverState *bs)
-{
-}
-
-
-#define PERM_PASSTHROUGH (BLK_PERM_CONSISTENT_READ \
-                          | BLK_PERM_WRITE \
-                          | BLK_PERM_RESIZE)
-#define PERM_UNCHANGED (BLK_PERM_ALL & ~PERM_PASSTHROUGH)
-
-static void cor_child_perm(BlockDriverState *bs, BdrvChild *c,
-                           const BdrvChildRole *role,
-                           BlockReopenQueue *reopen_queue,
-                           uint64_t perm, uint64_t shared,
-                           uint64_t *nperm, uint64_t *nshared)
-{
-    if (c == NULL) {
-        *nperm = (perm & PERM_PASSTHROUGH) | BLK_PERM_WRITE_UNCHANGED;
-        *nshared = (shared & PERM_PASSTHROUGH) | PERM_UNCHANGED;
-        return;
-    }
-
-    *nperm = (perm & PERM_PASSTHROUGH) |
-             (c->perm & PERM_UNCHANGED);
-    *nshared = (shared & PERM_PASSTHROUGH) |
-               (c->shared_perm & PERM_UNCHANGED);
-}
-
-
-static int64_t cor_getlength(BlockDriverState *bs)
-{
-    return bdrv_getlength(bs->file->bs);
-}
-
-
-static int coroutine_fn cor_co_truncate(BlockDriverState *bs, int64_t offset,
-                                        PreallocMode prealloc, Error **errp)
-{
-    return bdrv_co_truncate(bs->file, offset, prealloc, errp);
-}
-
-
-static int coroutine_fn cor_co_preadv(BlockDriverState *bs,
-                                      uint64_t offset, uint64_t bytes,
-                                      QEMUIOVector *qiov, int flags)
-{
-    return bdrv_co_preadv(bs->file, offset, bytes, qiov,
-                          flags | BDRV_REQ_COPY_ON_READ);
-}
-
-
-static int coroutine_fn cor_co_pwritev(BlockDriverState *bs,
-                                       uint64_t offset, uint64_t bytes,
-                                       QEMUIOVector *qiov, int flags)
-{
-
-    return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
-}
-
-
-static int coroutine_fn cor_co_pwrite_zeroes(BlockDriverState *bs,
-                                             int64_t offset, int bytes,
-                                             BdrvRequestFlags flags)
-{
-    return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
-}
-
-
-static int coroutine_fn cor_co_pdiscard(BlockDriverState *bs,
-                                        int64_t offset, int bytes)
-{
-    return bdrv_co_pdiscard(bs->file, offset, bytes);
-}
-
-
-static void cor_eject(BlockDriverState *bs, bool eject_flag)
-{
-    bdrv_eject(bs->file->bs, eject_flag);
-}
-
-
-static void cor_lock_medium(BlockDriverState *bs, bool locked)
-{
-    bdrv_lock_medium(bs->file->bs, locked);
-}
-
-
-static bool cor_recurse_is_first_non_filter(BlockDriverState *bs,
-                                            BlockDriverState *candidate)
-{
-    return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate);
-}
-
-
-BlockDriver bdrv_copy_on_read = {
-    .format_name                        = "copy-on-read",
-
-    .bdrv_open                          = cor_open,
-    .bdrv_close                         = cor_close,
-    .bdrv_child_perm                    = cor_child_perm,
-
-    .bdrv_getlength                     = cor_getlength,
-    .bdrv_co_truncate                   = cor_co_truncate,
-
-    .bdrv_co_preadv                     = cor_co_preadv,
-    .bdrv_co_pwritev                    = cor_co_pwritev,
-    .bdrv_co_pwrite_zeroes              = cor_co_pwrite_zeroes,
-    .bdrv_co_pdiscard                   = cor_co_pdiscard,
-
-    .bdrv_eject                         = cor_eject,
-    .bdrv_lock_medium                   = cor_lock_medium,
-
-    .bdrv_co_block_status               = bdrv_co_block_status_from_file,
-
-    .bdrv_recurse_is_first_non_filter   = cor_recurse_is_first_non_filter,
-
-    .has_variable_length                = true,
-    .is_filter                          = true,
-};
-
-static void bdrv_copy_on_read_init(void)
-{
-    bdrv_register(&bdrv_copy_on_read);
-}
-
-block_init(bdrv_copy_on_read_init);

block/create.c

@@ -24,51 +24,28 @@
 
 #include "qemu/osdep.h"
 #include "block/block_int.h"
-#include "qemu/job.h"
 #include "qapi/qapi-commands-block-core.h"
-#include "qapi/qapi-visit-block-core.h"
-#include "qapi/clone-visitor.h"
 #include "qapi/error.h"
 
-typedef struct BlockdevCreateJob {
-    Job common;
+typedef struct BlockdevCreateCo {
     BlockDriver *drv;
     BlockdevCreateOptions *opts;
     int ret;
-    Error *err;
-} BlockdevCreateJob;
+    Error **errp;
+} BlockdevCreateCo;
 
-static void blockdev_create_complete(Job *job, void *opaque)
+static void coroutine_fn bdrv_co_create_co_entry(void *opaque)
 {
-    BlockdevCreateJob *s = container_of(job, BlockdevCreateJob, common);
-
-    job_completed(job, s->ret, s->err);
+    BlockdevCreateCo *cco = opaque;
+    cco->ret = cco->drv->bdrv_co_create(cco->opts, cco->errp);
 }
 
-static void coroutine_fn blockdev_create_run(void *opaque)
+void qmp_x_blockdev_create(BlockdevCreateOptions *options, Error **errp)
 {
-    BlockdevCreateJob *s = opaque;
-
-    job_progress_set_remaining(&s->common, 1);
-    s->ret = s->drv->bdrv_co_create(s->opts, &s->err);
-    job_progress_update(&s->common, 1);
-
-    qapi_free_BlockdevCreateOptions(s->opts);
-    job_defer_to_main_loop(&s->common, blockdev_create_complete, NULL);
-}
-
-static const JobDriver blockdev_create_job_driver = {
-    .instance_size = sizeof(BlockdevCreateJob),
-    .job_type      = JOB_TYPE_CREATE,
-    .start         = blockdev_create_run,
-};
-
-void qmp_blockdev_create(const char *job_id, BlockdevCreateOptions *options,
-                         Error **errp)
-{
-    BlockdevCreateJob *s;
     const char *fmt = BlockdevDriver_str(options->driver);
     BlockDriver *drv = bdrv_find_format(fmt);
+    Coroutine *co;
+    BlockdevCreateCo cco;
 
     /* If the driver is in the schema, we know that it exists. But it may not
      * be whitelisted. */
@@ -78,24 +55,22 @@ void qmp_blockdev_create(const char *job_id, BlockdevCreateOptions *options,
         return;
     }
 
-    /* Error out if the driver doesn't support .bdrv_co_create */
+    /* Call callback if it exists */
     if (!drv->bdrv_co_create) {
         error_setg(errp, "Driver does not support blockdev-create");
         return;
     }
 
-    /* Create the block job */
-    /* TODO Running in the main context. Block drivers need to error out or add
-     * locking when they use a BDS in a different AioContext. */
-    s = job_create(job_id, &blockdev_create_job_driver, NULL,
-                   qemu_get_aio_context(), JOB_DEFAULT | JOB_MANUAL_DISMISS,
-                   NULL, NULL, errp);
-    if (!s) {
-        return;
-    }
+    cco = (BlockdevCreateCo) {
+        .drv = drv,
+        .opts = options,
+        .ret = -EINPROGRESS,
+        .errp = errp,
+    };
 
-    s->drv = drv,
-    s->opts = QAPI_CLONE(BlockdevCreateOptions, options),
-
-    job_start(&s->common);
+    co = qemu_coroutine_create(bdrv_co_create_co_entry, &cco);
+    qemu_coroutine_enter(co);
+    while (cco.ret == -EINPROGRESS) {
+        aio_poll(qemu_get_aio_context(), true);
+    }
 }

block/crypto.c

@@ -21,15 +21,15 @@
 #include "qemu/osdep.h"
 
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "sysemu/block-backend.h"
 #include "crypto/block.h"
 #include "qapi/opts-visitor.h"
 #include "qapi/qapi-visit-crypto.h"
+#include "qapi/qmp/qdict.h"
 #include "qapi/qobject-input-visitor.h"
 #include "qapi/error.h"
 #include "qemu/option.h"
-#include "crypto.h"
+#include "block/crypto.h"
 
 typedef struct BlockCrypto BlockCrypto;
 
@@ -71,6 +71,8 @@ static ssize_t block_crypto_read_func(QCryptoBlock *block,
 
 
 struct BlockCryptoCreateData {
+    const char *filename;
+    QemuOpts *opts;
     BlockBackend *blk;
     uint64_t size;
 };
@@ -101,18 +103,27 @@ static ssize_t block_crypto_init_func(QCryptoBlock *block,
                                       Error **errp)
 {
     struct BlockCryptoCreateData *data = opaque;
-
-    if (data->size > INT64_MAX || headerlen > INT64_MAX - data->size) {
-        error_setg(errp, "The requested file size is too large");
-        return -EFBIG;
-    }
+    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
      */
-    return blk_truncate(data->blk, data->size + headerlen, PREALLOC_MODE_OFF,
-                        errp);
+    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;
 }
 
 
@@ -148,36 +159,102 @@ static QemuOptsList block_crypto_create_opts_luks = {
 
 
 QCryptoBlockOpenOptions *
-block_crypto_open_opts_init(QDict *opts, Error **errp)
+block_crypto_open_opts_init(QCryptoBlockFormat format,
+                            QDict *opts,
+                            Error **errp)
 {
     Visitor *v;
-    QCryptoBlockOpenOptions *ret;
+    QCryptoBlockOpenOptions *ret = NULL;
+    Error *local_err = NULL;
 
-    v = qobject_input_visitor_new_flat_confused(opts, errp);
-    if (!v) {
-        return NULL;
+    ret = g_new0(QCryptoBlockOpenOptions, 1);
+    ret->format = format;
+
+    v = qobject_input_visitor_new_keyval(QOBJECT(opts));
+
+    visit_start_struct(v, NULL, NULL, 0, &local_err);
+    if (local_err) {
+        goto out;
     }
 
-    visit_type_QCryptoBlockOpenOptions(v, NULL, &ret, errp);
+    switch (format) {
+    case Q_CRYPTO_BLOCK_FORMAT_LUKS:
+        visit_type_QCryptoBlockOptionsLUKS_members(
+            v, &ret->u.luks, &local_err);
+        break;
 
+    case Q_CRYPTO_BLOCK_FORMAT_QCOW:
+        visit_type_QCryptoBlockOptionsQCow_members(
+            v, &ret->u.qcow, &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;
 }
 
 
 QCryptoBlockCreateOptions *
-block_crypto_create_opts_init(QDict *opts, Error **errp)
+block_crypto_create_opts_init(QCryptoBlockFormat format,
+                              QDict *opts,
+                              Error **errp)
 {
     Visitor *v;
-    QCryptoBlockCreateOptions *ret;
+    QCryptoBlockCreateOptions *ret = NULL;
+    Error *local_err = NULL;
 
-    v = qobject_input_visitor_new_flat_confused(opts, errp);
-    if (!v) {
-        return NULL;
+    ret = g_new0(QCryptoBlockCreateOptions, 1);
+    ret->format = format;
+
+    v = qobject_input_visitor_new_keyval(QOBJECT(opts));
+
+    visit_start_struct(v, NULL, NULL, 0, &local_err);
+    if (local_err) {
+        goto out;
     }
 
-    visit_type_QCryptoBlockCreateOptions(v, NULL, &ret, errp);
+    switch (format) {
+    case Q_CRYPTO_BLOCK_FORMAT_LUKS:
+        visit_type_QCryptoBlockCreateOptionsLUKS_members(
+            v, &ret->u.luks, &local_err);
+        break;
 
+    case Q_CRYPTO_BLOCK_FORMAT_QCOW:
+        visit_type_QCryptoBlockOptionsQCow_members(
+            v, &ret->u.qcow, &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;
 }
@@ -215,9 +292,8 @@ static int block_crypto_open_generic(QCryptoBlockFormat format,
     }
 
     cryptoopts = qemu_opts_to_qdict(opts, NULL);
-    qdict_put_str(cryptoopts, "format", QCryptoBlockFormat_str(format));
 
-    open_opts = block_crypto_open_opts_init(cryptoopts, errp);
+    open_opts = block_crypto_open_opts_init(format, cryptoopts, errp);
     if (!open_opts) {
         goto cleanup;
     }
@@ -240,35 +316,36 @@ static int block_crypto_open_generic(QCryptoBlockFormat format,
 
     ret = 0;
  cleanup:
-    qobject_unref(cryptoopts);
+    QDECREF(cryptoopts);
     qapi_free_QCryptoBlockOpenOptions(open_opts);
     return ret;
 }
 
 
-static int block_crypto_co_create_generic(BlockDriverState *bs,
-                                          int64_t size,
-                                          QCryptoBlockCreateOptions *opts,
+static int block_crypto_create_generic(QCryptoBlockFormat format,
+                                       const char *filename,
+                                       QemuOpts *opts,
                                        Error **errp)
 {
-    int ret;
-    BlockBackend *blk;
+    int ret = -EINVAL;
+    QCryptoBlockCreateOptions *create_opts = NULL;
     QCryptoBlock *crypto = NULL;
-    struct BlockCryptoCreateData data;
+    struct BlockCryptoCreateData data = {
+        .size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                         BDRV_SECTOR_SIZE),
+        .opts = opts,
+        .filename = filename,
+    };
+    QDict *cryptoopts;
 
-    blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
+    cryptoopts = qemu_opts_to_qdict(opts, NULL);
 
-    ret = blk_insert_bs(blk, bs, errp);
-    if (ret < 0) {
-        goto cleanup;
+    create_opts = block_crypto_create_opts_init(format, cryptoopts, errp);
+    if (!create_opts) {
+        return -1;
     }
 
-    data = (struct BlockCryptoCreateData) {
-        .blk = blk,
-        .size = size,
-    };
-
-    crypto = qcrypto_block_create(opts, NULL,
+    crypto = qcrypto_block_create(create_opts, NULL,
                                   block_crypto_init_func,
                                   block_crypto_write_func,
                                   &data,
@@ -281,27 +358,24 @@ static int block_crypto_co_create_generic(BlockDriverState *bs,
 
     ret = 0;
  cleanup:
+    QDECREF(cryptoopts);
     qcrypto_block_free(crypto);
-    blk_unref(blk);
+    blk_unref(data.blk);
+    qapi_free_QCryptoBlockCreateOptions(create_opts);
     return ret;
 }
 
-static int coroutine_fn
-block_crypto_co_truncate(BlockDriverState *bs, int64_t offset,
+static int block_crypto_truncate(BlockDriverState *bs, int64_t offset,
                                  PreallocMode prealloc, Error **errp)
 {
     BlockCrypto *crypto = bs->opaque;
     uint64_t payload_offset =
         qcrypto_block_get_payload_offset(crypto->block);
-
-    if (payload_offset > INT64_MAX - offset) {
-        error_setg(errp, "The requested file size is too large");
-        return -EFBIG;
-    }
+    assert(payload_offset < (INT64_MAX - offset));
 
     offset += payload_offset;
 
-    return bdrv_co_truncate(bs->file, offset, prealloc, errp);
+    return bdrv_truncate(bs->file, offset, prealloc, errp);
 }
 
 static void block_crypto_close(BlockDriverState *bs)
@@ -463,10 +537,7 @@ static int64_t block_crypto_getlength(BlockDriverState *bs)
 
     uint64_t offset = qcrypto_block_get_payload_offset(crypto->block);
     assert(offset < INT64_MAX);
-
-    if (offset > len) {
-        return -EIO;
-    }
+    assert(offset < len);
 
     len -= offset;
 
@@ -491,88 +562,12 @@ static int block_crypto_open_luks(BlockDriverState *bs,
                                      bs, options, flags, errp);
 }
 
-static int coroutine_fn
-block_crypto_co_create_luks(BlockdevCreateOptions *create_options, Error **errp)
-{
-    BlockdevCreateOptionsLUKS *luks_opts;
-    BlockDriverState *bs = NULL;
-    QCryptoBlockCreateOptions create_opts;
-    int ret;
-
-    assert(create_options->driver == BLOCKDEV_DRIVER_LUKS);
-    luks_opts = &create_options->u.luks;
-
-    bs = bdrv_open_blockdev_ref(luks_opts->file, errp);
-    if (bs == NULL) {
-        return -EIO;
-    }
-
-    create_opts = (QCryptoBlockCreateOptions) {
-        .format = Q_CRYPTO_BLOCK_FORMAT_LUKS,
-        .u.luks = *qapi_BlockdevCreateOptionsLUKS_base(luks_opts),
-    };
-
-    ret = block_crypto_co_create_generic(bs, luks_opts->size, &create_opts,
-                                         errp);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    ret = 0;
-fail:
-    bdrv_unref(bs);
-    return ret;
-}
-
 static int coroutine_fn block_crypto_co_create_opts_luks(const char *filename,
                                                          QemuOpts *opts,
                                                          Error **errp)
 {
-    QCryptoBlockCreateOptions *create_opts = NULL;
-    BlockDriverState *bs = NULL;
-    QDict *cryptoopts;
-    int64_t size;
-    int ret;
-
-    /* Parse options */
-    size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
-
-    cryptoopts = qemu_opts_to_qdict_filtered(opts, NULL,
-                                             &block_crypto_create_opts_luks,
-                                             true);
-
-    qdict_put_str(cryptoopts, "format", "luks");
-    create_opts = block_crypto_create_opts_init(cryptoopts, errp);
-    if (!create_opts) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* Create protocol layer */
-    ret = bdrv_create_file(filename, opts, errp);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    bs = bdrv_open(filename, NULL, NULL,
-                   BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
-    if (!bs) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* Create format layer */
-    ret = block_crypto_co_create_generic(bs, size, create_opts, errp);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    ret = 0;
-fail:
-    bdrv_unref(bs);
-    qapi_free_QCryptoBlockCreateOptions(create_opts);
-    qobject_unref(cryptoopts);
-    return ret;
+    return block_crypto_create_generic(Q_CRYPTO_BLOCK_FORMAT_LUKS,
+                                       filename, opts, errp);
 }
 
 static int block_crypto_get_info_luks(BlockDriverState *bs,
@@ -628,9 +623,8 @@ BlockDriver bdrv_crypto_luks = {
     .bdrv_open          = block_crypto_open_luks,
     .bdrv_close         = block_crypto_close,
     .bdrv_child_perm    = bdrv_format_default_perms,
-    .bdrv_co_create     = block_crypto_co_create_luks,
     .bdrv_co_create_opts = block_crypto_co_create_opts_luks,
-    .bdrv_co_truncate   = block_crypto_co_truncate,
+    .bdrv_truncate      = block_crypto_truncate,
     .create_opts        = &block_crypto_create_opts_luks,
 
     .bdrv_reopen_prepare = block_crypto_reopen_prepare,

block/crypto.h

@@ -89,9 +89,13 @@
     }
 
 QCryptoBlockCreateOptions *
-block_crypto_create_opts_init(QDict *opts, Error **errp);
+block_crypto_create_opts_init(QCryptoBlockFormat format,
+                              QDict *opts,
+                              Error **errp);
 
 QCryptoBlockOpenOptions *
-block_crypto_open_opts_init(QDict *opts, Error **errp);
+block_crypto_open_opts_init(QCryptoBlockFormat format,
+                            QDict *opts,
+                            Error **errp);
 
 #endif /* BLOCK_CRYPTO_H__ */

block/dirty-bitmap.c

@@ -40,8 +40,6 @@ struct BdrvDirtyBitmap {
     QemuMutex *mutex;
     HBitmap *bitmap;            /* Dirty bitmap implementation */
     HBitmap *meta;              /* Meta dirty bitmap */
-    bool qmp_locked;            /* Bitmap is locked, it can't be modified
-                                   through QMP */
     BdrvDirtyBitmap *successor; /* Anonymous child; implies frozen status */
     char *name;                 /* Optional non-empty unique ID */
     int64_t size;               /* Size of the bitmap, in bytes */
@@ -97,6 +95,15 @@ BdrvDirtyBitmap *bdrv_find_dirty_bitmap(BlockDriverState *bs, const char *name)
     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;
+    bitmap->persistent = false;
+}
+
 /* Called with BQL taken.  */
 BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs,
                                           uint32_t granularity,
@@ -176,18 +183,6 @@ bool bdrv_dirty_bitmap_frozen(BdrvDirtyBitmap *bitmap)
     return bitmap->successor;
 }
 
-void bdrv_dirty_bitmap_set_qmp_locked(BdrvDirtyBitmap *bitmap, bool qmp_locked)
-{
-    qemu_mutex_lock(bitmap->mutex);
-    bitmap->qmp_locked = qmp_locked;
-    qemu_mutex_unlock(bitmap->mutex);
-}
-
-bool bdrv_dirty_bitmap_qmp_locked(BdrvDirtyBitmap *bitmap)
-{
-    return bitmap->qmp_locked;
-}
-
 /* Called with BQL taken.  */
 bool bdrv_dirty_bitmap_enabled(BdrvDirtyBitmap *bitmap)
 {
@@ -199,8 +194,6 @@ DirtyBitmapStatus bdrv_dirty_bitmap_status(BdrvDirtyBitmap *bitmap)
 {
     if (bdrv_dirty_bitmap_frozen(bitmap)) {
         return DIRTY_BITMAP_STATUS_FROZEN;
-    } else if (bdrv_dirty_bitmap_qmp_locked(bitmap)) {
-        return DIRTY_BITMAP_STATUS_LOCKED;
     } else if (!bdrv_dirty_bitmap_enabled(bitmap)) {
         return DIRTY_BITMAP_STATUS_DISABLED;
     } else {
@@ -241,33 +234,6 @@ int bdrv_dirty_bitmap_create_successor(BlockDriverState *bs,
     return 0;
 }
 
-void bdrv_enable_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap)
-{
-    assert(!bdrv_dirty_bitmap_frozen(bitmap));
-    bitmap->disabled = false;
-}
-
-/* Called with BQL taken. */
-void bdrv_dirty_bitmap_enable_successor(BdrvDirtyBitmap *bitmap)
-{
-    assert(bitmap->mutex == bitmap->successor->mutex);
-    qemu_mutex_lock(bitmap->mutex);
-    bdrv_enable_dirty_bitmap_locked(bitmap->successor);
-    qemu_mutex_unlock(bitmap->mutex);
-}
-
-/* Called within bdrv_dirty_bitmap_lock..unlock and with BQL taken.  */
-static void bdrv_release_dirty_bitmap_locked(BdrvDirtyBitmap *bitmap)
-{
-    assert(!bitmap->active_iterators);
-    assert(!bdrv_dirty_bitmap_frozen(bitmap));
-    assert(!bitmap->meta);
-    QLIST_REMOVE(bitmap, list);
-    hbitmap_free(bitmap->bitmap);
-    g_free(bitmap->name);
-    g_free(bitmap);
-}
-
 /**
  * For a bitmap with a successor, yield our name to the successor,
  * delete the old bitmap, and return a handle to the new bitmap.
@@ -301,9 +267,9 @@ BdrvDirtyBitmap *bdrv_dirty_bitmap_abdicate(BlockDriverState *bs,
  * 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 within bdrv_dirty_bitmap_lock..unlock and with BQL taken.
+ * Called with BQL taken.
  */
-BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap_locked(BlockDriverState *bs,
+BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap(BlockDriverState *bs,
                                            BdrvDirtyBitmap *parent,
                                            Error **errp)
 {
@@ -318,26 +284,12 @@ BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap_locked(BlockDriverState *bs,
         error_setg(errp, "Merging of parent and successor bitmap failed");
         return NULL;
     }
-    bdrv_release_dirty_bitmap_locked(successor);
+    bdrv_release_dirty_bitmap(bs, successor);
     parent->successor = NULL;
 
     return parent;
 }
 
-/* Called with BQL taken. */
-BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap(BlockDriverState *bs,
-                                           BdrvDirtyBitmap *parent,
-                                           Error **errp)
-{
-    BdrvDirtyBitmap *ret;
-
-    qemu_mutex_lock(parent->mutex);
-    ret = bdrv_reclaim_dirty_bitmap_locked(bs, parent, errp);
-    qemu_mutex_unlock(parent->mutex);
-
-    return ret;
-}
-
 /**
  * Truncates _all_ bitmaps attached to a BDS.
  * Called with BQL taken.
@@ -356,12 +308,45 @@ void bdrv_dirty_bitmap_truncate(BlockDriverState *bs, int64_t bytes)
     bdrv_dirty_bitmaps_unlock(bs);
 }
 
+static bool bdrv_dirty_bitmap_has_name(BdrvDirtyBitmap *bitmap)
+{
+    return !!bdrv_dirty_bitmap_name(bitmap);
+}
+
+/* Called with BQL taken.  */
+static void bdrv_do_release_matching_dirty_bitmap(
+    BlockDriverState *bs, BdrvDirtyBitmap *bitmap,
+    bool (*cond)(BdrvDirtyBitmap *bitmap))
+{
+    BdrvDirtyBitmap *bm, *next;
+    bdrv_dirty_bitmaps_lock(bs);
+    QLIST_FOREACH_SAFE(bm, &bs->dirty_bitmaps, list, next) {
+        if ((!bitmap || bm == bitmap) && (!cond || cond(bm))) {
+            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_dirty_bitmaps_lock(bs);
-    bdrv_release_dirty_bitmap_locked(bitmap);
-    bdrv_dirty_bitmaps_unlock(bs);
+    bdrv_do_release_matching_dirty_bitmap(bs, bitmap, NULL);
 }
 
 /**
@@ -372,15 +357,7 @@ void bdrv_release_dirty_bitmap(BlockDriverState *bs, BdrvDirtyBitmap *bitmap)
  */
 void bdrv_release_named_dirty_bitmaps(BlockDriverState *bs)
 {
-    BdrvDirtyBitmap *bm, *next;
-
-    bdrv_dirty_bitmaps_lock(bs);
-    QLIST_FOREACH_SAFE(bm, &bs->dirty_bitmaps, list, next) {
-        if (bdrv_dirty_bitmap_name(bm)) {
-            bdrv_release_dirty_bitmap_locked(bm);
-        }
-    }
-    bdrv_dirty_bitmaps_unlock(bs);
+    bdrv_do_release_matching_dirty_bitmap(bs, NULL, bdrv_dirty_bitmap_has_name);
 }
 
 /**
@@ -388,19 +365,11 @@ void bdrv_release_named_dirty_bitmaps(BlockDriverState *bs)
  * bdrv_inactivate_recurse()).
  * There must not be any frozen bitmaps attached.
  * This function does not remove persistent bitmaps from the storage.
- * Called with BQL taken.
  */
 void bdrv_release_persistent_dirty_bitmaps(BlockDriverState *bs)
 {
-    BdrvDirtyBitmap *bm, *next;
-
-    bdrv_dirty_bitmaps_lock(bs);
-    QLIST_FOREACH_SAFE(bm, &bs->dirty_bitmaps, list, next) {
-        if (bdrv_dirty_bitmap_get_persistance(bm)) {
-            bdrv_release_dirty_bitmap_locked(bm);
-        }
-    }
-    bdrv_dirty_bitmaps_unlock(bs);
+    bdrv_do_release_matching_dirty_bitmap(bs, NULL,
+                                          bdrv_dirty_bitmap_get_persistance);
 }
 
 /**
@@ -420,19 +389,18 @@ void bdrv_remove_persistent_dirty_bitmap(BlockDriverState *bs,
     }
 }
 
+/* Called with BQL taken.  */
 void bdrv_disable_dirty_bitmap(BdrvDirtyBitmap *bitmap)
 {
-    bdrv_dirty_bitmap_lock(bitmap);
     assert(!bdrv_dirty_bitmap_frozen(bitmap));
     bitmap->disabled = true;
-    bdrv_dirty_bitmap_unlock(bitmap);
 }
 
+/* Called with BQL taken.  */
 void bdrv_enable_dirty_bitmap(BdrvDirtyBitmap *bitmap)
 {
-    bdrv_dirty_bitmap_lock(bitmap);
-    bdrv_enable_dirty_bitmap_locked(bitmap);
-    bdrv_dirty_bitmap_unlock(bitmap);
+    assert(!bdrv_dirty_bitmap_frozen(bitmap));
+    bitmap->disabled = false;
 }
 
 BlockDirtyInfoList *bdrv_query_dirty_bitmaps(BlockDriverState *bs)
@@ -525,62 +493,7 @@ void bdrv_dirty_iter_free(BdrvDirtyBitmapIter *iter)
 
 int64_t bdrv_dirty_iter_next(BdrvDirtyBitmapIter *iter)
 {
-    return hbitmap_iter_next(&iter->hbi, true);
-}
-
-/**
- * Return the next consecutively dirty area in the dirty bitmap
- * belonging to the given iterator @iter.
- *
- * @max_offset: Maximum value that may be returned for
- *              *offset + *bytes
- * @offset:     Will contain the start offset of the next dirty area
- * @bytes:      Will contain the length of the next dirty area
- *
- * Returns: True if a dirty area could be found before max_offset
- *          (which means that *offset and *bytes then contain valid
- *          values), false otherwise.
- *
- * Note that @iter is never advanced if false is returned.  If an area
- * is found (which means that true is returned), it will be advanced
- * past that area.
- */
-bool bdrv_dirty_iter_next_area(BdrvDirtyBitmapIter *iter, uint64_t max_offset,
-                               uint64_t *offset, int *bytes)
-{
-    uint32_t granularity = bdrv_dirty_bitmap_granularity(iter->bitmap);
-    uint64_t gran_max_offset;
-    int64_t ret;
-    int size;
-
-    if (max_offset == iter->bitmap->size) {
-        /* If max_offset points to the image end, round it up by the
-         * bitmap granularity */
-        gran_max_offset = ROUND_UP(max_offset, granularity);
-    } else {
-        gran_max_offset = max_offset;
-    }
-
-    ret = hbitmap_iter_next(&iter->hbi, false);
-    if (ret < 0 || ret + granularity > gran_max_offset) {
-        return false;
-    }
-
-    *offset = ret;
-    size = 0;
-
-    assert(granularity <= INT_MAX);
-
-    do {
-        /* Advance iterator */
-        ret = hbitmap_iter_next(&iter->hbi, true);
-        size += granularity;
-    } while (ret + granularity <= gran_max_offset &&
-             hbitmap_iter_next(&iter->hbi, false) == ret + granularity &&
-             size <= INT_MAX - granularity);
-
-    *bytes = MIN(size, max_offset - *offset);
-    return true;
+    return hbitmap_iter_next(&iter->hbi);
 }
 
 /* Called within bdrv_dirty_bitmap_lock..unlock */
@@ -789,21 +702,3 @@ int64_t bdrv_dirty_bitmap_next_zero(BdrvDirtyBitmap *bitmap, uint64_t offset)
 {
     return hbitmap_next_zero(bitmap->bitmap, offset);
 }
-
-void bdrv_merge_dirty_bitmap(BdrvDirtyBitmap *dest, const BdrvDirtyBitmap *src,
-                             Error **errp)
-{
-    /* only bitmaps from one bds are supported */
-    assert(dest->mutex == src->mutex);
-
-    qemu_mutex_lock(dest->mutex);
-
-    assert(bdrv_dirty_bitmap_enabled(dest));
-    assert(!bdrv_dirty_bitmap_readonly(dest));
-
-    if (!hbitmap_merge(dest->bitmap, src->bitmap)) {
-        error_setg(errp, "Bitmaps are incompatible and can't be merged");
-    }
-
-    qemu_mutex_unlock(dest->mutex);
-}

block/file-win32.c

@@ -162,7 +162,7 @@ static BlockAIOCB *paio_submit(BlockDriverState *bs, HANDLE hfile,
     acb->aio_nbytes = count;
     acb->aio_offset = offset;
 
-    trace_file_paio_submit(acb, opaque, offset, count, type);
+    trace_paio_submit(acb, opaque, offset, count, type);
     pool = aio_get_thread_pool(bdrv_get_aio_context(bs));
     return thread_pool_submit_aio(pool, aio_worker, acb, cb, opaque);
 }
@@ -251,11 +251,7 @@ static void raw_probe_alignment(BlockDriverState *bs, Error **errp)
                          &dg.Geometry.BytesPerSector,
                          &freeClusters, &totalClusters);
         bs->bl.request_alignment = dg.Geometry.BytesPerSector;
-        return;
     }
-
-    /* XXX Does Windows support AIO on less than 512-byte alignment? */
-    bs->bl.request_alignment = 512;
 }
 
 static void raw_parse_flags(int flags, bool use_aio, int *access_flags,
@@ -414,32 +410,32 @@ fail:
     return ret;
 }
 
-static BlockAIOCB *raw_aio_preadv(BlockDriverState *bs,
-                                  uint64_t offset, uint64_t bytes,
-                                  QEMUIOVector *qiov, int flags,
+static BlockAIOCB *raw_aio_readv(BlockDriverState *bs,
+                         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
                          BlockCompletionFunc *cb, void *opaque)
 {
     BDRVRawState *s = bs->opaque;
     if (s->aio) {
-        return win32_aio_submit(bs, s->aio, s->hfile, offset, bytes, qiov,
-                                cb, opaque, QEMU_AIO_READ);
+        return win32_aio_submit(bs, s->aio, s->hfile, sector_num, qiov,
+                                nb_sectors, cb, opaque, QEMU_AIO_READ);
     } else {
-        return paio_submit(bs, s->hfile, offset, qiov, bytes,
+        return paio_submit(bs, s->hfile, sector_num << BDRV_SECTOR_BITS, qiov,
+                           nb_sectors << BDRV_SECTOR_BITS,
                            cb, opaque, QEMU_AIO_READ);
     }
 }
 
-static BlockAIOCB *raw_aio_pwritev(BlockDriverState *bs,
-                                   uint64_t offset, uint64_t bytes,
-                                   QEMUIOVector *qiov, int flags,
+static BlockAIOCB *raw_aio_writev(BlockDriverState *bs,
+                          int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
                           BlockCompletionFunc *cb, void *opaque)
 {
     BDRVRawState *s = bs->opaque;
     if (s->aio) {
-        return win32_aio_submit(bs, s->aio, s->hfile, offset, bytes, qiov,
-                                cb, opaque, QEMU_AIO_WRITE);
+        return win32_aio_submit(bs, s->aio, s->hfile, sector_num, qiov,
+                                nb_sectors, cb, opaque, QEMU_AIO_WRITE);
     } else {
-        return paio_submit(bs, s->hfile, offset, qiov, bytes,
+        return paio_submit(bs, s->hfile, sector_num << BDRV_SECTOR_BITS, qiov,
+                           nb_sectors << BDRV_SECTOR_BITS,
                            cb, opaque, QEMU_AIO_WRITE);
     }
 }
@@ -467,7 +463,7 @@ static void raw_close(BlockDriverState *bs)
     }
 }
 
-static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset,
+static int raw_truncate(BlockDriverState *bs, int64_t offset,
                         PreallocMode prealloc, Error **errp)
 {
     BDRVRawState *s = bs->opaque;
@@ -636,11 +632,11 @@ BlockDriver bdrv_file = {
     .bdrv_co_create_opts = raw_co_create_opts,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
 
-    .bdrv_aio_preadv    = raw_aio_preadv,
-    .bdrv_aio_pwritev   = raw_aio_pwritev,
+    .bdrv_aio_readv     = raw_aio_readv,
+    .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush     = raw_aio_flush,
 
-    .bdrv_co_truncate   = raw_co_truncate,
+    .bdrv_truncate	= raw_truncate,
     .bdrv_getlength	= raw_getlength,
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
@@ -712,12 +708,6 @@ static void hdev_parse_filename(const char *filename, QDict *options,
     bdrv_parse_filename_strip_prefix(filename, "host_device:", options);
 }
 
-static void hdev_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    /* XXX Does Windows support AIO on less than 512-byte alignment? */
-    bs->bl.request_alignment = 512;
-}
-
 static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
                      Error **errp)
 {
@@ -803,10 +793,9 @@ static BlockDriver bdrv_host_device = {
     .bdrv_probe_device	= hdev_probe_device,
     .bdrv_file_open	= hdev_open,
     .bdrv_close		= raw_close,
-    .bdrv_refresh_limits = hdev_refresh_limits,
 
-    .bdrv_aio_preadv    = raw_aio_preadv,
-    .bdrv_aio_pwritev   = raw_aio_pwritev,
+    .bdrv_aio_readv     = raw_aio_readv,
+    .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush     = raw_aio_flush,
 
     .bdrv_detach_aio_context = raw_detach_aio_context,

block/gluster.c

@@ -11,7 +11,6 @@
 #include "qemu/osdep.h"
 #include <glusterfs/api/glfs.h>
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qerror.h"
@@ -168,12 +167,7 @@ static QemuOptsList runtime_unix_opts = {
         {
             .name = GLUSTER_OPT_SOCKET,
             .type = QEMU_OPT_STRING,
-            .help = "socket file path (legacy)",
-        },
-        {
-            .name = GLUSTER_OPT_PATH,
-            .type = QEMU_OPT_STRING,
-            .help = "socket file path (QAPI)",
+            .help = "socket file path)",
         },
         { /* end of list */ }
     },
@@ -621,18 +615,10 @@ static int qemu_gluster_parse_json(BlockdevOptionsGluster *gconf,
                 goto out;
             }
 
-            ptr = qemu_opt_get(opts, GLUSTER_OPT_PATH);
-            if (!ptr) {
             ptr = qemu_opt_get(opts, GLUSTER_OPT_SOCKET);
-            } else if (qemu_opt_get(opts, GLUSTER_OPT_SOCKET)) {
-                error_setg(&local_err,
-                           "Conflicting parameters 'path' and 'socket'");
-                error_append_hint(&local_err, GERR_INDEX_HINT, i);
-                goto out;
-            }
             if (!ptr) {
                 error_setg(&local_err, QERR_MISSING_PARAMETER,
-                           GLUSTER_OPT_PATH);
+                           GLUSTER_OPT_SOCKET);
                 error_append_hint(&local_err, GERR_INDEX_HINT, i);
                 goto out;
             }
@@ -651,7 +637,7 @@ static int qemu_gluster_parse_json(BlockdevOptionsGluster *gconf,
         }
         gsconf = NULL;
 
-        qobject_unref(backing_options);
+        QDECREF(backing_options);
         backing_options = NULL;
         g_free(str);
         str = NULL;
@@ -664,7 +650,7 @@ out:
     qapi_free_SocketAddress(gsconf);
     qemu_opts_del(opts);
     g_free(str);
-    qobject_unref(backing_options);
+    QDECREF(backing_options);
     errno = EINVAL;
     return -errno;
 }
@@ -679,7 +665,7 @@ static int qemu_gluster_parse(BlockdevOptionsGluster *gconf,
     if (filename) {
         ret = qemu_gluster_parse_uri(gconf, filename);
         if (ret < 0) {
-            error_setg(errp, "invalid URI %s", filename);
+            error_setg(errp, "invalid URI");
             error_append_hint(errp, "Usage: file=gluster[+transport]://"
                                     "[host[:port]]volume/path[?socket=...]"
                                     "[,file.debug=N]"
@@ -698,7 +684,7 @@ static int qemu_gluster_parse(BlockdevOptionsGluster *gconf,
                              "file.server.0.host=1.2.3.4,"
                              "file.server.0.port=24007,"
                              "file.server.1.transport=unix,"
-                             "file.server.1.path=/var/run/glusterd.socket ..."
+                             "file.server.1.socket=/var/run/glusterd.socket ..."
                              "\n");
             return ret;
         }
@@ -1177,10 +1163,8 @@ static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,
     return acb.ret;
 }
 
-static coroutine_fn int qemu_gluster_co_truncate(BlockDriverState *bs,
-                                                 int64_t offset,
-                                                 PreallocMode prealloc,
-                                                 Error **errp)
+static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset,
+                                 PreallocMode prealloc, Error **errp)
 {
     BDRVGlusterState *s = bs->opaque;
     return qemu_gluster_do_truncate(s->fd, offset, prealloc, errp);
@@ -1197,10 +1181,8 @@ static coroutine_fn int qemu_gluster_co_readv(BlockDriverState *bs,
 static coroutine_fn int qemu_gluster_co_writev(BlockDriverState *bs,
                                                int64_t sector_num,
                                                int nb_sectors,
-                                               QEMUIOVector *qiov,
-                                               int flags)
+                                               QEMUIOVector *qiov)
 {
-    assert(!flags);
     return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 1);
 }
 
@@ -1501,7 +1483,7 @@ static BlockDriver bdrv_gluster = {
     .bdrv_co_create_opts          = qemu_gluster_co_create_opts,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_co_truncate             = qemu_gluster_co_truncate,
+    .bdrv_truncate                = qemu_gluster_truncate,
     .bdrv_co_readv                = qemu_gluster_co_readv,
     .bdrv_co_writev               = qemu_gluster_co_writev,
     .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
@@ -1530,7 +1512,7 @@ static BlockDriver bdrv_gluster_tcp = {
     .bdrv_co_create_opts          = qemu_gluster_co_create_opts,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_co_truncate             = qemu_gluster_co_truncate,
+    .bdrv_truncate                = qemu_gluster_truncate,
     .bdrv_co_readv                = qemu_gluster_co_readv,
     .bdrv_co_writev               = qemu_gluster_co_writev,
     .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
@@ -1559,7 +1541,7 @@ static BlockDriver bdrv_gluster_unix = {
     .bdrv_co_create_opts          = qemu_gluster_co_create_opts,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_co_truncate             = qemu_gluster_co_truncate,
+    .bdrv_truncate                = qemu_gluster_truncate,
     .bdrv_co_readv                = qemu_gluster_co_readv,
     .bdrv_co_writev               = qemu_gluster_co_writev,
     .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,
@@ -1594,7 +1576,7 @@ static BlockDriver bdrv_gluster_rdma = {
     .bdrv_co_create_opts          = qemu_gluster_co_create_opts,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
-    .bdrv_co_truncate             = qemu_gluster_co_truncate,
+    .bdrv_truncate                = qemu_gluster_truncate,
     .bdrv_co_readv                = qemu_gluster_co_readv,
     .bdrv_co_writev               = qemu_gluster_co_writev,
     .bdrv_co_flush_to_disk        = qemu_gluster_co_flush_to_disk,

block/iscsi.c

@@ -33,7 +33,6 @@
 #include "qemu/bitops.h"
 #include "qemu/bitmap.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "scsi/constants.h"
 #include "qemu/iov.h"
 #include "qemu/option.h"
@@ -44,7 +43,6 @@
 #include "qapi/qmp/qstring.h"
 #include "crypto/secret.h"
 #include "scsi/utils.h"
-#include "trace.h"
 
 /* Conflict between scsi/utils.h and libiscsi! :( */
 #define SCSI_XFER_NONE ISCSI_XFER_NONE
@@ -70,7 +68,6 @@ typedef struct IscsiLun {
     QemuMutex mutex;
     struct scsi_inquiry_logical_block_provisioning lbp;
     struct scsi_inquiry_block_limits bl;
-    struct scsi_inquiry_device_designator *dd;
     unsigned char *zeroblock;
     /* The allocmap tracks which clusters (pages) on the iSCSI target are
      * allocated and which are not. In case a target returns zeros for
@@ -558,19 +555,8 @@ static inline bool iscsi_allocmap_is_valid(IscsiLun *iscsilun,
                                offset / iscsilun->cluster_size) == size);
 }
 
-static void coroutine_fn iscsi_co_wait_for_task(IscsiTask *iTask,
-                                                IscsiLun *iscsilun)
-{
-    while (!iTask->complete) {
-        iscsi_set_events(iscsilun);
-        qemu_mutex_unlock(&iscsilun->mutex);
-        qemu_coroutine_yield();
-        qemu_mutex_lock(&iscsilun->mutex);
-    }
-}
-
 static int coroutine_fn
-iscsi_co_writev(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
+iscsi_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
                       QEMUIOVector *iov, int flags)
 {
     IscsiLun *iscsilun = bs->opaque;
@@ -630,7 +616,12 @@ retry:
     scsi_task_set_iov_out(iTask.task, (struct scsi_iovec *) iov->iov,
                           iov->niov);
 #endif
-    iscsi_co_wait_for_task(&iTask, iscsilun);
+    while (!iTask.complete) {
+        iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
+        qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
+    }
 
     if (iTask.task != NULL) {
         scsi_free_scsi_task(iTask.task);
@@ -701,7 +692,13 @@ retry:
         ret = -ENOMEM;
         goto out_unlock;
     }
-    iscsi_co_wait_for_task(&iTask, iscsilun);
+
+    while (!iTask.complete) {
+        iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
+        qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
+    }
 
     if (iTask.do_retry) {
         if (iTask.task != NULL) {
@@ -735,7 +732,7 @@ retry:
         goto out_unlock;
     }
 
-    *pnum = (int64_t) lbasd->num_blocks * iscsilun->block_size;
+    *pnum = lbasd->num_blocks * iscsilun->block_size;
 
     if (lbasd->provisioning == SCSI_PROVISIONING_TYPE_DEALLOCATED ||
         lbasd->provisioning == SCSI_PROVISIONING_TYPE_ANCHORED) {
@@ -865,8 +862,13 @@ retry:
 #if LIBISCSI_API_VERSION < (20160603)
     scsi_task_set_iov_in(iTask.task, (struct scsi_iovec *) iov->iov, iov->niov);
 #endif
+    while (!iTask.complete) {
+        iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
+        qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
+    }
 
-    iscsi_co_wait_for_task(&iTask, iscsilun);
     if (iTask.task != NULL) {
         scsi_free_scsi_task(iTask.task);
         iTask.task = NULL;
@@ -903,7 +905,12 @@ retry:
         return -ENOMEM;
     }
 
-    iscsi_co_wait_for_task(&iTask, iscsilun);
+    while (!iTask.complete) {
+        iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
+        qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
+    }
 
     if (iTask.task != NULL) {
         scsi_free_scsi_task(iTask.task);
@@ -1135,7 +1142,12 @@ retry:
         goto out_unlock;
     }
 
-    iscsi_co_wait_for_task(&iTask, iscsilun);
+    while (!iTask.complete) {
+        iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
+        qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
+    }
 
     if (iTask.task != NULL) {
         scsi_free_scsi_task(iTask.task);
@@ -1231,7 +1243,12 @@ retry:
         return -ENOMEM;
     }
 
-    iscsi_co_wait_for_task(&iTask, iscsilun);
+    while (!iTask.complete) {
+        iscsi_set_events(iscsilun);
+        qemu_mutex_unlock(&iscsilun->mutex);
+        qemu_coroutine_yield();
+        qemu_mutex_lock(&iscsilun->mutex);
+    }
 
     if (iTask.status == SCSI_STATUS_CHECK_CONDITION &&
         iTask.task->sense.key == SCSI_SENSE_ILLEGAL_REQUEST &&
@@ -1715,34 +1732,14 @@ static QemuOptsList runtime_opts = {
             .name = "timeout",
             .type = QEMU_OPT_NUMBER,
         },
+        {
+            .name = "filename",
+            .type = QEMU_OPT_STRING,
+        },
         { /* end of list */ }
     },
 };
 
-static void iscsi_save_designator(IscsiLun *lun,
-                                  struct scsi_inquiry_device_identification *inq_di)
-{
-    struct scsi_inquiry_device_designator *desig, *copy = NULL;
-
-    for (desig = inq_di->designators; desig; desig = desig->next) {
-        if (desig->association ||
-            desig->designator_type > SCSI_DESIGNATOR_TYPE_NAA) {
-            continue;
-        }
-        /* NAA works better than T10 vendor ID based designator. */
-        if (!copy || copy->designator_type < desig->designator_type) {
-            copy = desig;
-        }
-    }
-    if (copy) {
-        lun->dd = g_new(struct scsi_inquiry_device_designator, 1);
-        *lun->dd = *copy;
-        lun->dd->next = NULL;
-        lun->dd->designator = g_malloc(copy->designator_length);
-        memcpy(lun->dd->designator, copy->designator, copy->designator_length);
-    }
-}
-
 static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
                       Error **errp)
 {
@@ -1754,12 +1751,27 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
     char *initiator_name = NULL;
     QemuOpts *opts;
     Error *local_err = NULL;
-    const char *transport_name, *portal, *target;
+    const char *transport_name, *portal, *target, *filename;
 #if LIBISCSI_API_VERSION >= (20160603)
     enum iscsi_transport_type transport;
 #endif
     int i, ret = 0, timeout = 0, lun;
 
+    /* If we are given a filename, parse the filename, with precedence given to
+     * filename encoded options */
+    filename = qdict_get_try_str(options, "filename");
+    if (filename) {
+        warn_report("'filename' option specified. "
+                    "This is an unsupported option, and may be deprecated "
+                    "in the future");
+        iscsi_parse_filename(filename, options, &local_err);
+        if (local_err) {
+            ret = -EINVAL;
+            error_propagate(errp, local_err);
+            goto exit;
+        }
+    }
+
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
@@ -1910,7 +1922,6 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
         struct scsi_task *inq_task;
         struct scsi_inquiry_logical_block_provisioning *inq_lbp;
         struct scsi_inquiry_block_limits *inq_bl;
-        struct scsi_inquiry_device_identification *inq_di;
         switch (inq_vpd->pages[i]) {
         case SCSI_INQUIRY_PAGECODE_LOGICAL_BLOCK_PROVISIONING:
             inq_task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
@@ -1936,17 +1947,6 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
                    sizeof(struct scsi_inquiry_block_limits));
             scsi_free_scsi_task(inq_task);
             break;
-        case SCSI_INQUIRY_PAGECODE_DEVICE_IDENTIFICATION:
-            inq_task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 1,
-                                    SCSI_INQUIRY_PAGECODE_DEVICE_IDENTIFICATION,
-                                    (void **) &inq_di, errp);
-            if (inq_task == NULL) {
-                ret = -EINVAL;
-                goto out;
-            }
-            iscsi_save_designator(iscsilun, inq_di);
-            scsi_free_scsi_task(inq_task);
-            break;
         default:
             break;
         }
@@ -1989,7 +1989,7 @@ out:
         }
         memset(iscsilun, 0, sizeof(IscsiLun));
     }
-
+exit:
     return ret;
 }
 
@@ -2003,10 +2003,6 @@ static void iscsi_close(BlockDriverState *bs)
         iscsi_logout_sync(iscsi);
     }
     iscsi_destroy_context(iscsi);
-    if (iscsilun->dd) {
-        g_free(iscsilun->dd->designator);
-        g_free(iscsilun->dd);
-    }
     g_free(iscsilun->zeroblock);
     iscsi_allocmap_free(iscsilun);
     qemu_mutex_destroy(&iscsilun->mutex);
@@ -2086,7 +2082,7 @@ static void iscsi_reopen_commit(BDRVReopenState *reopen_state)
     }
 }
 
-static int coroutine_fn iscsi_co_truncate(BlockDriverState *bs, int64_t offset,
+static int iscsi_truncate(BlockDriverState *bs, int64_t offset,
                           PreallocMode prealloc, Error **errp)
 {
     IscsiLun *iscsilun = bs->opaque;
@@ -2147,7 +2143,7 @@ static int coroutine_fn iscsi_co_create_opts(const char *filename, QemuOpts *opt
     } else {
         ret = iscsi_open(bs, bs_options, 0, NULL);
     }
-    qobject_unref(bs_options);
+    QDECREF(bs_options);
 
     if (ret != 0) {
         goto out;
@@ -2188,226 +2184,6 @@ static void coroutine_fn iscsi_co_invalidate_cache(BlockDriverState *bs,
     iscsi_allocmap_invalidate(iscsilun);
 }
 
-static int coroutine_fn iscsi_co_copy_range_from(BlockDriverState *bs,
-                                                 BdrvChild *src,
-                                                 uint64_t src_offset,
-                                                 BdrvChild *dst,
-                                                 uint64_t dst_offset,
-                                                 uint64_t bytes,
-                                                 BdrvRequestFlags read_flags,
-                                                 BdrvRequestFlags write_flags)
-{
-    return bdrv_co_copy_range_to(src, src_offset, dst, dst_offset, bytes,
-                                 read_flags, write_flags);
-}
-
-static struct scsi_task *iscsi_xcopy_task(int param_len)
-{
-    struct scsi_task *task;
-
-    task = g_new0(struct scsi_task, 1);
-
-    task->cdb[0]     = EXTENDED_COPY;
-    task->cdb[10]    = (param_len >> 24) & 0xFF;
-    task->cdb[11]    = (param_len >> 16) & 0xFF;
-    task->cdb[12]    = (param_len >> 8) & 0xFF;
-    task->cdb[13]    = param_len & 0xFF;
-    task->cdb_size   = 16;
-    task->xfer_dir   = SCSI_XFER_WRITE;
-    task->expxferlen = param_len;
-
-    return task;
-}
-
-static void iscsi_populate_target_desc(unsigned char *desc, IscsiLun *lun)
-{
-    struct scsi_inquiry_device_designator *dd = lun->dd;
-
-    memset(desc, 0, 32);
-    desc[0] = 0xE4; /* IDENT_DESCR_TGT_DESCR */
-    desc[4] = dd->code_set;
-    desc[5] = (dd->designator_type & 0xF)
-        | ((dd->association & 3) << 4);
-    desc[7] = dd->designator_length;
-    memcpy(desc + 8, dd->designator, MIN(dd->designator_length, 20));
-
-    desc[28] = 0;
-    desc[29] = (lun->block_size >> 16) & 0xFF;
-    desc[30] = (lun->block_size >> 8) & 0xFF;
-    desc[31] = lun->block_size & 0xFF;
-}
-
-static void iscsi_xcopy_desc_hdr(uint8_t *hdr, int dc, int cat, int src_index,
-                                 int dst_index)
-{
-    hdr[0] = 0x02; /* BLK_TO_BLK_SEG_DESCR */
-    hdr[1] = ((dc << 1) | cat) & 0xFF;
-    hdr[2] = (XCOPY_BLK2BLK_SEG_DESC_SIZE >> 8) & 0xFF;
-    /* don't account for the first 4 bytes in descriptor header*/
-    hdr[3] = (XCOPY_BLK2BLK_SEG_DESC_SIZE - 4 /* SEG_DESC_SRC_INDEX_OFFSET */) & 0xFF;
-    hdr[4] = (src_index >> 8) & 0xFF;
-    hdr[5] = src_index & 0xFF;
-    hdr[6] = (dst_index >> 8) & 0xFF;
-    hdr[7] = dst_index & 0xFF;
-}
-
-static void iscsi_xcopy_populate_desc(uint8_t *desc, int dc, int cat,
-                                      int src_index, int dst_index, int num_blks,
-                                      uint64_t src_lba, uint64_t dst_lba)
-{
-    iscsi_xcopy_desc_hdr(desc, dc, cat, src_index, dst_index);
-
-    /* The caller should verify the request size */
-    assert(num_blks < 65536);
-    desc[10] = (num_blks >> 8) & 0xFF;
-    desc[11] = num_blks & 0xFF;
-    desc[12] = (src_lba >> 56) & 0xFF;
-    desc[13] = (src_lba >> 48) & 0xFF;
-    desc[14] = (src_lba >> 40) & 0xFF;
-    desc[15] = (src_lba >> 32) & 0xFF;
-    desc[16] = (src_lba >> 24) & 0xFF;
-    desc[17] = (src_lba >> 16) & 0xFF;
-    desc[18] = (src_lba >> 8) & 0xFF;
-    desc[19] = src_lba & 0xFF;
-    desc[20] = (dst_lba >> 56) & 0xFF;
-    desc[21] = (dst_lba >> 48) & 0xFF;
-    desc[22] = (dst_lba >> 40) & 0xFF;
-    desc[23] = (dst_lba >> 32) & 0xFF;
-    desc[24] = (dst_lba >> 24) & 0xFF;
-    desc[25] = (dst_lba >> 16) & 0xFF;
-    desc[26] = (dst_lba >> 8) & 0xFF;
-    desc[27] = dst_lba & 0xFF;
-}
-
-static void iscsi_xcopy_populate_header(unsigned char *buf, int list_id, int str,
-                                        int list_id_usage, int prio,
-                                        int tgt_desc_len,
-                                        int seg_desc_len, int inline_data_len)
-{
-    buf[0] = list_id;
-    buf[1] = ((str & 1) << 5) | ((list_id_usage & 3) << 3) | (prio & 7);
-    buf[2] = (tgt_desc_len >> 8) & 0xFF;
-    buf[3] = tgt_desc_len & 0xFF;
-    buf[8] = (seg_desc_len >> 24) & 0xFF;
-    buf[9] = (seg_desc_len >> 16) & 0xFF;
-    buf[10] = (seg_desc_len >> 8) & 0xFF;
-    buf[11] = seg_desc_len & 0xFF;
-    buf[12] = (inline_data_len >> 24) & 0xFF;
-    buf[13] = (inline_data_len >> 16) & 0xFF;
-    buf[14] = (inline_data_len >> 8) & 0xFF;
-    buf[15] = inline_data_len & 0xFF;
-}
-
-static void iscsi_xcopy_data(struct iscsi_data *data,
-                             IscsiLun *src, int64_t src_lba,
-                             IscsiLun *dst, int64_t dst_lba,
-                             uint16_t num_blocks)
-{
-    uint8_t *buf;
-    const int src_offset = XCOPY_DESC_OFFSET;
-    const int dst_offset = XCOPY_DESC_OFFSET + IDENT_DESCR_TGT_DESCR_SIZE;
-    const int seg_offset = dst_offset + IDENT_DESCR_TGT_DESCR_SIZE;
-
-    data->size = XCOPY_DESC_OFFSET +
-                 IDENT_DESCR_TGT_DESCR_SIZE * 2 +
-                 XCOPY_BLK2BLK_SEG_DESC_SIZE;
-    data->data = g_malloc0(data->size);
-    buf = data->data;
-
-    /* Initialise the parameter list header */
-    iscsi_xcopy_populate_header(buf, 1, 0, 2 /* LIST_ID_USAGE_DISCARD */,
-                                0, 2 * IDENT_DESCR_TGT_DESCR_SIZE,
-                                XCOPY_BLK2BLK_SEG_DESC_SIZE,
-                                0);
-
-    /* Initialise CSCD list with one src + one dst descriptor */
-    iscsi_populate_target_desc(&buf[src_offset], src);
-    iscsi_populate_target_desc(&buf[dst_offset], dst);
-
-    /* Initialise one segment descriptor */
-    iscsi_xcopy_populate_desc(&buf[seg_offset], 0, 0, 0, 1, num_blocks,
-                              src_lba, dst_lba);
-}
-
-static int coroutine_fn iscsi_co_copy_range_to(BlockDriverState *bs,
-                                               BdrvChild *src,
-                                               uint64_t src_offset,
-                                               BdrvChild *dst,
-                                               uint64_t dst_offset,
-                                               uint64_t bytes,
-                                               BdrvRequestFlags read_flags,
-                                               BdrvRequestFlags write_flags)
-{
-    IscsiLun *dst_lun = dst->bs->opaque;
-    IscsiLun *src_lun;
-    struct IscsiTask iscsi_task;
-    struct iscsi_data data;
-    int r = 0;
-    int block_size;
-
-    if (src->bs->drv->bdrv_co_copy_range_to != iscsi_co_copy_range_to) {
-        return -ENOTSUP;
-    }
-    src_lun = src->bs->opaque;
-
-    if (!src_lun->dd || !dst_lun->dd) {
-        return -ENOTSUP;
-    }
-    if (!is_byte_request_lun_aligned(dst_offset, bytes, dst_lun)) {
-        return -ENOTSUP;
-    }
-    if (!is_byte_request_lun_aligned(src_offset, bytes, src_lun)) {
-        return -ENOTSUP;
-    }
-    if (dst_lun->block_size != src_lun->block_size ||
-        !dst_lun->block_size) {
-        return -ENOTSUP;
-    }
-
-    block_size = dst_lun->block_size;
-    if (bytes / block_size > 65535) {
-        return -ENOTSUP;
-    }
-
-    iscsi_xcopy_data(&data,
-                     src_lun, src_offset / block_size,
-                     dst_lun, dst_offset / block_size,
-                     bytes / block_size);
-
-    iscsi_co_init_iscsitask(dst_lun, &iscsi_task);
-
-    qemu_mutex_lock(&dst_lun->mutex);
-    iscsi_task.task = iscsi_xcopy_task(data.size);
-retry:
-    if (iscsi_scsi_command_async(dst_lun->iscsi, dst_lun->lun,
-                                 iscsi_task.task, iscsi_co_generic_cb,
-                                 &data,
-                                 &iscsi_task) != 0) {
-        r = -EIO;
-        goto out_unlock;
-    }
-
-    iscsi_co_wait_for_task(&iscsi_task, dst_lun);
-
-    if (iscsi_task.do_retry) {
-        iscsi_task.complete = 0;
-        goto retry;
-    }
-
-    if (iscsi_task.status != SCSI_STATUS_GOOD) {
-        r = iscsi_task.err_code;
-        goto out_unlock;
-    }
-
-out_unlock:
-
-    trace_iscsi_xcopy(src_lun, src_offset, dst_lun, dst_offset, bytes, r);
-    g_free(iscsi_task.task);
-    qemu_mutex_unlock(&dst_lun->mutex);
-    g_free(iscsi_task.err_str);
-    return r;
-}
-
 static QemuOptsList iscsi_create_opts = {
     .name = "iscsi-create-opts",
     .head = QTAILQ_HEAD_INITIALIZER(iscsi_create_opts.head),
@@ -2437,16 +2213,14 @@ static BlockDriver bdrv_iscsi = {
 
     .bdrv_getlength  = iscsi_getlength,
     .bdrv_get_info   = iscsi_get_info,
-    .bdrv_co_truncate    = iscsi_co_truncate,
+    .bdrv_truncate   = iscsi_truncate,
     .bdrv_refresh_limits = iscsi_refresh_limits,
 
     .bdrv_co_block_status  = iscsi_co_block_status,
     .bdrv_co_pdiscard      = iscsi_co_pdiscard,
-    .bdrv_co_copy_range_from = iscsi_co_copy_range_from,
-    .bdrv_co_copy_range_to  = iscsi_co_copy_range_to,
     .bdrv_co_pwrite_zeroes = iscsi_co_pwrite_zeroes,
     .bdrv_co_readv         = iscsi_co_readv,
-    .bdrv_co_writev        = iscsi_co_writev,
+    .bdrv_co_writev_flags  = iscsi_co_writev_flags,
     .bdrv_co_flush_to_disk = iscsi_co_flush,
 
 #ifdef __linux__
@@ -2470,20 +2244,18 @@ static BlockDriver bdrv_iser = {
     .create_opts            = &iscsi_create_opts,
     .bdrv_reopen_prepare    = iscsi_reopen_prepare,
     .bdrv_reopen_commit     = iscsi_reopen_commit,
-    .bdrv_co_invalidate_cache  = iscsi_co_invalidate_cache,
+    .bdrv_invalidate_cache  = iscsi_invalidate_cache,
 
     .bdrv_getlength  = iscsi_getlength,
     .bdrv_get_info   = iscsi_get_info,
-    .bdrv_co_truncate    = iscsi_co_truncate,
+    .bdrv_truncate   = iscsi_truncate,
     .bdrv_refresh_limits = iscsi_refresh_limits,
 
     .bdrv_co_block_status  = iscsi_co_block_status,
     .bdrv_co_pdiscard      = iscsi_co_pdiscard,
-    .bdrv_co_copy_range_from = iscsi_co_copy_range_from,
-    .bdrv_co_copy_range_to  = iscsi_co_copy_range_to,
     .bdrv_co_pwrite_zeroes = iscsi_co_pwrite_zeroes,
     .bdrv_co_readv         = iscsi_co_readv,
-    .bdrv_co_writev        = iscsi_co_writev,
+    .bdrv_co_writev_flags  = iscsi_co_writev_flags,
     .bdrv_co_flush_to_disk = iscsi_co_flush,
 
 #ifdef __linux__

block/linux-aio.c

@@ -15,7 +15,6 @@
 #include "block/raw-aio.h"
 #include "qemu/event_notifier.h"
 #include "qemu/coroutine.h"
-#include "qapi/error.h"
 
 #include <libaio.h>
 
@@ -471,21 +470,16 @@ void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context)
                            qemu_laio_poll_cb);
 }
 
-LinuxAioState *laio_init(Error **errp)
+LinuxAioState *laio_init(void)
 {
-    int rc;
     LinuxAioState *s;
 
     s = g_malloc0(sizeof(*s));
-    rc = event_notifier_init(&s->e, false);
-    if (rc < 0) {
-        error_setg_errno(errp, -rc, "failed to to initialize event notifier");
+    if (event_notifier_init(&s->e, false) < 0) {
         goto out_free_state;
     }
 
-    rc = io_setup(MAX_EVENTS, &s->ctx);
-    if (rc < 0) {
-        error_setg_errno(errp, -rc, "failed to create linux AIO context");
+    if (io_setup(MAX_EVENTS, &s->ctx) != 0) {
         goto out_close_efd;
     }
 

block/nbd-client.c

@@ -228,52 +228,6 @@ static int nbd_parse_offset_hole_payload(NBDStructuredReplyChunk *chunk,
     return 0;
 }
 
-/* nbd_parse_blockstatus_payload
- * support only one extent in reply and only for
- * base:allocation context
- */
-static int nbd_parse_blockstatus_payload(NBDClientSession *client,
-                                         NBDStructuredReplyChunk *chunk,
-                                         uint8_t *payload, uint64_t orig_length,
-                                         NBDExtent *extent, Error **errp)
-{
-    uint32_t context_id;
-
-    if (chunk->length != sizeof(context_id) + sizeof(*extent)) {
-        error_setg(errp, "Protocol error: invalid payload for "
-                         "NBD_REPLY_TYPE_BLOCK_STATUS");
-        return -EINVAL;
-    }
-
-    context_id = payload_advance32(&payload);
-    if (client->info.meta_base_allocation_id != context_id) {
-        error_setg(errp, "Protocol error: unexpected context id %d for "
-                         "NBD_REPLY_TYPE_BLOCK_STATUS, when negotiated context "
-                         "id is %d", context_id,
-                         client->info.meta_base_allocation_id);
-        return -EINVAL;
-    }
-
-    extent->length = payload_advance32(&payload);
-    extent->flags = payload_advance32(&payload);
-
-    if (extent->length == 0 ||
-        (client->info.min_block && !QEMU_IS_ALIGNED(extent->length,
-                                                    client->info.min_block))) {
-        error_setg(errp, "Protocol error: server sent status chunk with "
-                   "invalid length");
-        return -EINVAL;
-    }
-
-    /* The server is allowed to send us extra information on the final
-     * extent; just clamp it to the length we requested. */
-    if (extent->length > orig_length) {
-        extent->length = orig_length;
-    }
-
-    return 0;
-}
-
 /* nbd_parse_error_payload
  * on success @errp contains message describing nbd error reply
  */
@@ -527,7 +481,6 @@ static coroutine_fn int nbd_co_receive_one_chunk(
 
 typedef struct NBDReplyChunkIter {
     int ret;
-    bool fatal;
     Error *err;
     bool done, only_structured;
 } NBDReplyChunkIter;
@@ -537,12 +490,11 @@ static void nbd_iter_error(NBDReplyChunkIter *iter, bool fatal,
 {
     assert(ret < 0);
 
-    if ((fatal && !iter->fatal) || iter->ret == 0) {
+    if (fatal || iter->ret == 0) {
         if (iter->ret != 0) {
             error_free(iter->err);
             iter->err = NULL;
         }
-        iter->fatal = fatal;
         iter->ret = ret;
         error_propagate(&iter->err, *local_err);
     } else {
@@ -688,68 +640,6 @@ static int nbd_co_receive_cmdread_reply(NBDClientSession *s, uint64_t handle,
     return iter.ret;
 }
 
-static int nbd_co_receive_blockstatus_reply(NBDClientSession *s,
-                                            uint64_t handle, uint64_t length,
-                                            NBDExtent *extent, Error **errp)
-{
-    NBDReplyChunkIter iter;
-    NBDReply reply;
-    void *payload = NULL;
-    Error *local_err = NULL;
-    bool received = false;
-
-    assert(!extent->length);
-    NBD_FOREACH_REPLY_CHUNK(s, iter, handle, s->info.structured_reply,
-                            NULL, &reply, &payload)
-    {
-        int ret;
-        NBDStructuredReplyChunk *chunk = &reply.structured;
-
-        assert(nbd_reply_is_structured(&reply));
-
-        switch (chunk->type) {
-        case NBD_REPLY_TYPE_BLOCK_STATUS:
-            if (received) {
-                s->quit = true;
-                error_setg(&local_err, "Several BLOCK_STATUS chunks in reply");
-                nbd_iter_error(&iter, true, -EINVAL, &local_err);
-            }
-            received = true;
-
-            ret = nbd_parse_blockstatus_payload(s, &reply.structured,
-                                                payload, length, extent,
-                                                &local_err);
-            if (ret < 0) {
-                s->quit = true;
-                nbd_iter_error(&iter, true, ret, &local_err);
-            }
-            break;
-        default:
-            if (!nbd_reply_type_is_error(chunk->type)) {
-                s->quit = true;
-                error_setg(&local_err,
-                           "Unexpected reply type: %d (%s) "
-                           "for CMD_BLOCK_STATUS",
-                           chunk->type, nbd_reply_type_lookup(chunk->type));
-                nbd_iter_error(&iter, true, -EINVAL, &local_err);
-            }
-        }
-
-        g_free(payload);
-        payload = NULL;
-    }
-
-    if (!extent->length && !iter.err) {
-        error_setg(&iter.err,
-                   "Server did not reply with any status extents");
-        if (!iter.ret) {
-            iter.ret = -EIO;
-        }
-    }
-    error_propagate(errp, iter.err);
-    return iter.ret;
-}
-
 static int nbd_co_request(BlockDriverState *bs, NBDRequest *request,
                           QEMUIOVector *write_qiov)
 {
@@ -892,51 +782,6 @@ int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes)
     return nbd_co_request(bs, &request, NULL);
 }
 
-int coroutine_fn nbd_client_co_block_status(BlockDriverState *bs,
-                                            bool want_zero,
-                                            int64_t offset, int64_t bytes,
-                                            int64_t *pnum, int64_t *map,
-                                            BlockDriverState **file)
-{
-    int64_t ret;
-    NBDExtent extent = { 0 };
-    NBDClientSession *client = nbd_get_client_session(bs);
-    Error *local_err = NULL;
-
-    NBDRequest request = {
-        .type = NBD_CMD_BLOCK_STATUS,
-        .from = offset,
-        .len = MIN(MIN_NON_ZERO(QEMU_ALIGN_DOWN(INT_MAX,
-                                                bs->bl.request_alignment),
-                                client->info.max_block), bytes),
-        .flags = NBD_CMD_FLAG_REQ_ONE,
-    };
-
-    if (!client->info.base_allocation) {
-        *pnum = bytes;
-        return BDRV_BLOCK_DATA;
-    }
-
-    ret = nbd_co_send_request(bs, &request, NULL);
-    if (ret < 0) {
-        return ret;
-    }
-
-    ret = nbd_co_receive_blockstatus_reply(client, request.handle, bytes,
-                                           &extent, &local_err);
-    if (local_err) {
-        error_report_err(local_err);
-    }
-    if (ret < 0) {
-        return ret;
-    }
-
-    assert(extent.length);
-    *pnum = extent.length;
-    return (extent.flags & NBD_STATE_HOLE ? 0 : BDRV_BLOCK_DATA) |
-           (extent.flags & NBD_STATE_ZERO ? BDRV_BLOCK_ZERO : 0);
-}
-
 void nbd_client_detach_aio_context(BlockDriverState *bs)
 {
     NBDClientSession *client = nbd_get_client_session(bs);
@@ -970,7 +815,6 @@ int nbd_client_init(BlockDriverState *bs,
                     const char *export,
                     QCryptoTLSCreds *tlscreds,
                     const char *hostname,
-                    const char *x_dirty_bitmap,
                     Error **errp)
 {
     NBDClientSession *client = nbd_get_client_session(bs);
@@ -982,12 +826,9 @@ int nbd_client_init(BlockDriverState *bs,
 
     client->info.request_sizes = true;
     client->info.structured_reply = true;
-    client->info.base_allocation = true;
-    client->info.x_dirty_bitmap = g_strdup(x_dirty_bitmap);
     ret = nbd_receive_negotiate(QIO_CHANNEL(sioc), export,
                                 tlscreds, hostname,
                                 &client->ioc, &client->info, errp);
-    g_free(client->info.x_dirty_bitmap);
     if (ret < 0) {
         logout("Failed to negotiate with the NBD server\n");
         return ret;

block/nbd-client.h

@@ -45,7 +45,6 @@ int nbd_client_init(BlockDriverState *bs,
                     const char *export_name,
                     QCryptoTLSCreds *tlscreds,
                     const char *hostname,
-                    const char *x_dirty_bitmap,
                     Error **errp);
 void nbd_client_close(BlockDriverState *bs);
 
@@ -62,10 +61,4 @@ void nbd_client_detach_aio_context(BlockDriverState *bs);
 void nbd_client_attach_aio_context(BlockDriverState *bs,
                                    AioContext *new_context);
 
-int coroutine_fn nbd_client_co_block_status(BlockDriverState *bs,
-                                            bool want_zero,
-                                            int64_t offset, int64_t bytes,
-                                            int64_t *pnum, int64_t *map,
-                                            BlockDriverState **file);
-
 #endif /* NBD_CLIENT_H */

block/nbd.c

@@ -27,8 +27,7 @@
  */
 
 #include "qemu/osdep.h"
-#include "nbd-client.h"
-#include "block/qdict.h"
+#include "block/nbd-client.h"
 #include "qapi/error.h"
 #include "qemu/uri.h"
 #include "block/block_int.h"
@@ -263,6 +262,7 @@ static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options,
 {
     SocketAddress *saddr = NULL;
     QDict *addr = NULL;
+    QObject *crumpled_addr = NULL;
     Visitor *iv = NULL;
     Error *local_err = NULL;
 
@@ -272,11 +272,20 @@ static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options,
         goto done;
     }
 
-    iv = qobject_input_visitor_new_flat_confused(addr, errp);
-    if (!iv) {
+    crumpled_addr = qdict_crumple(addr, errp);
+    if (!crumpled_addr) {
         goto done;
     }
 
+    /*
+     * 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);
@@ -284,7 +293,8 @@ static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options,
     }
 
 done:
-    qobject_unref(addr);
+    QDECREF(addr);
+    qobject_decref(crumpled_addr);
     visit_free(iv);
     return saddr;
 }
@@ -378,12 +388,6 @@ static QemuOptsList nbd_runtime_opts = {
             .type = QEMU_OPT_STRING,
             .help = "ID of the TLS credentials to use",
         },
-        {
-            .name = "x-dirty-bitmap",
-            .type = QEMU_OPT_STRING,
-            .help = "experimental: expose named dirty bitmap in place of "
-                    "block status",
-        },
         { /* end of list */ }
     },
 };
@@ -444,8 +448,8 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     /* NBD handshake */
-    ret = nbd_client_init(bs, sioc, s->export, tlscreds, hostname,
-                          qemu_opt_get(opts, "x-dirty-bitmap"), errp);
+    ret = nbd_client_init(bs, sioc, s->export,
+                          tlscreds, hostname, errp);
  error:
     if (sioc) {
         object_unref(OBJECT(sioc));
@@ -581,7 +585,6 @@ static BlockDriver bdrv_nbd = {
     .bdrv_detach_aio_context    = nbd_detach_aio_context,
     .bdrv_attach_aio_context    = nbd_attach_aio_context,
     .bdrv_refresh_filename      = nbd_refresh_filename,
-    .bdrv_co_block_status       = nbd_client_co_block_status,
 };
 
 static BlockDriver bdrv_nbd_tcp = {
@@ -601,7 +604,6 @@ static BlockDriver bdrv_nbd_tcp = {
     .bdrv_detach_aio_context    = nbd_detach_aio_context,
     .bdrv_attach_aio_context    = nbd_attach_aio_context,
     .bdrv_refresh_filename      = nbd_refresh_filename,
-    .bdrv_co_block_status       = nbd_client_co_block_status,
 };
 
 static BlockDriver bdrv_nbd_unix = {
@@ -621,7 +623,6 @@ static BlockDriver bdrv_nbd_unix = {
     .bdrv_detach_aio_context    = nbd_detach_aio_context,
     .bdrv_attach_aio_context    = nbd_attach_aio_context,
     .bdrv_refresh_filename      = nbd_refresh_filename,
-    .bdrv_co_block_status       = nbd_client_co_block_status,
 };
 
 static void bdrv_nbd_init(void)

block/nfs.c

@@ -29,7 +29,6 @@
 #include "qemu/error-report.h"
 #include "qapi/error.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "trace.h"
 #include "qemu/iov.h"
 #include "qemu/option.h"
@@ -556,29 +555,24 @@ static BlockdevOptionsNfs *nfs_options_qdict_to_qapi(QDict *options,
                                                      Error **errp)
 {
     BlockdevOptionsNfs *opts = NULL;
+    QObject *crumpled = NULL;
     Visitor *v;
-    const QDictEntry *e;
     Error *local_err = NULL;
 
-    v = qobject_input_visitor_new_flat_confused(options, errp);
-    if (!v) {
+    crumpled = qdict_crumple(options, errp);
+    if (crumpled == NULL) {
         return NULL;
     }
 
+    v = qobject_input_visitor_new_keyval(crumpled);
     visit_type_BlockdevOptionsNfs(v, NULL, &opts, &local_err);
     visit_free(v);
+    qobject_decref(crumpled);
 
     if (local_err) {
-        error_propagate(errp, local_err);
         return NULL;
     }
 
-    /* Remove the processed options from the QDict (the visitor processes
-     * _all_ options in the QDict) */
-    while ((e = qdict_first(options))) {
-        qdict_del(options, e->key);
-    }
-
     return opts;
 }
 
@@ -689,7 +683,7 @@ static int coroutine_fn nfs_file_co_create_opts(const char *url, QemuOpts *opts,
 
     ret = 0;
 out:
-    qobject_unref(options);
+    QDECREF(options);
     qapi_free_BlockdevCreateOptions(create_options);
     return ret;
 }
@@ -743,8 +737,7 @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
     return (task.ret < 0 ? task.ret : st.st_blocks * 512);
 }
 
-static int coroutine_fn
-nfs_file_co_truncate(BlockDriverState *bs, int64_t offset,
+static int nfs_file_truncate(BlockDriverState *bs, int64_t offset,
                              PreallocMode prealloc, Error **errp)
 {
     NFSClient *client = bs->opaque;
@@ -874,7 +867,7 @@ static BlockDriver bdrv_nfs = {
 
     .bdrv_has_zero_init             = nfs_has_zero_init,
     .bdrv_get_allocated_file_size   = nfs_get_allocated_file_size,
-    .bdrv_co_truncate               = nfs_file_co_truncate,
+    .bdrv_truncate                  = nfs_file_truncate,
 
     .bdrv_file_open                 = nfs_file_open,
     .bdrv_close                     = nfs_file_close,

block/null.c

@@ -93,7 +93,6 @@ static int null_file_open(BlockDriverState *bs, QDict *options, int flags,
     }
     s->read_zeroes = qemu_opt_get_bool(opts, NULL_OPT_ZEROES, false);
     qemu_opts_del(opts);
-    bs->supported_write_flags = BDRV_REQ_FUA;
     return ret;
 }
 
@@ -117,22 +116,22 @@ static coroutine_fn int null_co_common(BlockDriverState *bs)
     return 0;
 }
 
-static coroutine_fn int null_co_preadv(BlockDriverState *bs,
-                                       uint64_t offset, uint64_t bytes,
-                                       QEMUIOVector *qiov, int flags)
+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, bytes);
+        qemu_iovec_memset(qiov, 0, 0, nb_sectors * BDRV_SECTOR_SIZE);
     }
 
     return null_co_common(bs);
 }
 
-static coroutine_fn int null_co_pwritev(BlockDriverState *bs,
-                                        uint64_t offset, uint64_t bytes,
-                                        QEMUIOVector *qiov, int flags)
+static coroutine_fn int null_co_writev(BlockDriverState *bs,
+                                       int64_t sector_num, int nb_sectors,
+                                       QEMUIOVector *qiov)
 {
     return null_co_common(bs);
 }
@@ -187,24 +186,24 @@ static inline BlockAIOCB *null_aio_common(BlockDriverState *bs,
     return &acb->common;
 }
 
-static BlockAIOCB *null_aio_preadv(BlockDriverState *bs,
-                                   uint64_t offset, uint64_t bytes,
-                                   QEMUIOVector *qiov, int flags,
+static BlockAIOCB *null_aio_readv(BlockDriverState *bs,
+                                  int64_t sector_num, QEMUIOVector *qiov,
+                                  int nb_sectors,
                                   BlockCompletionFunc *cb,
                                   void *opaque)
 {
     BDRVNullState *s = bs->opaque;
 
     if (s->read_zeroes) {
-        qemu_iovec_memset(qiov, 0, 0, bytes);
+        qemu_iovec_memset(qiov, 0, 0, nb_sectors * BDRV_SECTOR_SIZE);
     }
 
     return null_aio_common(bs, cb, opaque);
 }
 
-static BlockAIOCB *null_aio_pwritev(BlockDriverState *bs,
-                                    uint64_t offset, uint64_t bytes,
-                                    QEMUIOVector *qiov, int flags,
+static BlockAIOCB *null_aio_writev(BlockDriverState *bs,
+                                   int64_t sector_num, QEMUIOVector *qiov,
+                                   int nb_sectors,
                                    BlockCompletionFunc *cb,
                                    void *opaque)
 {
@@ -245,6 +244,7 @@ static int coroutine_fn null_co_block_status(BlockDriverState *bs,
 
 static void null_refresh_filename(BlockDriverState *bs, QDict *opts)
 {
+    QINCREF(opts);
     qdict_del(opts, "filename");
 
     if (!qdict_size(opts)) {
@@ -253,7 +253,7 @@ static void null_refresh_filename(BlockDriverState *bs, QDict *opts)
     }
 
     qdict_put_str(opts, "driver", bs->drv->format_name);
-    bs->full_open_options = qobject_ref(opts);
+    bs->full_open_options = opts;
 }
 
 static BlockDriver bdrv_null_co = {
@@ -266,8 +266,8 @@ static BlockDriver bdrv_null_co = {
     .bdrv_close             = null_close,
     .bdrv_getlength         = null_getlength,
 
-    .bdrv_co_preadv         = null_co_preadv,
-    .bdrv_co_pwritev        = null_co_pwritev,
+    .bdrv_co_readv          = null_co_readv,
+    .bdrv_co_writev         = null_co_writev,
     .bdrv_co_flush_to_disk  = null_co_flush,
     .bdrv_reopen_prepare    = null_reopen_prepare,
 
@@ -286,8 +286,8 @@ static BlockDriver bdrv_null_aio = {
     .bdrv_close             = null_close,
     .bdrv_getlength         = null_getlength,
 
-    .bdrv_aio_preadv        = null_aio_preadv,
-    .bdrv_aio_pwritev       = null_aio_pwritev,
+    .bdrv_aio_readv         = null_aio_readv,
+    .bdrv_aio_writev        = null_aio_writev,
     .bdrv_aio_flush         = null_aio_flush,
     .bdrv_reopen_prepare    = null_reopen_prepare,
 

block/nvme.c

@@ -695,11 +695,12 @@ static void nvme_parse_filename(const char *filename, QDict *options,
         unsigned long ns;
         const char *slash = strchr(tmp, '/');
         if (!slash) {
-            qdict_put_str(options, NVME_BLOCK_OPT_DEVICE, tmp);
+            qdict_put(options, NVME_BLOCK_OPT_DEVICE,
+                      qstring_from_str(tmp));
             return;
         }
         device = g_strndup(tmp, slash - tmp);
-        qdict_put_str(options, NVME_BLOCK_OPT_DEVICE, device);
+        qdict_put(options, NVME_BLOCK_OPT_DEVICE, qstring_from_str(device));
         g_free(device);
         namespace = slash + 1;
         if (*namespace && qemu_strtoul(namespace, NULL, 10, &ns)) {
@@ -707,8 +708,8 @@ static void nvme_parse_filename(const char *filename, QDict *options,
                        namespace);
             return;
         }
-        qdict_put_str(options, NVME_BLOCK_OPT_NAMESPACE,
-                      *namespace ? namespace : "1");
+        qdict_put(options, NVME_BLOCK_OPT_NAMESPACE,
+                  qstring_from_str(*namespace ? namespace : "1"));
     }
 }
 
@@ -1073,6 +1074,7 @@ static int nvme_reopen_prepare(BDRVReopenState *reopen_state,
 
 static void nvme_refresh_filename(BlockDriverState *bs, QDict *opts)
 {
+    QINCREF(opts);
     qdict_del(opts, "filename");
 
     if (!qdict_size(opts)) {
@@ -1080,8 +1082,8 @@ static void nvme_refresh_filename(BlockDriverState *bs, QDict *opts)
                  bs->drv->format_name);
     }
 
-    qdict_put_str(opts, "driver", bs->drv->format_name);
-    bs->full_open_options = qobject_ref(opts);
+    qdict_put(opts, "driver", qstring_from_str(bs->drv->format_name));
+    bs->full_open_options = opts;
 }
 
 static void nvme_refresh_limits(BlockDriverState *bs, Error **errp)

block/parallels.c

@@ -31,13 +31,9 @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "sysemu/block-backend.h"
 #include "qemu/module.h"
 #include "qemu/option.h"
-#include "qapi/qmp/qdict.h"
-#include "qapi/qobject-input-visitor.h"
-#include "qapi/qapi-visit-block-core.h"
 #include "qemu/bswap.h"
 #include "qemu/bitmap.h"
 #include "migration/blocker.h"
@@ -83,25 +79,6 @@ static QemuOptsList parallels_runtime_opts = {
     },
 };
 
-static QemuOptsList parallels_create_opts = {
-    .name = "parallels-create-opts",
-    .head = QTAILQ_HEAD_INITIALIZER(parallels_create_opts.head),
-    .desc = {
-        {
-            .name = BLOCK_OPT_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Virtual disk size",
-        },
-        {
-            .name = BLOCK_OPT_CLUSTER_SIZE,
-            .type = QEMU_OPT_SIZE,
-            .help = "Parallels image cluster size",
-            .def_value_str = stringify(DEFAULT_CLUSTER_SIZE),
-        },
-        { /* end of list */ }
-    }
-};
-
 
 static int64_t bat2sect(BDRVParallelsState *s, uint32_t idx)
 {
@@ -227,15 +204,14 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
         };
         qemu_iovec_init_external(&qiov, &iov, 1);
 
-        ret = bdrv_co_preadv(bs->backing, idx * s->tracks * BDRV_SECTOR_SIZE,
-                             nb_cow_bytes, &qiov, 0);
+        ret = bdrv_co_readv(bs->backing, idx * s->tracks, nb_cow_sectors,
+                            &qiov);
         if (ret < 0) {
             qemu_vfree(iov.iov_base);
             return ret;
         }
 
-        ret = bdrv_co_pwritev(bs->file, s->data_end * BDRV_SECTOR_SIZE,
-                              nb_cow_bytes, &qiov, 0);
+        ret = bdrv_co_writev(bs->file, s->data_end, nb_cow_sectors, &qiov);
         qemu_vfree(iov.iov_base);
         if (ret < 0) {
             return ret;
@@ -313,15 +289,13 @@ static int coroutine_fn parallels_co_block_status(BlockDriverState *bs,
 }
 
 static coroutine_fn int parallels_co_writev(BlockDriverState *bs,
-                                            int64_t sector_num, int nb_sectors,
-                                            QEMUIOVector *qiov, int flags)
+        int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
 {
     BDRVParallelsState *s = bs->opaque;
     uint64_t bytes_done = 0;
     QEMUIOVector hd_qiov;
     int ret = 0;
 
-    assert(!flags);
     qemu_iovec_init(&hd_qiov, qiov->niov);
 
     while (nb_sectors > 0) {
@@ -341,8 +315,7 @@ 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_pwritev(bs->file, position * BDRV_SECTOR_SIZE, nbytes,
-                              &hd_qiov, 0);
+        ret = bdrv_co_writev(bs->file, position, n, &hd_qiov);
         if (ret < 0) {
             break;
         }
@@ -381,8 +354,7 @@ static coroutine_fn int parallels_co_readv(BlockDriverState *bs,
 
         if (position < 0) {
             if (bs->backing) {
-                ret = bdrv_co_preadv(bs->backing, sector_num * BDRV_SECTOR_SIZE,
-                                     nbytes, &hd_qiov, 0);
+                ret = bdrv_co_readv(bs->backing, sector_num, n, &hd_qiov);
                 if (ret < 0) {
                     break;
                 }
@@ -390,8 +362,7 @@ static coroutine_fn int parallels_co_readv(BlockDriverState *bs,
                 qemu_iovec_memset(&hd_qiov, 0, 0, nbytes);
             }
         } else {
-            ret = bdrv_co_preadv(bs->file, position * BDRV_SECTOR_SIZE, nbytes,
-                                 &hd_qiov, 0);
+            ret = bdrv_co_readv(bs->file, position, n, &hd_qiov);
             if (ret < 0) {
                 break;
             }
@@ -509,67 +480,46 @@ out:
 }
 
 
-static int coroutine_fn parallels_co_create(BlockdevCreateOptions* opts,
+static int coroutine_fn parallels_co_create_opts(const char *filename,
+                                                 QemuOpts *opts,
                                                  Error **errp)
 {
-    BlockdevCreateOptionsParallels *parallels_opts;
-    BlockDriverState *bs;
-    BlockBackend *blk;
     int64_t total_size, cl_size;
+    uint8_t tmp[BDRV_SECTOR_SIZE];
+    Error *local_err = NULL;
+    BlockBackend *file;
     uint32_t bat_entries, bat_sectors;
     ParallelsHeader header;
-    uint8_t tmp[BDRV_SECTOR_SIZE];
     int ret;
 
-    assert(opts->driver == BLOCKDEV_DRIVER_PARALLELS);
-    parallels_opts = &opts->u.parallels;
-
-    /* Sanity checks */
-    total_size = parallels_opts->size;
-
-    if (parallels_opts->has_cluster_size) {
-        cl_size = parallels_opts->cluster_size;
-    } else {
-        cl_size = DEFAULT_CLUSTER_SIZE;
-    }
-
-    /* XXX What is the real limit here? This is an insanely large maximum. */
-    if (cl_size >= INT64_MAX / MAX_PARALLELS_IMAGE_FACTOR) {
-        error_setg(errp, "Cluster size is too large");
-        return -EINVAL;
-    }
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          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_setg(errp, "Image size is too large for this cluster size");
+        error_propagate(errp, local_err);
         return -E2BIG;
     }
 
-    if (!QEMU_IS_ALIGNED(total_size, BDRV_SECTOR_SIZE)) {
-        error_setg(errp, "Image size must be a multiple of 512 bytes");
-        return -EINVAL;
+    ret = bdrv_create_file(filename, opts, &local_err);
+    if (ret < 0) {
+        error_propagate(errp, local_err);
+        return ret;
     }
 
-    if (!QEMU_IS_ALIGNED(cl_size, BDRV_SECTOR_SIZE)) {
-        error_setg(errp, "Cluster size must be a multiple of 512 bytes");
-        return -EINVAL;
-    }
-
-    /* Create BlockBackend to write to the image */
-    bs = bdrv_open_blockdev_ref(parallels_opts->file, errp);
-    if (bs == NULL) {
+    file = blk_new_open(filename, NULL, NULL,
+                        BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                        &local_err);
+    if (file == NULL) {
+        error_propagate(errp, local_err);
         return -EIO;
     }
 
-    blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
-    ret = blk_insert_bs(blk, bs, errp);
-    if (ret < 0) {
-        goto out;
-    }
-    blk_set_allow_write_beyond_eof(blk, true);
+    blk_set_allow_write_beyond_eof(file, true);
 
-    /* Create image format */
-    ret = blk_truncate(blk, 0, PREALLOC_MODE_OFF, errp);
+    ret = blk_truncate(file, 0, PREALLOC_MODE_OFF, errp);
     if (ret < 0) {
-        goto out;
+        goto exit;
     }
 
     bat_entries = DIV_ROUND_UP(total_size, cl_size);
@@ -592,105 +542,26 @@ static int coroutine_fn parallels_co_create(BlockdevCreateOptions* opts,
     memset(tmp, 0, sizeof(tmp));
     memcpy(tmp, &header, sizeof(header));
 
-    ret = blk_pwrite(blk, 0, tmp, BDRV_SECTOR_SIZE, 0);
+    ret = blk_pwrite(file, 0, tmp, BDRV_SECTOR_SIZE, 0);
     if (ret < 0) {
         goto exit;
     }
-    ret = blk_pwrite_zeroes(blk, BDRV_SECTOR_SIZE,
+    ret = blk_pwrite_zeroes(file, BDRV_SECTOR_SIZE,
                             (bat_sectors - 1) << BDRV_SECTOR_BITS, 0);
     if (ret < 0) {
         goto exit;
     }
-
     ret = 0;
-out:
-    blk_unref(blk);
-    bdrv_unref(bs);
+
+done:
+    blk_unref(file);
     return ret;
 
 exit:
     error_setg_errno(errp, -ret, "Failed to create Parallels image");
-    goto out;
-}
-
-static int coroutine_fn parallels_co_create_opts(const char *filename,
-                                                 QemuOpts *opts,
-                                                 Error **errp)
-{
-    BlockdevCreateOptions *create_options = NULL;
-    Error *local_err = NULL;
-    BlockDriverState *bs = NULL;
-    QDict *qdict;
-    Visitor *v;
-    int ret;
-
-    static const QDictRenames opt_renames[] = {
-        { BLOCK_OPT_CLUSTER_SIZE,       "cluster-size" },
-        { NULL, NULL },
-    };
-
-    /* Parse options and convert legacy syntax */
-    qdict = qemu_opts_to_qdict_filtered(opts, NULL, &parallels_create_opts,
-                                        true);
-
-    if (!qdict_rename_keys(qdict, opt_renames, errp)) {
-        ret = -EINVAL;
     goto done;
 }
 
-    /* Create and open the file (protocol layer) */
-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto done;
-    }
-
-    bs = bdrv_open(filename, NULL, NULL,
-                   BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
-    if (bs == NULL) {
-        ret = -EIO;
-        goto done;
-    }
-
-    /* Now get the QAPI type BlockdevCreateOptions */
-    qdict_put_str(qdict, "driver", "parallels");
-    qdict_put_str(qdict, "file", bs->node_name);
-
-    v = qobject_input_visitor_new_flat_confused(qdict, errp);
-    if (!v) {
-        ret = -EINVAL;
-        goto done;
-    }
-
-    visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err);
-    visit_free(v);
-
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto done;
-    }
-
-    /* Silently round up sizes */
-    create_options->u.parallels.size =
-        ROUND_UP(create_options->u.parallels.size, BDRV_SECTOR_SIZE);
-    create_options->u.parallels.cluster_size =
-        ROUND_UP(create_options->u.parallels.cluster_size, BDRV_SECTOR_SIZE);
-
-    /* Create the Parallels image (format layer) */
-    ret = parallels_co_create(create_options, errp);
-    if (ret < 0) {
-        goto done;
-    }
-    ret = 0;
-
-done:
-    qobject_unref(qdict);
-    bdrv_unref(bs);
-    qapi_free_BlockdevCreateOptions(create_options);
-    return ret;
-}
-
 
 static int parallels_probe(const uint8_t *buf, int buf_size,
                            const char *filename)
@@ -900,6 +771,25 @@ static void parallels_close(BlockDriverState *bs)
     error_free(s->migration_blocker);
 }
 
+static QemuOptsList parallels_create_opts = {
+    .name = "parallels-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(parallels_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size",
+        },
+        {
+            .name = BLOCK_OPT_CLUSTER_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Parallels image cluster size",
+            .def_value_str = stringify(DEFAULT_CLUSTER_SIZE),
+        },
+        { /* end of list */ }
+    }
+};
+
 static BlockDriver bdrv_parallels = {
     .format_name	= "parallels",
     .instance_size	= sizeof(BDRVParallelsState),
@@ -913,7 +803,6 @@ static BlockDriver bdrv_parallels = {
     .bdrv_co_readv  = parallels_co_readv,
     .bdrv_co_writev = parallels_co_writev,
     .supports_backing = true,
-    .bdrv_co_create      = parallels_co_create,
     .bdrv_co_create_opts = parallels_co_create_opts,
     .bdrv_co_check  = parallels_co_check,
     .create_opts    = &parallels_create_opts,

block/qapi.c

@@ -394,37 +394,6 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
     qapi_free_BlockInfo(info);
 }
 
-static uint64List *uint64_list(uint64_t *list, int size)
-{
-    int i;
-    uint64List *out_list = NULL;
-    uint64List **pout_list = &out_list;
-
-    for (i = 0; i < size; i++) {
-        uint64List *entry = g_new(uint64List, 1);
-        entry->value = list[i];
-        *pout_list = entry;
-        pout_list = &entry->next;
-    }
-
-    *pout_list = NULL;
-
-    return out_list;
-}
-
-static void bdrv_latency_histogram_stats(BlockLatencyHistogram *hist,
-                                         bool *not_null,
-                                         BlockLatencyHistogramInfo **info)
-{
-    *not_null = hist->bins != NULL;
-    if (*not_null) {
-        *info = g_new0(BlockLatencyHistogramInfo, 1);
-
-        (*info)->boundaries = uint64_list(hist->boundaries, hist->nbins - 1);
-        (*info)->bins = uint64_list(hist->bins, hist->nbins);
-    }
-}
-
 static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
 {
     BlockAcctStats *stats = blk_get_stats(blk);
@@ -490,16 +459,6 @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
         dev_stats->avg_wr_queue_depth =
             block_acct_queue_depth(ts, BLOCK_ACCT_WRITE);
     }
-
-    bdrv_latency_histogram_stats(&stats->latency_histogram[BLOCK_ACCT_READ],
-                                 &ds->has_x_rd_latency_histogram,
-                                 &ds->x_rd_latency_histogram);
-    bdrv_latency_histogram_stats(&stats->latency_histogram[BLOCK_ACCT_WRITE],
-                                 &ds->has_x_wr_latency_histogram,
-                                 &ds->x_wr_latency_histogram);
-    bdrv_latency_histogram_stats(&stats->latency_histogram[BLOCK_ACCT_FLUSH],
-                                 &ds->has_x_flush_latency_histogram,
-                                 &ds->x_flush_latency_histogram);
 }
 
 static BlockStats *bdrv_query_bds_stats(BlockDriverState *bs,
@@ -688,29 +647,29 @@ static void dump_qobject(fprintf_function func_fprintf, void *f,
 {
     switch (qobject_type(obj)) {
         case QTYPE_QNUM: {
-            QNum *value = qobject_to(QNum, obj);
+            QNum *value = qobject_to_qnum(obj);
             char *tmp = qnum_to_string(value);
             func_fprintf(f, "%s", tmp);
             g_free(tmp);
             break;
         }
         case QTYPE_QSTRING: {
-            QString *value = qobject_to(QString, obj);
+            QString *value = qobject_to_qstring(obj);
             func_fprintf(f, "%s", qstring_get_str(value));
             break;
         }
         case QTYPE_QDICT: {
-            QDict *value = qobject_to(QDict, obj);
+            QDict *value = qobject_to_qdict(obj);
             dump_qdict(func_fprintf, f, comp_indent, value);
             break;
         }
         case QTYPE_QLIST: {
-            QList *value = qobject_to(QList, obj);
+            QList *value = qobject_to_qlist(obj);
             dump_qlist(func_fprintf, f, comp_indent, value);
             break;
         }
         case QTYPE_QBOOL: {
-            QBool *value = qobject_to(QBool, obj);
+            QBool *value = qobject_to_qbool(obj);
             func_fprintf(f, "%s", qbool_get_bool(value) ? "true" : "false");
             break;
         }
@@ -771,9 +730,9 @@ void bdrv_image_info_specific_dump(fprintf_function func_fprintf, void *f,
 
     visit_type_ImageInfoSpecific(v, NULL, &info_spec, &error_abort);
     visit_complete(v, &obj);
-    data = qdict_get(qobject_to(QDict, obj), "data");
+    data = qdict_get(qobject_to_qdict(obj), "data");
     dump_qobject(func_fprintf, f, 1, data);
-    qobject_unref(obj);
+    qobject_decref(obj);
     visit_free(v);
 }
 

block/qcow.c

@@ -26,7 +26,6 @@
 #include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "sysemu/block-backend.h"
 #include "qemu/module.h"
 #include "qemu/option.h"
@@ -34,11 +33,9 @@
 #include <zlib.h>
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qstring.h"
-#include "qapi/qobject-input-visitor.h"
-#include "qapi/qapi-visit-block-core.h"
 #include "crypto/block.h"
 #include "migration/blocker.h"
-#include "crypto.h"
+#include "block/crypto.h"
 
 /**************************************************************/
 /* QEMU COW block driver with compression and encryption support */
@@ -70,6 +67,7 @@ typedef struct QCowHeader {
 typedef struct BDRVQcowState {
     int cluster_bits;
     int cluster_size;
+    int cluster_sectors;
     int l2_bits;
     int l2_size;
     unsigned int l1_size;
@@ -88,8 +86,6 @@ typedef struct BDRVQcowState {
     Error *migration_blocker;
 } BDRVQcowState;
 
-static QemuOptsList qcow_create_opts;
-
 static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset);
 
 static int qcow_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -202,8 +198,9 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
                 ret = -EINVAL;
                 goto fail;
             }
-            qdict_put_str(encryptopts, "format", "qcow");
-            crypto_opts = block_crypto_open_opts_init(encryptopts, errp);
+            qdict_del(encryptopts, "format");
+            crypto_opts = block_crypto_open_opts_init(
+                Q_CRYPTO_BLOCK_FORMAT_QCOW, encryptopts, errp);
             if (!crypto_opts) {
                 ret = -EINVAL;
                 goto fail;
@@ -234,6 +231,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     }
     s->cluster_bits = header.cluster_bits;
     s->cluster_size = 1 << s->cluster_bits;
+    s->cluster_sectors = 1 << (s->cluster_bits - 9);
     s->l2_bits = header.l2_bits;
     s->l2_size = 1 << s->l2_bits;
     bs->total_sectors = header.size / 512;
@@ -313,7 +311,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    qobject_unref(encryptopts);
+    QDECREF(encryptopts);
     qapi_free_QCryptoBlockOpenOptions(crypto_opts);
     qemu_co_mutex_init(&s->lock);
     return 0;
@@ -324,7 +322,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     g_free(s->cluster_cache);
     g_free(s->cluster_data);
     qcrypto_block_free(s->crypto);
-    qobject_unref(encryptopts);
+    QDECREF(encryptopts);
     qapi_free_QCryptoBlockOpenOptions(crypto_opts);
     return ret;
 }
@@ -343,8 +341,8 @@ static int qcow_reopen_prepare(BDRVReopenState *state,
  *
  * 0 to not allocate.
  *
- * 1 to allocate a normal cluster (for sector-aligned byte offsets 'n_start'
- * to 'n_end' within the cluster)
+ * 1 to allocate a normal cluster (for sector indexes 'n_start' to
+ * 'n_end')
  *
  * 2 to allocate a compressed cluster of size
  * 'compressed_size'. 'compressed_size' must be > 0 and <
@@ -438,10 +436,9 @@ static int get_cluster_offset(BlockDriverState *bs,
         if (!allocate)
             return 0;
         BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_ALLOC);
-        assert(QEMU_IS_ALIGNED(n_start | n_end, BDRV_SECTOR_SIZE));
         /* allocate a new cluster */
         if ((cluster_offset & QCOW_OFLAG_COMPRESSED) &&
-            (n_end - n_start) < s->cluster_size) {
+            (n_end - n_start) < s->cluster_sectors) {
             /* if the cluster is already compressed, we must
                decompress it in the case it is not completely
                overwritten */
@@ -479,15 +476,16 @@ static int get_cluster_offset(BlockDriverState *bs,
                 /* if encrypted, we must initialize the cluster
                    content which won't be written */
                 if (bs->encrypted &&
-                    (n_end - n_start) < s->cluster_size) {
-                    uint64_t start_offset;
+                    (n_end - n_start) < s->cluster_sectors) {
+                    uint64_t start_sect;
                     assert(s->crypto);
-                    start_offset = offset & ~(s->cluster_size - 1);
-                    for (i = 0; i < s->cluster_size; i += BDRV_SECTOR_SIZE) {
+                    start_sect = (offset & ~(s->cluster_size - 1)) >> 9;
+                    for(i = 0; i < s->cluster_sectors; i++) {
                         if (i < n_start || i >= n_end) {
-                            memset(s->cluster_data, 0x00, BDRV_SECTOR_SIZE);
+                            memset(s->cluster_data, 0x00, 512);
                             if (qcrypto_block_encrypt(s->crypto,
-                                                      start_offset + i,
+                                                      (start_sect + i) *
+                                                      BDRV_SECTOR_SIZE,
                                                       s->cluster_data,
                                                       BDRV_SECTOR_SIZE,
                                                       NULL) < 0) {
@@ -495,9 +493,8 @@ static int get_cluster_offset(BlockDriverState *bs,
                             }
                             BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
                             ret = bdrv_pwrite(bs->file,
-                                              cluster_offset + i,
-                                              s->cluster_data,
-                                              BDRV_SECTOR_SIZE);
+                                              cluster_offset + i * 512,
+                                              s->cluster_data, 512);
                             if (ret < 0) {
                                 return ret;
                             }
@@ -611,21 +608,11 @@ static int decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
     return 0;
 }
 
-static void qcow_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    /* At least encrypted images require 512-byte alignment. Apply the
-     * limit universally, rather than just on encrypted images, as
-     * it's easier to let the block layer handle rounding than to
-     * audit this code further. */
-    bs->bl.request_alignment = BDRV_SECTOR_SIZE;
-}
-
-static coroutine_fn int qcow_co_preadv(BlockDriverState *bs, uint64_t offset,
-                                       uint64_t bytes, QEMUIOVector *qiov,
-                                       int flags)
+static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
+                         int nb_sectors, QEMUIOVector *qiov)
 {
     BDRVQcowState *s = bs->opaque;
-    int offset_in_cluster;
+    int index_in_cluster;
     int ret = 0, n;
     uint64_t cluster_offset;
     struct iovec hd_iov;
@@ -633,7 +620,6 @@ static coroutine_fn int qcow_co_preadv(BlockDriverState *bs, uint64_t offset,
     uint8_t *buf;
     void *orig_buf;
 
-    assert(!flags);
     if (qiov->niov > 1) {
         buf = orig_buf = qemu_try_blockalign(bs, qiov->size);
         if (buf == NULL) {
@@ -646,35 +632,36 @@ static coroutine_fn int qcow_co_preadv(BlockDriverState *bs, uint64_t offset,
 
     qemu_co_mutex_lock(&s->lock);
 
-    while (bytes != 0) {
+    while (nb_sectors != 0) {
         /* prepare next request */
-        ret = get_cluster_offset(bs, offset, 0, 0, 0, 0, &cluster_offset);
+        ret = get_cluster_offset(bs, sector_num << 9,
+                                 0, 0, 0, 0, &cluster_offset);
         if (ret < 0) {
             break;
         }
-        offset_in_cluster = offset & (s->cluster_size - 1);
-        n = s->cluster_size - offset_in_cluster;
-        if (n > bytes) {
-            n = bytes;
+        index_in_cluster = sector_num & (s->cluster_sectors - 1);
+        n = s->cluster_sectors - index_in_cluster;
+        if (n > nb_sectors) {
+            n = nb_sectors;
         }
 
         if (!cluster_offset) {
             if (bs->backing) {
                 /* read from the base image */
                 hd_iov.iov_base = (void *)buf;
-                hd_iov.iov_len = n;
+                hd_iov.iov_len = n * 512;
                 qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
                 qemu_co_mutex_unlock(&s->lock);
                 /* qcow2 emits this on bs->file instead of bs->backing */
                 BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO);
-                ret = bdrv_co_preadv(bs->backing, offset, n, &hd_qiov, 0);
+                ret = bdrv_co_readv(bs->backing, sector_num, n, &hd_qiov);
                 qemu_co_mutex_lock(&s->lock);
                 if (ret < 0) {
                     break;
                 }
             } else {
                 /* Note: in this case, no need to wait */
-                memset(buf, 0, n);
+                memset(buf, 0, 512 * n);
             }
         } else if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
             /* add AIO support for compressed blocks ? */
@@ -682,19 +669,21 @@ static coroutine_fn int qcow_co_preadv(BlockDriverState *bs, uint64_t offset,
                 ret = -EIO;
                 break;
             }
-            memcpy(buf, s->cluster_cache + offset_in_cluster, n);
+            memcpy(buf,
+                   s->cluster_cache + index_in_cluster * 512, 512 * n);
         } else {
             if ((cluster_offset & 511) != 0) {
                 ret = -EIO;
                 break;
             }
             hd_iov.iov_base = (void *)buf;
-            hd_iov.iov_len = n;
+            hd_iov.iov_len = n * 512;
             qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
             qemu_co_mutex_unlock(&s->lock);
             BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
-            ret = bdrv_co_preadv(bs->file, cluster_offset + offset_in_cluster,
-                                 n, &hd_qiov, 0);
+            ret = bdrv_co_readv(bs->file,
+                                (cluster_offset >> 9) + index_in_cluster,
+                                n, &hd_qiov);
             qemu_co_mutex_lock(&s->lock);
             if (ret < 0) {
                 break;
@@ -702,7 +691,8 @@ static coroutine_fn int qcow_co_preadv(BlockDriverState *bs, uint64_t offset,
             if (bs->encrypted) {
                 assert(s->crypto);
                 if (qcrypto_block_decrypt(s->crypto,
-                                          offset, buf, n, NULL) < 0) {
+                                          sector_num * BDRV_SECTOR_SIZE, buf,
+                                          n * BDRV_SECTOR_SIZE, NULL) < 0) {
                     ret = -EIO;
                     break;
                 }
@@ -710,9 +700,9 @@ static coroutine_fn int qcow_co_preadv(BlockDriverState *bs, uint64_t offset,
         }
         ret = 0;
 
-        bytes -= n;
-        offset += n;
-        buf += n;
+        nb_sectors -= n;
+        sector_num += n;
+        buf += n * 512;
     }
 
     qemu_co_mutex_unlock(&s->lock);
@@ -725,12 +715,11 @@ static coroutine_fn int qcow_co_preadv(BlockDriverState *bs, uint64_t offset,
     return ret;
 }
 
-static coroutine_fn int qcow_co_pwritev(BlockDriverState *bs, uint64_t offset,
-                                        uint64_t bytes, QEMUIOVector *qiov,
-                                        int flags)
+static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
+                          int nb_sectors, QEMUIOVector *qiov)
 {
     BDRVQcowState *s = bs->opaque;
-    int offset_in_cluster;
+    int index_in_cluster;
     uint64_t cluster_offset;
     int ret = 0, n;
     struct iovec hd_iov;
@@ -738,7 +727,6 @@ static coroutine_fn int qcow_co_pwritev(BlockDriverState *bs, uint64_t offset,
     uint8_t *buf;
     void *orig_buf;
 
-    assert(!flags);
     s->cluster_cache_offset = -1; /* disable compressed cache */
 
     /* We must always copy the iov when encrypting, so we
@@ -756,14 +744,16 @@ static coroutine_fn int qcow_co_pwritev(BlockDriverState *bs, uint64_t offset,
 
     qemu_co_mutex_lock(&s->lock);
 
-    while (bytes != 0) {
-        offset_in_cluster = offset & (s->cluster_size - 1);
-        n = s->cluster_size - offset_in_cluster;
-        if (n > bytes) {
-            n = bytes;
+    while (nb_sectors != 0) {
+
+        index_in_cluster = sector_num & (s->cluster_sectors - 1);
+        n = s->cluster_sectors - index_in_cluster;
+        if (n > nb_sectors) {
+            n = nb_sectors;
         }
-        ret = get_cluster_offset(bs, offset, 1, 0, offset_in_cluster,
-                                 offset_in_cluster + n, &cluster_offset);
+        ret = get_cluster_offset(bs, sector_num << 9, 1, 0,
+                                 index_in_cluster,
+                                 index_in_cluster + n, &cluster_offset);
         if (ret < 0) {
             break;
         }
@@ -773,28 +763,30 @@ static coroutine_fn int qcow_co_pwritev(BlockDriverState *bs, uint64_t offset,
         }
         if (bs->encrypted) {
             assert(s->crypto);
-            if (qcrypto_block_encrypt(s->crypto, offset, buf, n, NULL) < 0) {
+            if (qcrypto_block_encrypt(s->crypto, sector_num * BDRV_SECTOR_SIZE,
+                                      buf, n * BDRV_SECTOR_SIZE, NULL) < 0) {
                 ret = -EIO;
                 break;
             }
         }
 
         hd_iov.iov_base = (void *)buf;
-        hd_iov.iov_len = n;
+        hd_iov.iov_len = n * 512;
         qemu_iovec_init_external(&hd_qiov, &hd_iov, 1);
         qemu_co_mutex_unlock(&s->lock);
         BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
-        ret = bdrv_co_pwritev(bs->file, cluster_offset + offset_in_cluster,
-                              n, &hd_qiov, 0);
+        ret = bdrv_co_writev(bs->file,
+                             (cluster_offset >> 9) + index_in_cluster,
+                             n, &hd_qiov);
         qemu_co_mutex_lock(&s->lock);
         if (ret < 0) {
             break;
         }
         ret = 0;
 
-        bytes -= n;
-        offset += n;
-        buf += n;
+        nb_sectors -= n;
+        sector_num += n;
+        buf += n * 512;
     }
     qemu_co_mutex_unlock(&s->lock);
 
@@ -818,50 +810,62 @@ static void qcow_close(BlockDriverState *bs)
     error_free(s->migration_blocker);
 }
 
-static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts,
+static int coroutine_fn qcow_co_create_opts(const char *filename, QemuOpts *opts,
                                             Error **errp)
 {
-    BlockdevCreateOptionsQcow *qcow_opts;
     int header_size, backing_filename_len, l1_size, shift, i;
     QCowHeader header;
     uint8_t *tmp;
     int64_t total_size = 0;
+    char *backing_file = NULL;
+    Error *local_err = NULL;
     int ret;
-    BlockDriverState *bs;
     BlockBackend *qcow_blk;
+    char *encryptfmt = NULL;
+    QDict *options;
+    QDict *encryptopts = NULL;
+    QCryptoBlockCreateOptions *crypto_opts = NULL;
     QCryptoBlock *crypto = NULL;
 
-    assert(opts->driver == BLOCKDEV_DRIVER_QCOW);
-    qcow_opts = &opts->u.qcow;
-
-    /* Sanity checks */
-    total_size = qcow_opts->size;
+    /* Read out options */
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
     if (total_size == 0) {
         error_setg(errp, "Image size is too small, cannot be zero length");
-        return -EINVAL;
+        ret = -EINVAL;
+        goto cleanup;
     }
 
-    if (qcow_opts->has_encrypt &&
-        qcow_opts->encrypt->format != Q_CRYPTO_BLOCK_FORMAT_QCOW)
-    {
-        error_setg(errp, "Unsupported encryption format");
-        return -EINVAL;
+    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
+    encryptfmt = qemu_opt_get_del(opts, BLOCK_OPT_ENCRYPT_FORMAT);
+    if (encryptfmt) {
+        if (qemu_opt_get(opts, BLOCK_OPT_ENCRYPT)) {
+            error_setg(errp, "Options " BLOCK_OPT_ENCRYPT " and "
+                       BLOCK_OPT_ENCRYPT_FORMAT " are mutually exclusive");
+            ret = -EINVAL;
+            goto cleanup;
+        }
+    } else if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
+        encryptfmt = g_strdup("aes");
     }
 
-    /* Create BlockBackend to write to the image */
-    bs = bdrv_open_blockdev_ref(qcow_opts->file, errp);
-    if (bs == NULL) {
-        return -EIO;
-    }
-
-    qcow_blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
-    ret = blk_insert_bs(qcow_blk, bs, errp);
+    ret = bdrv_create_file(filename, opts, &local_err);
     if (ret < 0) {
-        goto exit;
+        error_propagate(errp, local_err);
+        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) {
+        error_propagate(errp, local_err);
+        ret = -EIO;
+        goto cleanup;
+    }
+
     blk_set_allow_write_beyond_eof(qcow_blk, true);
 
-    /* Create image format */
     ret = blk_truncate(qcow_blk, 0, PREALLOC_MODE_OFF, errp);
     if (ret < 0) {
         goto exit;
@@ -873,15 +877,16 @@ static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts,
     header.size = cpu_to_be64(total_size);
     header_size = sizeof(header);
     backing_filename_len = 0;
-    if (qcow_opts->has_backing_file) {
-        if (strcmp(qcow_opts->backing_file, "fat:")) {
+    if (backing_file) {
+        if (strcmp(backing_file, "fat:")) {
             header.backing_file_offset = cpu_to_be64(header_size);
-            backing_filename_len = strlen(qcow_opts->backing_file);
+            backing_filename_len = strlen(backing_file);
             header.backing_file_size = cpu_to_be32(backing_filename_len);
             header_size += backing_filename_len;
         } else {
             /* special backing file for vvfat */
-            qcow_opts->has_backing_file = false;
+            g_free(backing_file);
+            backing_file = NULL;
         }
         header.cluster_bits = 9; /* 512 byte cluster to avoid copying
                                     unmodified sectors */
@@ -896,10 +901,26 @@ static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts,
 
     header.l1_table_offset = cpu_to_be64(header_size);
 
-    if (qcow_opts->has_encrypt) {
+    options = qemu_opts_to_qdict(opts, NULL);
+    qdict_extract_subqdict(options, &encryptopts, "encrypt.");
+    QDECREF(options);
+    if (encryptfmt) {
+        if (!g_str_equal(encryptfmt, "aes")) {
+            error_setg(errp, "Unknown encryption format '%s', expected 'aes'",
+                       encryptfmt);
+            ret = -EINVAL;
+            goto exit;
+        }
         header.crypt_method = cpu_to_be32(QCOW_CRYPT_AES);
 
-        crypto = qcrypto_block_create(qcow_opts->encrypt, "encrypt.",
+        crypto_opts = block_crypto_create_opts_init(
+            Q_CRYPTO_BLOCK_FORMAT_QCOW, encryptopts, errp);
+        if (!crypto_opts) {
+            ret = -EINVAL;
+            goto exit;
+        }
+
+        crypto = qcrypto_block_create(crypto_opts, "encrypt.",
                                       NULL, NULL, NULL, errp);
         if (!crypto) {
             ret = -EINVAL;
@@ -915,9 +936,9 @@ static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts,
         goto exit;
     }
 
-    if (qcow_opts->has_backing_file) {
+    if (backing_file) {
         ret = blk_pwrite(qcow_blk, sizeof(header),
-                         qcow_opts->backing_file, backing_filename_len, 0);
+                         backing_file, backing_filename_len, 0);
         if (ret != backing_filename_len) {
             goto exit;
         }
@@ -938,96 +959,12 @@ static int coroutine_fn qcow_co_create(BlockdevCreateOptions *opts,
     ret = 0;
 exit:
     blk_unref(qcow_blk);
+cleanup:
+    QDECREF(encryptopts);
+    g_free(encryptfmt);
     qcrypto_block_free(crypto);
-    return ret;
-}
-
-static int coroutine_fn qcow_co_create_opts(const char *filename,
-                                            QemuOpts *opts, Error **errp)
-{
-    BlockdevCreateOptions *create_options = NULL;
-    BlockDriverState *bs = NULL;
-    QDict *qdict;
-    Visitor *v;
-    const char *val;
-    Error *local_err = NULL;
-    int ret;
-
-    static const QDictRenames opt_renames[] = {
-        { BLOCK_OPT_BACKING_FILE,       "backing-file" },
-        { BLOCK_OPT_ENCRYPT,            BLOCK_OPT_ENCRYPT_FORMAT },
-        { NULL, NULL },
-    };
-
-    /* Parse options and convert legacy syntax */
-    qdict = qemu_opts_to_qdict_filtered(opts, NULL, &qcow_create_opts, true);
-
-    val = qdict_get_try_str(qdict, BLOCK_OPT_ENCRYPT);
-    if (val && !strcmp(val, "on")) {
-        qdict_put_str(qdict, BLOCK_OPT_ENCRYPT, "qcow");
-    } else if (val && !strcmp(val, "off")) {
-        qdict_del(qdict, BLOCK_OPT_ENCRYPT);
-    }
-
-    val = qdict_get_try_str(qdict, BLOCK_OPT_ENCRYPT_FORMAT);
-    if (val && !strcmp(val, "aes")) {
-        qdict_put_str(qdict, BLOCK_OPT_ENCRYPT_FORMAT, "qcow");
-    }
-
-    if (!qdict_rename_keys(qdict, opt_renames, errp)) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* Create and open the file (protocol layer) */
-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto fail;
-    }
-
-    bs = bdrv_open(filename, NULL, NULL,
-                   BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
-    if (bs == NULL) {
-        ret = -EIO;
-        goto fail;
-    }
-
-    /* Now get the QAPI type BlockdevCreateOptions */
-    qdict_put_str(qdict, "driver", "qcow");
-    qdict_put_str(qdict, "file", bs->node_name);
-
-    v = qobject_input_visitor_new_flat_confused(qdict, errp);
-    if (!v) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err);
-    visit_free(v);
-
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* Silently round up size */
-    assert(create_options->driver == BLOCKDEV_DRIVER_QCOW);
-    create_options->u.qcow.size =
-        ROUND_UP(create_options->u.qcow.size, BDRV_SECTOR_SIZE);
-
-    /* Create the qcow image (format layer) */
-    ret = qcow_co_create(create_options, errp);
-    if (ret < 0) {
-        goto fail;
-    }
-
-    ret = 0;
-fail:
-    qobject_unref(qdict);
-    bdrv_unref(bs);
-    qapi_free_BlockdevCreateOptions(create_options);
+    qapi_free_QCryptoBlockCreateOptions(crypto_opts);
+    g_free(backing_file);
     return ret;
 }
 
@@ -1109,7 +1046,8 @@ 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_pwritev(bs, offset, bytes, qiov, 0);
+        ret = qcow_co_writev(bs, offset >> BDRV_SECTOR_BITS,
+                             bytes >> BDRV_SECTOR_BITS, qiov);
         if (ret < 0) {
             goto fail;
         }
@@ -1190,14 +1128,12 @@ static BlockDriver bdrv_qcow = {
     .bdrv_close		= qcow_close,
     .bdrv_child_perm        = bdrv_format_default_perms,
     .bdrv_reopen_prepare    = qcow_reopen_prepare,
-    .bdrv_co_create         = qcow_co_create,
     .bdrv_co_create_opts    = qcow_co_create_opts,
     .bdrv_has_zero_init     = bdrv_has_zero_init_1,
     .supports_backing       = true,
-    .bdrv_refresh_limits    = qcow_refresh_limits,
 
-    .bdrv_co_preadv         = qcow_co_preadv,
-    .bdrv_co_pwritev        = qcow_co_pwritev,
+    .bdrv_co_readv          = qcow_co_readv,
+    .bdrv_co_writev         = qcow_co_writev,
     .bdrv_co_block_status   = qcow_co_block_status,
 
     .bdrv_make_empty        = qcow_make_empty,

block/qcow2-bitmap.c

@@ -30,7 +30,7 @@
 #include "qemu/cutils.h"
 
 #include "block/block_int.h"
-#include "qcow2.h"
+#include "block/qcow2.h"
 
 /* NOTICE: BME here means Bitmaps Extension and used as a namespace for
  * _internal_ constants. Please do not use this _internal_ abbreviation for
@@ -254,6 +254,7 @@ static int free_bitmap_clusters(BlockDriverState *bs, Qcow2BitmapTable *tb)
 
     ret = bitmap_table_load(bs, tb, &bitmap_table);
     if (ret < 0) {
+        assert(bitmap_table == NULL);
         return ret;
     }
 
@@ -775,12 +776,7 @@ static int bitmap_list_store(BlockDriverState *bs, Qcow2BitmapList *bm_list,
         }
     }
 
-    /* Actually, even in in-place case ignoring QCOW2_OL_BITMAP_DIRECTORY is not
-     * necessary, because we drop QCOW2_AUTOCLEAR_BITMAPS when updating bitmap
-     * directory in-place (actually, turn-off the extension), which is checked
-     * in qcow2_check_metadata_overlap() */
-    ret = qcow2_pre_write_overlap_check(
-            bs, in_place ? QCOW2_OL_BITMAP_DIRECTORY : 0, dir_offset, dir_size);
+    ret = qcow2_pre_write_overlap_check(bs, 0, dir_offset, dir_size);
     if (ret < 0) {
         goto fail;
     }
@@ -1008,8 +1004,7 @@ fail:
     return false;
 }
 
-int qcow2_reopen_bitmaps_rw_hint(BlockDriverState *bs, bool *header_updated,
-                                 Error **errp)
+int qcow2_reopen_bitmaps_rw(BlockDriverState *bs, Error **errp)
 {
     BDRVQcow2State *s = bs->opaque;
     Qcow2BitmapList *bm_list;
@@ -1017,10 +1012,6 @@ int qcow2_reopen_bitmaps_rw_hint(BlockDriverState *bs, bool *header_updated,
     GSList *ro_dirty_bitmaps = NULL;
     int ret = 0;
 
-    if (header_updated != NULL) {
-        *header_updated = false;
-    }
-
     if (s->nb_bitmaps == 0) {
         /* No bitmaps - nothing to do */
         return 0;
@@ -1064,9 +1055,6 @@ int qcow2_reopen_bitmaps_rw_hint(BlockDriverState *bs, bool *header_updated,
             error_setg_errno(errp, -ret, "Can't update bitmap directory");
             goto out;
         }
-        if (header_updated != NULL) {
-            *header_updated = true;
-        }
         g_slist_foreach(ro_dirty_bitmaps, set_readonly_helper, false);
     }
 
@@ -1077,11 +1065,6 @@ out:
     return ret;
 }
 
-int qcow2_reopen_bitmaps_rw(BlockDriverState *bs, Error **errp)
-{
-    return qcow2_reopen_bitmaps_rw_hint(bs, NULL, errp);
-}
-
 /* store_bitmap_data()
  * Store bitmap to image, filling bitmap table accordingly.
  */

block/qcow2-cluster.c

@@ -28,7 +28,7 @@
 #include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
-#include "qcow2.h"
+#include "block/qcow2.h"
 #include "qemu/bswap.h"
 #include "trace.h"
 
@@ -994,17 +994,6 @@ err:
     return ret;
  }
 
-/**
- * Frees the allocated clusters because the request failed and they won't
- * actually be linked.
- */
-void qcow2_alloc_cluster_abort(BlockDriverState *bs, QCowL2Meta *m)
-{
-    BDRVQcow2State *s = bs->opaque;
-    qcow2_free_clusters(bs, m->alloc_offset, m->nb_clusters << s->cluster_bits,
-                        QCOW2_DISCARD_NEVER);
-}
-
 /*
  * Returns the number of contiguous clusters that can be used for an allocating
  * write, but require COW to be performed (this includes yet unallocated space,

block/qcow2-refcount.c

@@ -26,7 +26,7 @@
 #include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
-#include "qcow2.h"
+#include "block/qcow2.h"
 #include "qemu/range.h"
 #include "qemu/bswap.h"
 #include "qemu/cutils.h"
@@ -734,7 +734,7 @@ void qcow2_process_discards(BlockDriverState *bs, int ret)
 
         /* Discard is optional, ignore the return value */
         if (ret >= 0) {
-            bdrv_pdiscard(bs->file, d->offset, d->bytes);
+            bdrv_pdiscard(bs->file->bs, d->offset, d->bytes);
         }
 
         g_free(d);
@@ -839,13 +839,6 @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
                 qcow2_cache_put(s->refcount_block_cache, &refcount_block);
             }
             ret = alloc_refcount_block(bs, cluster_index, &refcount_block);
-            /* If the caller needs to restart the search for free clusters,
-             * try the same ones first to see if they're still free. */
-            if (ret == -EAGAIN) {
-                if (s->free_cluster_index > (start >> s->cluster_bits)) {
-                    s->free_cluster_index = (start >> s->cluster_bits);
-                }
-            }
             if (ret < 0) {
                 goto fail;
             }
@@ -1577,9 +1570,9 @@ static int check_refcounts_l2(BlockDriverState *bs, BdrvCheckResult *res,
         case QCOW2_CLUSTER_COMPRESSED:
             /* Compressed clusters don't have QCOW_OFLAG_COPIED */
             if (l2_entry & QCOW_OFLAG_COPIED) {
-                fprintf(stderr, "ERROR: coffset=0x%" PRIx64 ": "
+                fprintf(stderr, "ERROR: cluster %" PRId64 ": "
                     "copied flag must never be set for compressed "
-                    "clusters\n", l2_entry & s->cluster_offset_mask);
+                    "clusters\n", l2_entry >> s->cluster_bits);
                 l2_entry &= ~QCOW_OFLAG_COPIED;
                 res->corruptions++;
             }
@@ -1799,19 +1792,6 @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res,
     int ret;
     uint64_t refcount;
     int i, j;
-    bool repair;
-
-    if (fix & BDRV_FIX_ERRORS) {
-        /* Always repair */
-        repair = true;
-    } else if (fix & BDRV_FIX_LEAKS) {
-        /* Repair only if that seems safe: This function is always
-         * called after the refcounts have been fixed, so the refcount
-         * is accurate if that repair was successful */
-        repair = !res->check_errors && !res->corruptions && !res->leaks;
-    } else {
-        repair = false;
-    }
 
     for (i = 0; i < s->l1_size; i++) {
         uint64_t l1_entry = s->l1_table[i];
@@ -1831,8 +1811,10 @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res,
         if ((refcount == 1) != ((l1_entry & QCOW_OFLAG_COPIED) != 0)) {
             fprintf(stderr, "%s OFLAG_COPIED L2 cluster: l1_index=%d "
                     "l1_entry=%" PRIx64 " refcount=%" PRIu64 "\n",
-                    repair ? "Repairing" : "ERROR", i, l1_entry, refcount);
-            if (repair) {
+                    fix & BDRV_FIX_ERRORS ? "Repairing" :
+                                            "ERROR",
+                    i, l1_entry, refcount);
+            if (fix & BDRV_FIX_ERRORS) {
                 s->l1_table[i] = refcount == 1
                                ? l1_entry |  QCOW_OFLAG_COPIED
                                : l1_entry & ~QCOW_OFLAG_COPIED;
@@ -1873,8 +1855,10 @@ static int check_oflag_copied(BlockDriverState *bs, BdrvCheckResult *res,
                 if ((refcount == 1) != ((l2_entry & QCOW_OFLAG_COPIED) != 0)) {
                     fprintf(stderr, "%s OFLAG_COPIED data cluster: "
                             "l2_entry=%" PRIx64 " refcount=%" PRIu64 "\n",
-                            repair ? "Repairing" : "ERROR", l2_entry, refcount);
-                    if (repair) {
+                            fix & BDRV_FIX_ERRORS ? "Repairing" :
+                                                    "ERROR",
+                            l2_entry, refcount);
+                    if (fix & BDRV_FIX_ERRORS) {
                         l2_table[j] = cpu_to_be64(refcount == 1
                                     ? l2_entry |  QCOW_OFLAG_COPIED
                                     : l2_entry & ~QCOW_OFLAG_COPIED);
@@ -2705,16 +2689,6 @@ int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset,
         }
     }
 
-    if ((chk & QCOW2_OL_BITMAP_DIRECTORY) &&
-        (s->autoclear_features & QCOW2_AUTOCLEAR_BITMAPS))
-    {
-        if (overlaps_with(s->bitmap_directory_offset,
-                          s->bitmap_directory_size))
-        {
-            return QCOW2_OL_BITMAP_DIRECTORY;
-        }
-    }
-
     return 0;
 }
 

block/qcow2-snapshot.c

@@ -25,7 +25,7 @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "block/block_int.h"
-#include "qcow2.h"
+#include "block/qcow2.h"
 #include "qemu/bswap.h"
 #include "qemu/error-report.h"
 #include "qemu/cutils.h"

block/qcow2.h

@@ -77,6 +77,10 @@
 #define DEFAULT_L2_CACHE_CLUSTERS 8 /* clusters */
 #define DEFAULT_L2_CACHE_BYTE_SIZE 1048576 /* bytes */
 
+/* The refblock cache needs only a fourth of the L2 cache size to cover as many
+ * clusters */
+#define DEFAULT_L2_REFCOUNT_SIZE_RATIO 4
+
 #define DEFAULT_CLUSTER_SIZE 65536
 
 
@@ -94,7 +98,6 @@
 #define QCOW2_OPT_OVERLAP_SNAPSHOT_TABLE "overlap-check.snapshot-table"
 #define QCOW2_OPT_OVERLAP_INACTIVE_L1 "overlap-check.inactive-l1"
 #define QCOW2_OPT_OVERLAP_INACTIVE_L2 "overlap-check.inactive-l2"
-#define QCOW2_OPT_OVERLAP_BITMAP_DIRECTORY "overlap-check.bitmap-directory"
 #define QCOW2_OPT_CACHE_SIZE "cache-size"
 #define QCOW2_OPT_L2_CACHE_SIZE "l2-cache-size"
 #define QCOW2_OPT_L2_CACHE_ENTRY_SIZE "l2-cache-entry-size"
@@ -295,7 +298,6 @@ typedef struct BDRVQcow2State {
     uint32_t nb_bitmaps;
     uint64_t bitmap_directory_size;
     uint64_t bitmap_directory_offset;
-    bool dirty_bitmaps_loaded;
 
     int flags;
     int qcow_version;
@@ -327,9 +329,6 @@ typedef struct BDRVQcow2State {
      * override) */
     char *image_backing_file;
     char *image_backing_format;
-
-    CoQueue compress_wait_queue;
-    int nb_compress_threads;
 } BDRVQcow2State;
 
 typedef struct Qcow2COWRegion {
@@ -409,9 +408,8 @@ typedef enum QCow2MetadataOverlap {
     QCOW2_OL_SNAPSHOT_TABLE_BITNR = 5,
     QCOW2_OL_INACTIVE_L1_BITNR    = 6,
     QCOW2_OL_INACTIVE_L2_BITNR    = 7,
-    QCOW2_OL_BITMAP_DIRECTORY_BITNR = 8,
 
-    QCOW2_OL_MAX_BITNR              = 9,
+    QCOW2_OL_MAX_BITNR            = 8,
 
     QCOW2_OL_NONE           = 0,
     QCOW2_OL_MAIN_HEADER    = (1 << QCOW2_OL_MAIN_HEADER_BITNR),
@@ -424,13 +422,12 @@ typedef enum QCow2MetadataOverlap {
     /* NOTE: Checking overlaps with inactive L2 tables will result in bdrv
      * reads. */
     QCOW2_OL_INACTIVE_L2    = (1 << QCOW2_OL_INACTIVE_L2_BITNR),
-    QCOW2_OL_BITMAP_DIRECTORY = (1 << QCOW2_OL_BITMAP_DIRECTORY_BITNR),
 } QCow2MetadataOverlap;
 
 /* Perform all overlap checks which can be done in constant time */
 #define QCOW2_OL_CONSTANT \
     (QCOW2_OL_MAIN_HEADER | QCOW2_OL_ACTIVE_L1 | QCOW2_OL_REFCOUNT_TABLE | \
-     QCOW2_OL_SNAPSHOT_TABLE | QCOW2_OL_BITMAP_DIRECTORY)
+     QCOW2_OL_SNAPSHOT_TABLE)
 
 /* Perform all overlap checks which don't require disk access */
 #define QCOW2_OL_CACHED \
@@ -620,7 +617,6 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
                                          int compressed_size);
 
 int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m);
-void qcow2_alloc_cluster_abort(BlockDriverState *bs, QCowL2Meta *m);
 int qcow2_cluster_discard(BlockDriverState *bs, uint64_t offset,
                           uint64_t bytes, enum qcow2_discard_type type,
                           bool full_discard);
@@ -675,8 +671,6 @@ int qcow2_check_bitmaps_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
                                   void **refcount_table,
                                   int64_t *refcount_table_size);
 bool qcow2_load_dirty_bitmaps(BlockDriverState *bs, Error **errp);
-int qcow2_reopen_bitmaps_rw_hint(BlockDriverState *bs, bool *header_updated,
-                                 Error **errp);
 int qcow2_reopen_bitmaps_rw(BlockDriverState *bs, Error **errp);
 void qcow2_store_persistent_dirty_bitmaps(BlockDriverState *bs, Error **errp);
 int qcow2_reopen_bitmaps_ro(BlockDriverState *bs, Error **errp);

block/qed.c

@@ -13,7 +13,6 @@
  */
 
 #include "qemu/osdep.h"
-#include "block/qdict.h"
 #include "qapi/error.h"
 #include "qemu/timer.h"
 #include "qemu/bswap.h"
@@ -21,11 +20,6 @@
 #include "trace.h"
 #include "qed.h"
 #include "sysemu/block-backend.h"
-#include "qapi/qmp/qdict.h"
-#include "qapi/qobject-input-visitor.h"
-#include "qapi/qapi-visit-block-core.h"
-
-static QemuOptsList qed_create_opts;
 
 static int bdrv_qed_probe(const uint8_t *buf, int buf_size,
                           const char *filename)
@@ -600,78 +594,43 @@ static void bdrv_qed_close(BlockDriverState *bs)
     qemu_vfree(s->l1_table);
 }
 
-static int coroutine_fn bdrv_qed_co_create(BlockdevCreateOptions *opts,
-                                           Error **errp)
+static int qed_create(const char *filename, uint32_t cluster_size,
+                      uint64_t image_size, uint32_t table_size,
+                      const char *backing_file, const char *backing_fmt,
+                      QemuOpts *opts, Error **errp)
 {
-    BlockdevCreateOptionsQed *qed_opts;
-    BlockBackend *blk = NULL;
-    BlockDriverState *bs = NULL;
-
-    QEDHeader header;
-    QEDHeader le_header;
-    uint8_t *l1_table = NULL;
-    size_t l1_size;
-    int ret = 0;
-
-    assert(opts->driver == BLOCKDEV_DRIVER_QED);
-    qed_opts = &opts->u.qed;
-
-    /* Validate options and set default values */
-    if (!qed_opts->has_cluster_size) {
-        qed_opts->cluster_size = QED_DEFAULT_CLUSTER_SIZE;
-    }
-    if (!qed_opts->has_table_size) {
-        qed_opts->table_size = QED_DEFAULT_TABLE_SIZE;
-    }
-
-    if (!qed_is_cluster_size_valid(qed_opts->cluster_size)) {
-        error_setg(errp, "QED cluster size must be within range [%u, %u] "
-                         "and power of 2",
-                   QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE);
-        return -EINVAL;
-    }
-    if (!qed_is_table_size_valid(qed_opts->table_size)) {
-        error_setg(errp, "QED table size must be within range [%u, %u] "
-                         "and power of 2",
-                   QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE);
-        return -EINVAL;
-    }
-    if (!qed_is_image_size_valid(qed_opts->size, qed_opts->cluster_size,
-                                 qed_opts->table_size))
-    {
-        error_setg(errp, "QED image size must be a non-zero multiple of "
-                         "cluster size and less than %" PRIu64 " bytes",
-                   qed_max_image_size(qed_opts->cluster_size,
-                                      qed_opts->table_size));
-        return -EINVAL;
-    }
-
-    /* Create BlockBackend to write to the image */
-    bs = bdrv_open_blockdev_ref(qed_opts->file, errp);
-    if (bs == NULL) {
-        return -EIO;
-    }
-
-    blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
-    ret = blk_insert_bs(blk, bs, errp);
-    if (ret < 0) {
-        goto out;
-    }
-    blk_set_allow_write_beyond_eof(blk, true);
-
-    /* Prepare image format */
-    header = (QEDHeader) {
+    QEDHeader header = {
         .magic = QED_MAGIC,
-        .cluster_size = qed_opts->cluster_size,
-        .table_size = qed_opts->table_size,
+        .cluster_size = cluster_size,
+        .table_size = table_size,
         .header_size = 1,
         .features = 0,
         .compat_features = 0,
-        .l1_table_offset = qed_opts->cluster_size,
-        .image_size = qed_opts->size,
+        .l1_table_offset = cluster_size,
+        .image_size = image_size,
     };
+    QEDHeader le_header;
+    uint8_t *l1_table = NULL;
+    size_t l1_size = header.cluster_size * header.table_size;
+    Error *local_err = NULL;
+    int ret = 0;
+    BlockBackend *blk;
 
-    l1_size = header.cluster_size * header.table_size;
+    ret = bdrv_create_file(filename, opts, &local_err);
+    if (ret < 0) {
+        error_propagate(errp, local_err);
+        return ret;
+    }
+
+    blk = blk_new_open(filename, NULL, NULL,
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
+    if (blk == NULL) {
+        error_propagate(errp, local_err);
+        return -EIO;
+    }
+
+    blk_set_allow_write_beyond_eof(blk, true);
 
     /* File must start empty and grow, check truncate is supported */
     ret = blk_truncate(blk, 0, PREALLOC_MODE_OFF, errp);
@@ -679,25 +638,22 @@ static int coroutine_fn bdrv_qed_co_create(BlockdevCreateOptions *opts,
         goto out;
     }
 
-    if (qed_opts->has_backing_file) {
+    if (backing_file) {
         header.features |= QED_F_BACKING_FILE;
         header.backing_filename_offset = sizeof(le_header);
-        header.backing_filename_size = strlen(qed_opts->backing_file);
+        header.backing_filename_size = strlen(backing_file);
 
-        if (qed_opts->has_backing_fmt) {
-            const char *backing_fmt = BlockdevDriver_str(qed_opts->backing_fmt);
         if (qed_fmt_is_raw(backing_fmt)) {
             header.features |= QED_F_BACKING_FORMAT_NO_PROBE;
         }
     }
-    }
 
     qed_header_cpu_to_le(&header, &le_header);
     ret = blk_pwrite(blk, 0, &le_header, sizeof(le_header), 0);
     if (ret < 0) {
         goto out;
     }
-    ret = blk_pwrite(blk, sizeof(le_header), qed_opts->backing_file,
+    ret = blk_pwrite(blk, sizeof(le_header), backing_file,
                      header.backing_filename_size, 0);
     if (ret < 0) {
         goto out;
@@ -713,7 +669,6 @@ static int coroutine_fn bdrv_qed_co_create(BlockdevCreateOptions *opts,
 out:
     g_free(l1_table);
     blk_unref(blk);
-    bdrv_unref(bs);
     return ret;
 }
 
@@ -721,74 +676,51 @@ static int coroutine_fn bdrv_qed_co_create_opts(const char *filename,
                                                 QemuOpts *opts,
                                                 Error **errp)
 {
-    BlockdevCreateOptions *create_options = NULL;
-    QDict *qdict;
-    Visitor *v;
-    BlockDriverState *bs = NULL;
-    Error *local_err = NULL;
+    uint64_t image_size = 0;
+    uint32_t cluster_size = QED_DEFAULT_CLUSTER_SIZE;
+    uint32_t table_size = QED_DEFAULT_TABLE_SIZE;
+    char *backing_file = NULL;
+    char *backing_fmt = NULL;
     int ret;
 
-    static const QDictRenames opt_renames[] = {
-        { BLOCK_OPT_BACKING_FILE,       "backing-file" },
-        { BLOCK_OPT_BACKING_FMT,        "backing-fmt" },
-        { BLOCK_OPT_CLUSTER_SIZE,       "cluster-size" },
-        { BLOCK_OPT_TABLE_SIZE,         "table-size" },
-        { NULL, NULL },
-    };
+    image_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
+    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
+    backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT);
+    cluster_size = qemu_opt_get_size_del(opts,
+                                         BLOCK_OPT_CLUSTER_SIZE,
+                                         QED_DEFAULT_CLUSTER_SIZE);
+    table_size = qemu_opt_get_size_del(opts, BLOCK_OPT_TABLE_SIZE,
+                                       QED_DEFAULT_TABLE_SIZE);
 
-    /* Parse options and convert legacy syntax */
-    qdict = qemu_opts_to_qdict_filtered(opts, NULL, &qed_create_opts, true);
-
-    if (!qdict_rename_keys(qdict, opt_renames, errp)) {
+    if (!qed_is_cluster_size_valid(cluster_size)) {
+        error_setg(errp, "QED cluster size must be within range [%u, %u] "
+                         "and power of 2",
+                   QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE);
         ret = -EINVAL;
-        goto fail;
+        goto finish;
     }
-
-    /* Create and open the file (protocol layer) */
-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto fail;
-    }
-
-    bs = bdrv_open(filename, NULL, NULL,
-                   BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
-    if (bs == NULL) {
-        ret = -EIO;
-        goto fail;
-    }
-
-    /* Now get the QAPI type BlockdevCreateOptions */
-    qdict_put_str(qdict, "driver", "qed");
-    qdict_put_str(qdict, "file", bs->node_name);
-
-    v = qobject_input_visitor_new_flat_confused(qdict, errp);
-    if (!v) {
+    if (!qed_is_table_size_valid(table_size)) {
+        error_setg(errp, "QED table size must be within range [%u, %u] "
+                         "and power of 2",
+                   QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE);
         ret = -EINVAL;
-        goto fail;
+        goto finish;
     }
-
-    visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err);
-    visit_free(v);
-
-    if (local_err) {
-        error_propagate(errp, local_err);
+    if (!qed_is_image_size_valid(image_size, cluster_size, table_size)) {
+        error_setg(errp, "QED image size must be a non-zero multiple of "
+                         "cluster size and less than %" PRIu64 " bytes",
+                   qed_max_image_size(cluster_size, table_size));
         ret = -EINVAL;
-        goto fail;
+        goto finish;
     }
 
-    /* Silently round up size */
-    assert(create_options->driver == BLOCKDEV_DRIVER_QED);
-    create_options->u.qed.size =
-        ROUND_UP(create_options->u.qed.size, BDRV_SECTOR_SIZE);
+    ret = qed_create(filename, cluster_size, image_size, table_size,
+                     backing_file, backing_fmt, opts, errp);
 
-    /* Create the qed image (format layer) */
-    ret = bdrv_qed_co_create(create_options, errp);
-
-fail:
-    qobject_unref(qdict);
-    bdrv_unref(bs);
-    qapi_free_BlockdevCreateOptions(create_options);
+finish:
+    g_free(backing_file);
+    g_free(backing_fmt);
     return ret;
 }
 
@@ -1434,9 +1366,8 @@ static int coroutine_fn bdrv_qed_co_readv(BlockDriverState *bs,
 
 static int coroutine_fn bdrv_qed_co_writev(BlockDriverState *bs,
                                            int64_t sector_num, int nb_sectors,
-                                           QEMUIOVector *qiov, int flags)
+                                           QEMUIOVector *qiov)
 {
-    assert(!flags);
     return qed_co_request(bs, sector_num, qiov, nb_sectors, QED_AIOCB_WRITE);
 }
 
@@ -1467,10 +1398,8 @@ static int coroutine_fn bdrv_qed_co_pwrite_zeroes(BlockDriverState *bs,
                           QED_AIOCB_WRITE | QED_AIOCB_ZERO);
 }
 
-static int coroutine_fn bdrv_qed_co_truncate(BlockDriverState *bs,
-                                             int64_t offset,
-                                             PreallocMode prealloc,
-                                             Error **errp)
+static int bdrv_qed_truncate(BlockDriverState *bs, int64_t offset,
+                             PreallocMode prealloc, Error **errp)
 {
     BDRVQEDState *s = bs->opaque;
     uint64_t old_image_size;
@@ -1673,14 +1602,13 @@ static BlockDriver bdrv_qed = {
     .bdrv_close               = bdrv_qed_close,
     .bdrv_reopen_prepare      = bdrv_qed_reopen_prepare,
     .bdrv_child_perm          = bdrv_format_default_perms,
-    .bdrv_co_create           = bdrv_qed_co_create,
     .bdrv_co_create_opts      = bdrv_qed_co_create_opts,
     .bdrv_has_zero_init       = bdrv_has_zero_init_1,
     .bdrv_co_block_status     = bdrv_qed_co_block_status,
     .bdrv_co_readv            = bdrv_qed_co_readv,
     .bdrv_co_writev           = bdrv_qed_co_writev,
     .bdrv_co_pwrite_zeroes    = bdrv_qed_co_pwrite_zeroes,
-    .bdrv_co_truncate         = bdrv_qed_co_truncate,
+    .bdrv_truncate            = bdrv_qed_truncate,
     .bdrv_getlength           = bdrv_qed_getlength,
     .bdrv_get_info            = bdrv_qed_get_info,
     .bdrv_refresh_limits      = bdrv_qed_refresh_limits,

block/quorum.c

@@ -17,7 +17,6 @@
 #include "qemu/cutils.h"
 #include "qemu/option.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "qapi/error.h"
 #include "qapi/qapi-events-block.h"
 #include "qapi/qmp/qdict.h"
@@ -116,7 +115,6 @@ struct QuorumAIOCB {
     /* Request metadata */
     uint64_t offset;
     uint64_t bytes;
-    int flags;
 
     QEMUIOVector *qiov;         /* calling IOV */
 
@@ -159,8 +157,7 @@ static bool quorum_64bits_compare(QuorumVoteValue *a, QuorumVoteValue *b)
 static QuorumAIOCB *quorum_aio_get(BlockDriverState *bs,
                                    QEMUIOVector *qiov,
                                    uint64_t offset,
-                                   uint64_t bytes,
-                                   int flags)
+                                   uint64_t bytes)
 {
     BDRVQuorumState *s = bs->opaque;
     QuorumAIOCB *acb = g_new(QuorumAIOCB, 1);
@@ -171,7 +168,6 @@ static QuorumAIOCB *quorum_aio_get(BlockDriverState *bs,
         .bs                 = bs,
         .offset             = offset,
         .bytes              = bytes,
-        .flags              = flags,
         .qiov               = qiov,
         .votes.compare      = quorum_sha256_compare,
         .votes.vote_list    = QLIST_HEAD_INITIALIZER(acb.votes.vote_list),
@@ -275,11 +271,9 @@ static void quorum_rewrite_entry(void *opaque)
     BDRVQuorumState *s = acb->bs->opaque;
 
     /* Ignore any errors, it's just a correction attempt for already
-     * corrupted data.
-     * Mask out BDRV_REQ_WRITE_UNCHANGED because this overwrites the
-     * area with different data from the other children. */
+     * corrupted data. */
     bdrv_co_pwritev(s->children[co->idx], acb->offset, acb->bytes,
-                    acb->qiov, acb->flags & ~BDRV_REQ_WRITE_UNCHANGED);
+                    acb->qiov, 0);
 
     /* Wake up the caller after the last rewrite */
     acb->rewrite_count--;
@@ -614,7 +608,7 @@ static void read_quorum_children_entry(void *opaque)
 static int read_quorum_children(QuorumAIOCB *acb)
 {
     BDRVQuorumState *s = acb->bs->opaque;
-    int i;
+    int i, ret;
 
     acb->children_read = s->num_children;
     for (i = 0; i < s->num_children; i++) {
@@ -649,7 +643,9 @@ static int read_quorum_children(QuorumAIOCB *acb)
         qemu_coroutine_yield();
     }
 
-    return acb->vote_ret;
+    ret = acb->vote_ret;
+
+    return ret;
 }
 
 static int read_fifo_child(QuorumAIOCB *acb)
@@ -677,7 +673,7 @@ static int quorum_co_preadv(BlockDriverState *bs, uint64_t offset,
                             uint64_t bytes, QEMUIOVector *qiov, int flags)
 {
     BDRVQuorumState *s = bs->opaque;
-    QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes, flags);
+    QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes);
     int ret;
 
     acb->is_read = true;
@@ -703,7 +699,7 @@ static void write_quorum_entry(void *opaque)
 
     sacb->bs = s->children[i]->bs;
     sacb->ret = bdrv_co_pwritev(s->children[i], acb->offset, acb->bytes,
-                                acb->qiov, acb->flags);
+                                acb->qiov, 0);
     if (sacb->ret == 0) {
         acb->success_count++;
     } else {
@@ -723,7 +719,7 @@ static int quorum_co_pwritev(BlockDriverState *bs, uint64_t offset,
                              uint64_t bytes, QEMUIOVector *qiov, int flags)
 {
     BDRVQuorumState *s = bs->opaque;
-    QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes, flags);
+    QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes);
     int i, ret;
 
     for (i = 0; i < s->num_children; i++) {
@@ -965,8 +961,6 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
     }
     s->next_child_index = s->num_children;
 
-    bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED;
-
     g_free(opened);
     goto exit;
 
@@ -1088,8 +1082,8 @@ static void quorum_refresh_filename(BlockDriverState *bs, QDict *options)
 
     children = qlist_new();
     for (i = 0; i < s->num_children; i++) {
-        qlist_append(children,
-                     qobject_ref(s->children[i]->bs->full_open_options));
+        QINCREF(s->children[i]->bs->full_open_options);
+        qlist_append(children, s->children[i]->bs->full_open_options);
     }
 
     opts = qdict_new();

block/raw-format.c

@@ -167,37 +167,16 @@ static void raw_reopen_abort(BDRVReopenState *state)
     state->opaque = NULL;
 }
 
-/* Check and adjust the offset, against 'offset' and 'size' options. */
-static inline int raw_adjust_offset(BlockDriverState *bs, uint64_t *offset,
-                                    uint64_t bytes, bool is_write)
-{
-    BDRVRawState *s = bs->opaque;
-
-    if (s->has_size && (*offset > s->size || bytes > (s->size - *offset))) {
-        /* There's not enough space for the write, or the read request is
-         * out-of-range. Don't read/write anything to prevent leaking out of
-         * the size specified in options. */
-        return is_write ? -ENOSPC : -EINVAL;
-    }
-
-    if (*offset > INT64_MAX - s->offset) {
-        return -EINVAL;
-    }
-    *offset += s->offset;
-
-    return 0;
-}
-
 static int coroutine_fn raw_co_preadv(BlockDriverState *bs, uint64_t offset,
                                       uint64_t bytes, QEMUIOVector *qiov,
                                       int flags)
 {
-    int ret;
+    BDRVRawState *s = bs->opaque;
 
-    ret = raw_adjust_offset(bs, &offset, bytes, false);
-    if (ret) {
-        return ret;
+    if (offset > UINT64_MAX - s->offset) {
+        return -EINVAL;
     }
+    offset += s->offset;
 
     BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
     return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
@@ -207,11 +186,23 @@ static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, uint64_t offset,
                                        uint64_t bytes, QEMUIOVector *qiov,
                                        int flags)
 {
+    BDRVRawState *s = bs->opaque;
     void *buf = NULL;
     BlockDriver *drv;
     QEMUIOVector local_qiov;
     int ret;
 
+    if (s->has_size && (offset > s->size || bytes > (s->size - offset))) {
+        /* There's not enough space for the data. Don't write anything and just
+         * fail to prevent leaking out of the size specified in options. */
+        return -ENOSPC;
+    }
+
+    if (offset > UINT64_MAX - s->offset) {
+        ret = -EINVAL;
+        goto fail;
+    }
+
     if (bs->probed && offset < BLOCK_PROBE_BUF_SIZE && bytes) {
         /* Handling partial writes would be a pain - so we just
          * require that guests have 512-byte request alignment if
@@ -246,10 +237,7 @@ static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, uint64_t offset,
         qiov = &local_qiov;
     }
 
-    ret = raw_adjust_offset(bs, &offset, bytes, true);
-    if (ret) {
-        goto fail;
-    }
+    offset += s->offset;
 
     BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
     ret = bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
@@ -279,25 +267,23 @@ static int coroutine_fn raw_co_pwrite_zeroes(BlockDriverState *bs,
                                              int64_t offset, int bytes,
                                              BdrvRequestFlags flags)
 {
-    int ret;
-
-    ret = raw_adjust_offset(bs, (uint64_t *)&offset, bytes, true);
-    if (ret) {
-        return ret;
+    BDRVRawState *s = bs->opaque;
+    if (offset > UINT64_MAX - s->offset) {
+        return -EINVAL;
     }
+    offset += s->offset;
     return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
 }
 
 static int coroutine_fn raw_co_pdiscard(BlockDriverState *bs,
                                         int64_t offset, int bytes)
 {
-    int ret;
-
-    ret = raw_adjust_offset(bs, (uint64_t *)&offset, bytes, true);
-    if (ret) {
-        return ret;
+    BDRVRawState *s = bs->opaque;
+    if (offset > UINT64_MAX - s->offset) {
+        return -EINVAL;
     }
-    return bdrv_co_pdiscard(bs->file, offset, bytes);
+    offset += s->offset;
+    return bdrv_co_pdiscard(bs->file->bs, offset, bytes);
 }
 
 static int64_t raw_getlength(BlockDriverState *bs)
@@ -366,7 +352,7 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
     }
 }
 
-static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset,
+static int raw_truncate(BlockDriverState *bs, int64_t offset,
                         PreallocMode prealloc, Error **errp)
 {
     BDRVRawState *s = bs->opaque;
@@ -383,7 +369,7 @@ static int coroutine_fn raw_co_truncate(BlockDriverState *bs, int64_t offset,
 
     s->size = offset;
     offset += s->offset;
-    return bdrv_co_truncate(bs->file, offset, prealloc, errp);
+    return bdrv_truncate(bs->file, offset, prealloc, errp);
 }
 
 static void raw_eject(BlockDriverState *bs, bool eject_flag)
@@ -429,11 +415,10 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     bs->sg = bs->file->bs->sg;
-    bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED |
-        (BDRV_REQ_FUA & bs->file->bs->supported_write_flags);
-    bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED |
-        ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP) &
-            bs->file->bs->supported_zero_flags);
+    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;
 
     if (bs->probed && !bdrv_is_read_only(bs)) {
         fprintf(stderr,
@@ -497,44 +482,6 @@ static int raw_probe_geometry(BlockDriverState *bs, HDGeometry *geo)
     return bdrv_probe_geometry(bs->file->bs, geo);
 }
 
-static int coroutine_fn raw_co_copy_range_from(BlockDriverState *bs,
-                                               BdrvChild *src,
-                                               uint64_t src_offset,
-                                               BdrvChild *dst,
-                                               uint64_t dst_offset,
-                                               uint64_t bytes,
-                                               BdrvRequestFlags read_flags,
-                                               BdrvRequestFlags write_flags)
-{
-    int ret;
-
-    ret = raw_adjust_offset(bs, &src_offset, bytes, false);
-    if (ret) {
-        return ret;
-    }
-    return bdrv_co_copy_range_from(bs->file, src_offset, dst, dst_offset,
-                                   bytes, read_flags, write_flags);
-}
-
-static int coroutine_fn raw_co_copy_range_to(BlockDriverState *bs,
-                                             BdrvChild *src,
-                                             uint64_t src_offset,
-                                             BdrvChild *dst,
-                                             uint64_t dst_offset,
-                                             uint64_t bytes,
-                                             BdrvRequestFlags read_flags,
-                                             BdrvRequestFlags write_flags)
-{
-    int ret;
-
-    ret = raw_adjust_offset(bs, &dst_offset, bytes, true);
-    if (ret) {
-        return ret;
-    }
-    return bdrv_co_copy_range_to(src, src_offset, bs->file, dst_offset, bytes,
-                                 read_flags, write_flags);
-}
-
 BlockDriver bdrv_raw = {
     .format_name          = "raw",
     .instance_size        = sizeof(BDRVRawState),
@@ -551,9 +498,7 @@ BlockDriver bdrv_raw = {
     .bdrv_co_pwrite_zeroes = &raw_co_pwrite_zeroes,
     .bdrv_co_pdiscard     = &raw_co_pdiscard,
     .bdrv_co_block_status = &raw_co_block_status,
-    .bdrv_co_copy_range_from = &raw_co_copy_range_from,
-    .bdrv_co_copy_range_to  = &raw_co_copy_range_to,
-    .bdrv_co_truncate     = &raw_co_truncate,
+    .bdrv_truncate        = &raw_truncate,
     .bdrv_getlength       = &raw_getlength,
     .has_variable_length  = true,
     .bdrv_measure         = &raw_measure,

block/rbd.c

@@ -18,7 +18,6 @@
 #include "qemu/error-report.h"
 #include "qemu/option.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "crypto/secret.h"
 #include "qemu/cutils.h"
 #include "qapi/qmp/qstring.h"
@@ -227,57 +226,27 @@ static void qemu_rbd_parse_filename(const char *filename, QDict *options,
 
 done:
     g_free(buf);
-    qobject_unref(keypairs);
+    QDECREF(keypairs);
     return;
 }
 
 
-static void qemu_rbd_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    /* XXX Does RBD support AIO on less than 512-byte alignment? */
-    bs->bl.request_alignment = 512;
-}
-
-
-static int qemu_rbd_set_auth(rados_t cluster, BlockdevOptionsRbd *opts,
+static int qemu_rbd_set_auth(rados_t cluster, const char *secretid,
                              Error **errp)
 {
-    char *key, *acr;
-    int r;
-    GString *accu;
-    RbdAuthModeList *auth;
-
-    if (opts->key_secret) {
-        key = qcrypto_secret_lookup_as_base64(opts->key_secret, errp);
-        if (!key) {
-            return -EIO;
-        }
-        r = rados_conf_set(cluster, "key", key);
-        g_free(key);
-        if (r < 0) {
-            error_setg_errno(errp, -r, "Could not set 'key'");
-            return r;
-        }
+    if (secretid == 0) {
+        return 0;
     }
 
-    if (opts->has_auth_client_required) {
-        accu = g_string_new("");
-        for (auth = opts->auth_client_required; auth; auth = auth->next) {
-            if (accu->str[0]) {
-                g_string_append_c(accu, ';');
-            }
-            g_string_append(accu, RbdAuthMode_str(auth->value));
-        }
-        acr = g_string_free(accu, FALSE);
-        r = rados_conf_set(cluster, "auth_client_required", acr);
-        g_free(acr);
-        if (r < 0) {
-            error_setg_errno(errp, -r,
-                             "Could not set 'auth_client_required'");
-            return r;
-        }
+    gchar *secret = qcrypto_secret_lookup_as_base64(secretid,
+                                                    errp);
+    if (!secret) {
+        return -1;
     }
 
+    rados_conf_set(cluster, "key", secret);
+    g_free(secret);
+
     return 0;
 }
 
@@ -294,29 +263,29 @@ static int qemu_rbd_set_keypairs(rados_t cluster, const char *keypairs_json,
     if (!keypairs_json) {
         return ret;
     }
-    keypairs = qobject_to(QList,
-                          qobject_from_json(keypairs_json, &error_abort));
+    keypairs = qobject_to_qlist(qobject_from_json(keypairs_json,
+                                                  &error_abort));
     remaining = qlist_size(keypairs) / 2;
     assert(remaining);
 
     while (remaining--) {
-        name = qobject_to(QString, qlist_pop(keypairs));
-        value = qobject_to(QString, qlist_pop(keypairs));
+        name = qobject_to_qstring(qlist_pop(keypairs));
+        value = qobject_to_qstring(qlist_pop(keypairs));
         assert(name && value);
         key = qstring_get_str(name);
 
         ret = rados_conf_set(cluster, key, qstring_get_str(value));
-        qobject_unref(value);
+        QDECREF(value);
         if (ret < 0) {
             error_setg_errno(errp, -ret, "invalid conf option %s", key);
-            qobject_unref(name);
+            QDECREF(name);
             ret = -EINVAL;
             break;
         }
-        qobject_unref(name);
+        QDECREF(name);
     }
 
-    qobject_unref(keypairs);
+    QDECREF(keypairs);
     return ret;
 }
 
@@ -368,7 +337,9 @@ static QemuOptsList runtime_opts = {
     },
 };
 
-/* FIXME Deprecate and remove keypairs or make it available in QMP. */
+/* FIXME Deprecate and remove keypairs or make it available in QMP.
+ * password_secret should eventually be configurable in opts->location. Support
+ * for it in .bdrv_open will make it work here as well. */
 static int qemu_rbd_do_create(BlockdevCreateOptions *options,
                               const char *keypairs, const char *password_secret,
                               Error **errp)
@@ -478,7 +449,7 @@ static int coroutine_fn qemu_rbd_co_create_opts(const char *filename,
     }
 
 exit:
-    qobject_unref(options);
+    QDECREF(options);
     qapi_free_BlockdevCreateOptions(create_options);
     return ret;
 }
@@ -574,16 +545,6 @@ static int qemu_rbd_connect(rados_t *cluster, rados_ioctx_t *io_ctx,
     Error *local_err = NULL;
     int r;
 
-    if (secretid) {
-        if (opts->key_secret) {
-            error_setg(errp,
-                       "Legacy 'password-secret' clashes with 'key-secret'");
-            return -EINVAL;
-        }
-        opts->key_secret = g_strdup(secretid);
-        opts->has_key_secret = true;
-    }
-
     mon_host = qemu_rbd_mon_host(opts, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
@@ -616,8 +577,8 @@ static int qemu_rbd_connect(rados_t *cluster, rados_ioctx_t *io_ctx,
         }
     }
 
-    r = qemu_rbd_set_auth(*cluster, opts, errp);
-    if (r < 0) {
+    if (qemu_rbd_set_auth(*cluster, secretid, errp) < 0) {
+        r = -EIO;
         goto failed_shutdown;
     }
 
@@ -661,11 +622,27 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
     BDRVRBDState *s = bs->opaque;
     BlockdevOptionsRbd *opts = NULL;
     Visitor *v;
-    const QDictEntry *e;
+    QObject *crumpled = NULL;
     Error *local_err = NULL;
+    const char *filename;
     char *keypairs, *secretid;
     int r;
 
+    /* If we are given a filename, parse the filename, with precedence given to
+     * filename encoded options */
+    filename = qdict_get_try_str(options, "filename");
+    if (filename) {
+        warn_report("'filename' option specified. "
+                    "This is an unsupported option, and may be deprecated "
+                    "in the future");
+        qemu_rbd_parse_filename(filename, options, &local_err);
+        qdict_del(options, "filename");
+        if (local_err) {
+            error_propagate(errp, local_err);
+            return -EINVAL;
+        }
+    }
+
     keypairs = g_strdup(qdict_get_try_str(options, "=keyvalue-pairs"));
     if (keypairs) {
         qdict_del(options, "=keyvalue-pairs");
@@ -677,14 +654,16 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     /* Convert the remaining options into a QAPI object */
-    v = qobject_input_visitor_new_flat_confused(options, errp);
-    if (!v) {
+    crumpled = qdict_crumple(options, errp);
+    if (crumpled == NULL) {
         r = -EINVAL;
         goto out;
     }
 
+    v = qobject_input_visitor_new_keyval(crumpled);
     visit_type_BlockdevOptionsRbd(v, NULL, &opts, &local_err);
     visit_free(v);
+    qobject_decref(crumpled);
 
     if (local_err) {
         error_propagate(errp, local_err);
@@ -692,12 +671,6 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
         goto out;
     }
 
-    /* Remove the processed options from the QDict (the visitor processes
-     * _all_ options in the QDict) */
-    while ((e = qdict_first(options))) {
-        qdict_del(options, e->key);
-    }
-
     r = qemu_rbd_connect(&s->cluster, &s->io_ctx, opts,
                          !(flags & BDRV_O_NOCACHE), keypairs, secretid, errp);
     if (r < 0) {
@@ -919,23 +892,27 @@ failed:
     return NULL;
 }
 
-static BlockAIOCB *qemu_rbd_aio_preadv(BlockDriverState *bs,
-                                       uint64_t offset, uint64_t bytes,
-                                       QEMUIOVector *qiov, int flags,
+static BlockAIOCB *qemu_rbd_aio_readv(BlockDriverState *bs,
+                                      int64_t sector_num,
+                                      QEMUIOVector *qiov,
+                                      int nb_sectors,
                                       BlockCompletionFunc *cb,
                                       void *opaque)
 {
-    return rbd_start_aio(bs, offset, qiov, bytes, cb, opaque,
+    return rbd_start_aio(bs, sector_num << BDRV_SECTOR_BITS, qiov,
+                         (int64_t) nb_sectors << BDRV_SECTOR_BITS, cb, opaque,
                          RBD_AIO_READ);
 }
 
-static BlockAIOCB *qemu_rbd_aio_pwritev(BlockDriverState *bs,
-                                        uint64_t offset, uint64_t bytes,
-                                        QEMUIOVector *qiov, int flags,
+static BlockAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs,
+                                       int64_t sector_num,
+                                       QEMUIOVector *qiov,
+                                       int nb_sectors,
                                        BlockCompletionFunc *cb,
                                        void *opaque)
 {
-    return rbd_start_aio(bs, offset, qiov, bytes, cb, opaque,
+    return rbd_start_aio(bs, sector_num << BDRV_SECTOR_BITS, qiov,
+                         (int64_t) nb_sectors << BDRV_SECTOR_BITS, cb, opaque,
                          RBD_AIO_WRITE);
 }
 
@@ -990,10 +967,8 @@ static int64_t qemu_rbd_getlength(BlockDriverState *bs)
     return info.size;
 }
 
-static int coroutine_fn qemu_rbd_co_truncate(BlockDriverState *bs,
-                                             int64_t offset,
-                                             PreallocMode prealloc,
-                                             Error **errp)
+static int qemu_rbd_truncate(BlockDriverState *bs, int64_t offset,
+                             PreallocMode prealloc, Error **errp)
 {
     BDRVRBDState *s = bs->opaque;
     int r;
@@ -1176,7 +1151,6 @@ static BlockDriver bdrv_rbd = {
     .format_name            = "rbd",
     .instance_size          = sizeof(BDRVRBDState),
     .bdrv_parse_filename    = qemu_rbd_parse_filename,
-    .bdrv_refresh_limits    = qemu_rbd_refresh_limits,
     .bdrv_file_open         = qemu_rbd_open,
     .bdrv_close             = qemu_rbd_close,
     .bdrv_reopen_prepare    = qemu_rbd_reopen_prepare,
@@ -1186,11 +1160,11 @@ static BlockDriver bdrv_rbd = {
     .bdrv_get_info          = qemu_rbd_getinfo,
     .create_opts            = &qemu_rbd_create_opts,
     .bdrv_getlength         = qemu_rbd_getlength,
-    .bdrv_co_truncate       = qemu_rbd_co_truncate,
+    .bdrv_truncate          = qemu_rbd_truncate,
     .protocol_name          = "rbd",
 
-    .bdrv_aio_preadv        = qemu_rbd_aio_preadv,
-    .bdrv_aio_pwritev       = qemu_rbd_aio_pwritev,
+    .bdrv_aio_readv         = qemu_rbd_aio_readv,
+    .bdrv_aio_writev        = qemu_rbd_aio_writev,
 
 #ifdef LIBRBD_SUPPORTS_AIO_FLUSH
     .bdrv_aio_flush         = qemu_rbd_aio_flush,

block/replication.c

@@ -145,7 +145,7 @@ static void replication_close(BlockDriverState *bs)
         replication_stop(s->rs, false, NULL);
     }
     if (s->stage == BLOCK_REPLICATION_FAILOVER) {
-        job_cancel_sync(&s->active_disk->bs->job->job);
+        block_job_cancel_sync(s->active_disk->bs->job);
     }
 
     if (s->mode == REPLICATION_MODE_SECONDARY) {
@@ -246,14 +246,13 @@ static coroutine_fn int replication_co_readv(BlockDriverState *bs,
         backup_cow_request_begin(&req, child->bs->job,
                                  sector_num * BDRV_SECTOR_SIZE,
                                  remaining_bytes);
-        ret = bdrv_co_preadv(bs->file, sector_num * BDRV_SECTOR_SIZE,
-                             remaining_bytes, qiov, 0);
+        ret = bdrv_co_readv(bs->file, sector_num, remaining_sectors,
+                            qiov);
         backup_cow_request_end(&req);
         goto out;
     }
 
-    ret = bdrv_co_preadv(bs->file, sector_num * BDRV_SECTOR_SIZE,
-                         remaining_sectors * BDRV_SECTOR_SIZE, qiov, 0);
+    ret = bdrv_co_readv(bs->file, sector_num, remaining_sectors, qiov);
 out:
     return replication_return_value(s, ret);
 }
@@ -261,8 +260,7 @@ out:
 static coroutine_fn int replication_co_writev(BlockDriverState *bs,
                                               int64_t sector_num,
                                               int remaining_sectors,
-                                              QEMUIOVector *qiov,
-                                              int flags)
+                                              QEMUIOVector *qiov)
 {
     BDRVReplicationState *s = bs->opaque;
     QEMUIOVector hd_qiov;
@@ -273,15 +271,14 @@ static coroutine_fn int replication_co_writev(BlockDriverState *bs,
     int ret;
     int64_t n;
 
-    assert(!flags);
     ret = replication_get_io_status(s);
     if (ret < 0) {
         goto out;
     }
 
     if (ret == 0) {
-        ret = bdrv_co_pwritev(top, sector_num * BDRV_SECTOR_SIZE,
-                              remaining_sectors * BDRV_SECTOR_SIZE, qiov, 0);
+        ret = bdrv_co_writev(top, sector_num,
+                             remaining_sectors, qiov);
         return replication_return_value(s, ret);
     }
 
@@ -307,8 +304,7 @@ static coroutine_fn int replication_co_writev(BlockDriverState *bs,
         qemu_iovec_concat(&hd_qiov, qiov, bytes_done, count);
 
         target = ret ? top : base;
-        ret = bdrv_co_pwritev(target, sector_num * BDRV_SECTOR_SIZE,
-                              n * BDRV_SECTOR_SIZE, &hd_qiov, 0);
+        ret = bdrv_co_writev(target, sector_num, n, &hd_qiov);
         if (ret < 0) {
             goto out1;
         }
@@ -570,7 +566,7 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode,
         job = backup_job_create(NULL, s->secondary_disk->bs, s->hidden_disk->bs,
                                 0, MIRROR_SYNC_MODE_NONE, NULL, false,
                                 BLOCKDEV_ON_ERROR_REPORT,
-                                BLOCKDEV_ON_ERROR_REPORT, JOB_INTERNAL,
+                                BLOCKDEV_ON_ERROR_REPORT, BLOCK_JOB_INTERNAL,
                                 backup_job_completed, bs, NULL, &local_err);
         if (local_err) {
             error_propagate(errp, local_err);
@@ -578,7 +574,7 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode,
             aio_context_release(aio_context);
             return;
         }
-        job_start(&job->job);
+        block_job_start(job);
         break;
     default:
         aio_context_release(aio_context);
@@ -683,7 +679,7 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp)
          * disk, secondary disk in backup_job_completed().
          */
         if (s->secondary_disk->bs->job) {
-            job_cancel_sync(&s->secondary_disk->bs->job->job);
+            block_job_cancel_sync(s->secondary_disk->bs->job);
         }
 
         if (!failover) {
@@ -695,7 +691,7 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp)
 
         s->stage = BLOCK_REPLICATION_FAILOVER;
         commit_active_start(NULL, s->active_disk->bs, s->secondary_disk->bs,
-                            JOB_INTERNAL, 0, BLOCKDEV_ON_ERROR_REPORT,
+                            BLOCK_JOB_INTERNAL, 0, BLOCKDEV_ON_ERROR_REPORT,
                             NULL, replication_done, bs, true, errp);
         break;
     default:

block/sheepdog.c

@@ -24,7 +24,6 @@
 #include "qemu/option.h"
 #include "qemu/sockets.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "sysemu/block-backend.h"
 #include "qemu/bitops.h"
 #include "qemu/cutils.h"
@@ -539,17 +538,27 @@ static void sd_aio_setup(SheepdogAIOCB *acb, BDRVSheepdogState *s,
 static SocketAddress *sd_server_config(QDict *options, Error **errp)
 {
     QDict *server = NULL;
+    QObject *crumpled_server = NULL;
     Visitor *iv = NULL;
     SocketAddress *saddr = NULL;
     Error *local_err = NULL;
 
     qdict_extract_subqdict(options, &server, "server.");
 
-    iv = qobject_input_visitor_new_flat_confused(server, errp);
-    if (!iv) {
+    crumpled_server = qdict_crumple(server, errp);
+    if (!crumpled_server) {
         goto done;
     }
 
+    /*
+     * 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_server);
     visit_type_SocketAddress(iv, NULL, &saddr, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
@@ -558,7 +567,8 @@ static SocketAddress *sd_server_config(QDict *options, Error **errp)
 
 done:
     visit_free(iv);
-    qobject_unref(server);
+    qobject_decref(crumpled_server);
+    QDECREF(server);
     return saddr;
 }
 
@@ -1026,7 +1036,7 @@ static void sd_parse_uri(SheepdogConfig *cfg, const char *filename,
 
     cfg->uri = uri = uri_parse(filename);
     if (!uri) {
-        error_setg(&err, "invalid URI '%s'", filename);
+        error_setg(&err, "invalid URI");
         goto out;
     }
 
@@ -1849,7 +1859,9 @@ out:
         error_setg_errno(errp, -ret, "Can't pre-allocate");
     }
 out_with_err_set:
+    if (blk) {
         blk_unref(blk);
+    }
     g_free(buf);
 
     return ret;
@@ -1871,11 +1883,11 @@ static int sd_create_prealloc(BlockdevOptionsSheepdog *location, int64_t size,
 
     if (local_err) {
         error_propagate(errp, local_err);
-        qobject_unref(obj);
+        qobject_decref(obj);
         return -EINVAL;
     }
 
-    qdict = qobject_to(QDict, obj);
+    qdict = qobject_to_qdict(obj);
     qdict_flatten(qdict);
 
     qdict_put_str(qdict, "driver", "sheepdog");
@@ -1889,7 +1901,7 @@ static int sd_create_prealloc(BlockdevOptionsSheepdog *location, int64_t size,
     ret = sd_prealloc(bs, 0, size, errp);
 fail:
     bdrv_unref(bs);
-    qobject_unref(qdict);
+    QDECREF(qdict);
     return ret;
 }
 
@@ -1975,7 +1987,6 @@ static SheepdogRedundancy *parse_redundancy_str(const char *opt)
     } else {
         ret = qemu_strtol(n2, NULL, 10, &parity);
         if (ret < 0) {
-            g_free(redundancy);
             return NULL;
         }
 
@@ -2170,8 +2181,9 @@ static int coroutine_fn sd_co_create_opts(const char *filename, QemuOpts *opts,
 {
     BlockdevCreateOptions *create_options = NULL;
     QDict *qdict, *location_qdict;
+    QObject *crumpled;
     Visitor *v;
-    char *redundancy;
+    const char *redundancy;
     Error *local_err = NULL;
     int ret;
 
@@ -2205,14 +2217,16 @@ static int coroutine_fn sd_co_create_opts(const char *filename, QemuOpts *opts,
     }
 
     /* Get the QAPI object */
-    v = qobject_input_visitor_new_flat_confused(qdict, errp);
-    if (!v) {
+    crumpled = qdict_crumple(qdict, errp);
+    if (crumpled == NULL) {
         ret = -EINVAL;
         goto fail;
     }
 
+    v = qobject_input_visitor_new_keyval(crumpled);
     visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err);
     visit_free(v);
+    qobject_decref(crumpled);
 
     if (local_err) {
         error_propagate(errp, local_err);
@@ -2238,8 +2252,7 @@ static int coroutine_fn sd_co_create_opts(const char *filename, QemuOpts *opts,
     ret = sd_co_create(create_options, errp);
 fail:
     qapi_free_BlockdevCreateOptions(create_options);
-    qobject_unref(qdict);
-    g_free(redundancy);
+    QDECREF(qdict);
     return ret;
 }
 
@@ -2292,7 +2305,7 @@ static int64_t sd_getlength(BlockDriverState *bs)
     return s->inode.vdi_size;
 }
 
-static int coroutine_fn sd_co_truncate(BlockDriverState *bs, int64_t offset,
+static int sd_truncate(BlockDriverState *bs, int64_t offset,
                        PreallocMode prealloc, Error **errp)
 {
     BDRVSheepdogState *s = bs->opaque;
@@ -2322,7 +2335,7 @@ static int coroutine_fn sd_co_truncate(BlockDriverState *bs, int64_t offset,
     }
 
     /* we don't need to update entire object */
-    datalen = SD_INODE_HEADER_SIZE;
+    datalen = SD_INODE_SIZE - sizeof(s->inode.data_vdi_id);
     s->inode.vdi_size = offset;
     ret = write_object(fd, s->bs, (char *)&s->inode,
                        vid_to_vdi_oid(s->inode.vdi_id), s->inode.nr_copies,
@@ -2599,17 +2612,15 @@ static void sd_aio_complete(SheepdogAIOCB *acb)
 }
 
 static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
-                                     int nb_sectors, QEMUIOVector *qiov,
-                                     int flags)
+                        int nb_sectors, QEMUIOVector *qiov)
 {
     SheepdogAIOCB acb;
     int ret;
     int64_t offset = (sector_num + nb_sectors) * BDRV_SECTOR_SIZE;
     BDRVSheepdogState *s = bs->opaque;
 
-    assert(!flags);
     if (offset > s->inode.vdi_size) {
-        ret = sd_co_truncate(bs, offset, PREALLOC_MODE_OFF, NULL);
+        ret = sd_truncate(bs, offset, PREALLOC_MODE_OFF, NULL);
         if (ret < 0) {
             return ret;
         }
@@ -2690,7 +2701,7 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
      */
     strncpy(s->inode.tag, sn_info->name, sizeof(s->inode.tag));
     /* we don't need to update entire object */
-    datalen = SD_INODE_HEADER_SIZE;
+    datalen = SD_INODE_SIZE - sizeof(s->inode.data_vdi_id);
     inode = g_malloc(datalen);
 
     /* refresh inode. */
@@ -2925,14 +2936,13 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
     QEMUSnapshotInfo *sn_tab = NULL;
     unsigned wlen, rlen;
     int found = 0;
-    SheepdogInode *inode;
+    static SheepdogInode inode;
     unsigned long *vdi_inuse;
     unsigned int start_nr;
     uint64_t hval;
     uint32_t vid;
 
     vdi_inuse = g_malloc(max);
-    inode = g_malloc(SD_INODE_HEADER_SIZE);
 
     fd = connect_to_sdog(s, &local_err);
     if (fd < 0) {
@@ -2975,26 +2985,26 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
         }
 
         /* we don't need to read entire object */
-        ret = read_object(fd, s->bs, (char *)inode,
+        ret = read_object(fd, s->bs, (char *)&inode,
                           vid_to_vdi_oid(vid),
-                          0, SD_INODE_HEADER_SIZE, 0,
+                          0, SD_INODE_SIZE - sizeof(inode.data_vdi_id), 0,
                           s->cache_flags);
 
         if (ret) {
             continue;
         }
 
-        if (!strcmp(inode->name, s->name) && is_snapshot(inode)) {
-            sn_tab[found].date_sec = inode->snap_ctime >> 32;
-            sn_tab[found].date_nsec = inode->snap_ctime & 0xffffffff;
-            sn_tab[found].vm_state_size = inode->vm_state_size;
-            sn_tab[found].vm_clock_nsec = inode->vm_clock_nsec;
+        if (!strcmp(inode.name, s->name) && is_snapshot(&inode)) {
+            sn_tab[found].date_sec = inode.snap_ctime >> 32;
+            sn_tab[found].date_nsec = inode.snap_ctime & 0xffffffff;
+            sn_tab[found].vm_state_size = inode.vm_state_size;
+            sn_tab[found].vm_clock_nsec = inode.vm_clock_nsec;
 
             snprintf(sn_tab[found].id_str, sizeof(sn_tab[found].id_str),
-                     "%" PRIu32, inode->snap_id);
+                     "%" PRIu32, inode.snap_id);
             pstrcpy(sn_tab[found].name,
-                    MIN(sizeof(sn_tab[found].name), sizeof(inode->tag)),
-                    inode->tag);
+                    MIN(sizeof(sn_tab[found].name), sizeof(inode.tag)),
+                    inode.tag);
             found++;
         }
     }
@@ -3004,7 +3014,6 @@ out:
     *psn_tab = sn_tab;
 
     g_free(vdi_inuse);
-    g_free(inode);
 
     if (ret < 0) {
         return ret;
@@ -3231,7 +3240,7 @@ static BlockDriver bdrv_sheepdog = {
     .bdrv_has_zero_init           = bdrv_has_zero_init_1,
     .bdrv_getlength               = sd_getlength,
     .bdrv_get_allocated_file_size = sd_get_allocated_file_size,
-    .bdrv_co_truncate             = sd_co_truncate,
+    .bdrv_truncate                = sd_truncate,
 
     .bdrv_co_readv                = sd_co_readv,
     .bdrv_co_writev               = sd_co_writev,
@@ -3268,7 +3277,7 @@ static BlockDriver bdrv_sheepdog_tcp = {
     .bdrv_has_zero_init           = bdrv_has_zero_init_1,
     .bdrv_getlength               = sd_getlength,
     .bdrv_get_allocated_file_size = sd_get_allocated_file_size,
-    .bdrv_co_truncate             = sd_co_truncate,
+    .bdrv_truncate                = sd_truncate,
 
     .bdrv_co_readv                = sd_co_readv,
     .bdrv_co_writev               = sd_co_writev,
@@ -3305,7 +3314,7 @@ static BlockDriver bdrv_sheepdog_unix = {
     .bdrv_has_zero_init           = bdrv_has_zero_init_1,
     .bdrv_getlength               = sd_getlength,
     .bdrv_get_allocated_file_size = sd_get_allocated_file_size,
-    .bdrv_co_truncate             = sd_co_truncate,
+    .bdrv_truncate                = sd_truncate,
 
     .bdrv_co_readv                = sd_co_readv,
     .bdrv_co_writev               = sd_co_writev,

block/snapshot.c

@@ -25,7 +25,6 @@
 #include "qemu/osdep.h"
 #include "block/snapshot.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qerror.h"
@@ -215,7 +214,7 @@ int bdrv_snapshot_goto(BlockDriverState *bs,
         bdrv_ref(file);
 
         qdict_extract_subqdict(options, &file_options, "file.");
-        qobject_unref(file_options);
+        QDECREF(file_options);
         qdict_put_str(options, "file", bdrv_get_node_name(file));
 
         drv->bdrv_close(bs);
@@ -224,7 +223,7 @@ int bdrv_snapshot_goto(BlockDriverState *bs,
 
         ret = bdrv_snapshot_goto(file, snapshot_id, errp);
         open_ret = drv->bdrv_open(bs, options, bs->open_flags, &local_err);
-        qobject_unref(options);
+        QDECREF(options);
         if (open_ret < 0) {
             bdrv_unref(file);
             bs->drv = NULL;

block/ssh.c

@@ -28,7 +28,6 @@
 #include <libssh2_sftp.h>
 
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "qemu/option.h"
@@ -606,6 +605,7 @@ static BlockdevOptionsSsh *ssh_parse_options(QDict *options, Error **errp)
     BlockdevOptionsSsh *result = NULL;
     QemuOpts *opts = NULL;
     Error *local_err = NULL;
+    QObject *crumpled;
     const QDictEntry *e;
     Visitor *v;
 
@@ -622,13 +622,23 @@ static BlockdevOptionsSsh *ssh_parse_options(QDict *options, Error **errp)
     }
 
     /* Create the QAPI object */
-    v = qobject_input_visitor_new_flat_confused(options, errp);
-    if (!v) {
+    crumpled = qdict_crumple(options, errp);
+    if (crumpled == NULL) {
         goto fail;
     }
 
+    /*
+     * FIXME .numeric, .to, .ipv4 or .ipv6 don't work with -drive.
+     * .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.
+     */
+    v = qobject_input_visitor_new(crumpled);
     visit_type_BlockdevOptionsSsh(v, NULL, &result, &local_err);
     visit_free(v);
+    qobject_decref(crumpled);
 
     if (local_err) {
         error_propagate(errp, local_err);
@@ -907,7 +917,7 @@ static int coroutine_fn ssh_co_create_opts(const char *filename, QemuOpts *opts,
     ret = ssh_co_create(create_options, errp);
 
  out:
-    qobject_unref(uri_options);
+    QDECREF(uri_options);
     qapi_free_BlockdevCreateOptions(create_options);
     return ret;
 }
@@ -1154,13 +1164,11 @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
 
 static coroutine_fn int ssh_co_writev(BlockDriverState *bs,
                                       int64_t sector_num,
-                                      int nb_sectors, QEMUIOVector *qiov,
-                                      int flags)
+                                      int nb_sectors, QEMUIOVector *qiov)
 {
     BDRVSSHState *s = bs->opaque;
     int ret;
 
-    assert(!flags);
     qemu_co_mutex_lock(&s->lock);
     ret = ssh_write(s, bs, sector_num * BDRV_SECTOR_SIZE,
                     nb_sectors * BDRV_SECTOR_SIZE, qiov);
@@ -1243,7 +1251,7 @@ static int64_t ssh_getlength(BlockDriverState *bs)
     return length;
 }
 
-static int coroutine_fn ssh_co_truncate(BlockDriverState *bs, int64_t offset,
+static int ssh_truncate(BlockDriverState *bs, int64_t offset,
                         PreallocMode prealloc, Error **errp)
 {
     BDRVSSHState *s = bs->opaque;
@@ -1279,7 +1287,7 @@ static BlockDriver bdrv_ssh = {
     .bdrv_co_readv                = ssh_co_readv,
     .bdrv_co_writev               = ssh_co_writev,
     .bdrv_getlength               = ssh_getlength,
-    .bdrv_co_truncate             = ssh_co_truncate,
+    .bdrv_truncate                = ssh_truncate,
     .bdrv_co_flush_to_disk        = ssh_co_flush,
     .create_opts                  = &ssh_create_opts,
 };

block/stream.c

@@ -29,8 +29,11 @@ enum {
     STREAM_BUFFER_SIZE = 512 * 1024, /* in bytes */
 };
 
+#define SLICE_TIME 100000000ULL /* ns */
+
 typedef struct StreamBlockJob {
     BlockJob common;
+    RateLimit limit;
     BlockDriverState *base;
     BlockdevOnError on_error;
     char *backing_file_str;
@@ -58,16 +61,16 @@ typedef struct {
     int ret;
 } StreamCompleteData;
 
-static void stream_complete(Job *job, void *opaque)
+static void stream_complete(BlockJob *job, void *opaque)
 {
-    StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
-    BlockJob *bjob = &s->common;
+    StreamBlockJob *s = container_of(job, StreamBlockJob, common);
     StreamCompleteData *data = opaque;
-    BlockDriverState *bs = blk_bs(bjob->blk);
+    BlockDriverState *bs = blk_bs(job->blk);
     BlockDriverState *base = s->base;
     Error *local_err = NULL;
 
-    if (!job_is_cancelled(job) && bs->backing && data->ret == 0) {
+    if (!block_job_is_cancelled(&s->common) && bs->backing &&
+        data->ret == 0) {
         const char *base_id = NULL, *base_fmt = NULL;
         if (base) {
             base_id = s->backing_file_str;
@@ -88,12 +91,12 @@ out:
     /* Reopen the image back in read-only mode if necessary */
     if (s->bs_flags != bdrv_get_flags(bs)) {
         /* Give up write permissions before making it read-only */
-        blk_set_perm(bjob->blk, 0, BLK_PERM_ALL, &error_abort);
+        blk_set_perm(job->blk, 0, BLK_PERM_ALL, &error_abort);
         bdrv_reopen(bs, s->bs_flags, NULL);
     }
 
     g_free(s->backing_file_str);
-    job_completed(job, data->ret, NULL);
+    block_job_completed(&s->common, data->ret);
     g_free(data);
 }
 
@@ -104,7 +107,6 @@ static void coroutine_fn stream_run(void *opaque)
     BlockBackend *blk = s->common.blk;
     BlockDriverState *bs = blk_bs(blk);
     BlockDriverState *base = s->base;
-    int64_t len;
     int64_t offset = 0;
     uint64_t delay_ns = 0;
     int error = 0;
@@ -116,12 +118,11 @@ static void coroutine_fn stream_run(void *opaque)
         goto out;
     }
 
-    len = bdrv_getlength(bs);
-    if (len < 0) {
-        ret = len;
+    s->common.len = bdrv_getlength(bs);
+    if (s->common.len < 0) {
+        ret = s->common.len;
         goto out;
     }
-    job_progress_set_remaining(&s->common.job, len);
 
     buf = qemu_blockalign(bs, STREAM_BUFFER_SIZE);
 
@@ -134,14 +135,14 @@ static void coroutine_fn stream_run(void *opaque)
         bdrv_enable_copy_on_read(bs);
     }
 
-    for ( ; offset < len; offset += n) {
+    for ( ; offset < s->common.len; offset += n) {
         bool copy;
 
         /* 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.
          */
-        job_sleep_ns(&s->common.job, delay_ns);
-        if (job_is_cancelled(&s->common.job)) {
+        block_job_sleep_ns(&s->common, delay_ns);
+        if (block_job_is_cancelled(&s->common)) {
             break;
         }
 
@@ -158,7 +159,7 @@ static void coroutine_fn stream_run(void *opaque)
 
             /* Finish early if end of backing file has been reached */
             if (ret == 0 && n == 0) {
-                n = len - offset;
+                n = s->common.len - offset;
             }
 
             copy = (ret == 1);
@@ -184,11 +185,9 @@ static void coroutine_fn stream_run(void *opaque)
         ret = 0;
 
         /* Publish progress */
-        job_progress_update(&s->common.job, n);
-        if (copy) {
-            delay_ns = block_job_ratelimit_get_delay(&s->common, n);
-        } else {
-            delay_ns = 0;
+        s->common.offset += n;
+        if (copy && s->common.speed) {
+            delay_ns = ratelimit_calculate_delay(&s->limit, n);
         }
     }
 
@@ -205,18 +204,25 @@ out:
     /* Modify backing chain and close BDSes in main loop */
     data = g_malloc(sizeof(*data));
     data->ret = ret;
-    job_defer_to_main_loop(&s->common.job, stream_complete, data);
+    block_job_defer_to_main_loop(&s->common, stream_complete, data);
+}
+
+static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
+{
+    StreamBlockJob *s = container_of(job, StreamBlockJob, common);
+
+    if (speed < 0) {
+        error_setg(errp, QERR_INVALID_PARAMETER, "speed");
+        return;
+    }
+    ratelimit_set_speed(&s->limit, speed, SLICE_TIME);
 }
 
 static const BlockJobDriver stream_job_driver = {
-    .job_driver = {
     .instance_size = sizeof(StreamBlockJob),
-        .job_type      = JOB_TYPE_STREAM,
-        .free          = block_job_free,
+    .job_type      = BLOCK_JOB_TYPE_STREAM,
+    .set_speed     = stream_set_speed,
     .start         = stream_run,
-        .user_resume   = block_job_user_resume,
-        .drain         = block_job_drain,
-    },
 };
 
 void stream_start(const char *job_id, BlockDriverState *bs,
@@ -238,12 +244,12 @@ void stream_start(const char *job_id, BlockDriverState *bs,
     /* Prevent concurrent jobs trying to modify the graph structure here, we
      * already have our own plans. Also don't allow resize as the image size is
      * queried only at the job start and then cached. */
-    s = block_job_create(job_id, &stream_job_driver, NULL, bs,
+    s = block_job_create(job_id, &stream_job_driver, bs,
                          BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
                          BLK_PERM_GRAPH_MOD,
                          BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
                          BLK_PERM_WRITE,
-                         speed, JOB_DEFAULT, NULL, NULL, errp);
+                         speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp);
     if (!s) {
         goto fail;
     }
@@ -264,7 +270,7 @@ void stream_start(const char *job_id, BlockDriverState *bs,
 
     s->on_error = on_error;
     trace_stream_start(bs, base, s);
-    job_start(&s->common.job);
+    block_job_start(&s->common);
     return;
 
 fail:

block/throttle.c

@@ -36,12 +36,9 @@ static QemuOptsList throttle_opts = {
     },
 };
 
-/*
- * If this function succeeds then the throttle group name is stored in
- * @group and must be freed by the caller.
- * If there's an error then @group remains unmodified.
- */
-static int throttle_parse_options(QDict *options, char **group, Error **errp)
+static int throttle_configure_tgm(BlockDriverState *bs,
+                                  ThrottleGroupMember *tgm,
+                                  QDict *options, Error **errp)
 {
     int ret;
     const char *group_name;
@@ -66,7 +63,8 @@ static int throttle_parse_options(QDict *options, char **group, Error **errp)
         goto fin;
     }
 
-    *group = g_strdup(group_name);
+    /* Register membership to group with name group_name */
+    throttle_group_register_tgm(tgm, group_name, bdrv_get_aio_context(bs));
     ret = 0;
 fin:
     qemu_opts_del(opts);
@@ -77,27 +75,16 @@ static int throttle_open(BlockDriverState *bs, QDict *options,
                          int flags, Error **errp)
 {
     ThrottleGroupMember *tgm = bs->opaque;
-    char *group;
-    int ret;
 
     bs->file = bdrv_open_child(NULL, options, "file", bs,
                                &child_file, false, errp);
     if (!bs->file) {
         return -EINVAL;
     }
-    bs->supported_write_flags = bs->file->bs->supported_write_flags |
-                                BDRV_REQ_WRITE_UNCHANGED;
-    bs->supported_zero_flags = bs->file->bs->supported_zero_flags |
-                               BDRV_REQ_WRITE_UNCHANGED;
+    bs->supported_write_flags = bs->file->bs->supported_write_flags;
+    bs->supported_zero_flags = bs->file->bs->supported_zero_flags;
 
-    ret = throttle_parse_options(options, &group, errp);
-    if (ret == 0) {
-        /* Register membership to group with name group_name */
-        throttle_group_register_tgm(tgm, group, bdrv_get_aio_context(bs));
-        g_free(group);
-    }
-
-    return ret;
+    return throttle_configure_tgm(bs, tgm, options, errp);
 }
 
 static void throttle_close(BlockDriverState *bs)
@@ -149,7 +136,7 @@ static int coroutine_fn throttle_co_pdiscard(BlockDriverState *bs,
     ThrottleGroupMember *tgm = bs->opaque;
     throttle_group_co_io_limits_intercept(tgm, bytes, true);
 
-    return bdrv_co_pdiscard(bs->file, offset, bytes);
+    return bdrv_co_pdiscard(bs->file->bs, offset, bytes);
 }
 
 static int throttle_co_flush(BlockDriverState *bs)
@@ -173,36 +160,35 @@ static void throttle_attach_aio_context(BlockDriverState *bs,
 static int throttle_reopen_prepare(BDRVReopenState *reopen_state,
                                    BlockReopenQueue *queue, Error **errp)
 {
-    int ret;
-    char *group = NULL;
+    ThrottleGroupMember *tgm;
 
     assert(reopen_state != NULL);
     assert(reopen_state->bs != NULL);
 
-    ret = throttle_parse_options(reopen_state->options, &group, errp);
-    reopen_state->opaque = group;
-    return ret;
+    reopen_state->opaque = g_new0(ThrottleGroupMember, 1);
+    tgm = reopen_state->opaque;
+
+    return throttle_configure_tgm(reopen_state->bs, tgm, reopen_state->options,
+            errp);
 }
 
 static void throttle_reopen_commit(BDRVReopenState *reopen_state)
 {
-    BlockDriverState *bs = reopen_state->bs;
-    ThrottleGroupMember *tgm = bs->opaque;
-    char *group = reopen_state->opaque;
+    ThrottleGroupMember *old_tgm = reopen_state->bs->opaque;
+    ThrottleGroupMember *new_tgm = reopen_state->opaque;
 
-    assert(group);
-
-    if (strcmp(group, throttle_group_get_name(tgm))) {
-        throttle_group_unregister_tgm(tgm);
-        throttle_group_register_tgm(tgm, group, bdrv_get_aio_context(bs));
-    }
-    g_free(reopen_state->opaque);
+    throttle_group_unregister_tgm(old_tgm);
+    g_free(old_tgm);
+    reopen_state->bs->opaque = new_tgm;
     reopen_state->opaque = NULL;
 }
 
 static void throttle_reopen_abort(BDRVReopenState *reopen_state)
 {
-    g_free(reopen_state->opaque);
+    ThrottleGroupMember *tgm = reopen_state->opaque;
+
+    throttle_group_unregister_tgm(tgm);
+    g_free(tgm);
     reopen_state->opaque = NULL;
 }
 

block/trace-events

@@ -7,16 +7,12 @@ bdrv_lock_medium(void *bs, bool locked) "bs %p locked %d"
 # block/block-backend.c
 blk_co_preadv(void *blk, void *bs, int64_t offset, unsigned int bytes, int flags) "blk %p bs %p offset %"PRId64" bytes %u flags 0x%x"
 blk_co_pwritev(void *blk, void *bs, int64_t offset, unsigned int bytes, int flags) "blk %p bs %p offset %"PRId64" bytes %u flags 0x%x"
-blk_root_attach(void *child, void *blk, void *bs) "child %p blk %p bs %p"
-blk_root_detach(void *child, void *blk, void *bs) "child %p blk %p bs %p"
 
 # block/io.c
 bdrv_co_preadv(void *bs, int64_t offset, int64_t nbytes, unsigned int flags) "bs %p offset %"PRId64" nbytes %"PRId64" flags 0x%x"
 bdrv_co_pwritev(void *bs, int64_t offset, int64_t nbytes, unsigned int flags) "bs %p offset %"PRId64" nbytes %"PRId64" flags 0x%x"
 bdrv_co_pwrite_zeroes(void *bs, int64_t offset, int count, int flags) "bs %p offset %"PRId64" count %d flags 0x%x"
 bdrv_co_do_copy_on_readv(void *bs, int64_t offset, unsigned int bytes, int64_t cluster_offset, int64_t cluster_bytes) "bs %p offset %"PRId64" bytes %u cluster_offset %"PRId64" cluster_bytes %"PRId64
-bdrv_co_copy_range_from(void *src, uint64_t src_offset, void *dst, uint64_t dst_offset, uint64_t bytes, int read_flags, int write_flags) "src %p offset %"PRIu64" dst %p offset %"PRIu64" bytes %"PRIu64" rw flags 0x%x 0x%x"
-bdrv_co_copy_range_to(void *src, uint64_t src_offset, void *dst, uint64_t dst_offset, uint64_t bytes, int read_flags, int write_flags) "src %p offset %"PRIu64" dst %p offset %"PRIu64" bytes %"PRIu64" rw flags 0x%x 0x%x"
 
 # block/stream.c
 stream_one_iteration(void *s, int64_t offset, uint64_t bytes, int is_allocated) "s %p offset %" PRId64 " bytes %" PRIu64 " is_allocated %d"
@@ -44,22 +40,18 @@ backup_do_cow_skip(void *job, int64_t start) "job %p start %"PRId64
 backup_do_cow_process(void *job, int64_t start) "job %p start %"PRId64
 backup_do_cow_read_fail(void *job, int64_t start, int ret) "job %p start %"PRId64" ret %d"
 backup_do_cow_write_fail(void *job, int64_t start, int ret) "job %p start %"PRId64" ret %d"
-backup_do_cow_copy_range_fail(void *job, int64_t start, int ret) "job %p start %"PRId64" ret %d"
 
 # blockdev.c
 qmp_block_job_cancel(void *job) "job %p"
 qmp_block_job_pause(void *job) "job %p"
 qmp_block_job_resume(void *job) "job %p"
 qmp_block_job_complete(void *job) "job %p"
-qmp_block_job_finalize(void *job) "job %p"
-qmp_block_job_dismiss(void *job) "job %p"
 qmp_block_stream(void *bs, void *job) "bs %p job %p"
 
 # block/file-win32.c
 # block/file-posix.c
-file_paio_submit_co(int64_t offset, int count, int type) "offset %"PRId64" count %d type %d"
-file_paio_submit(void *acb, void *opaque, int64_t offset, int count, int type) "acb %p opaque %p offset %"PRId64" count %d type %d"
-file_copy_file_range(void *bs, int src, int64_t src_off, int dst, int64_t dst_off, int64_t bytes, int flags, int64_t ret) "bs %p src_fd %d offset %"PRIu64" dst_fd %d offset %"PRIu64" bytes %"PRIu64" flags %d ret %"PRId64
+paio_submit_co(int64_t offset, int count, int type) "offset %"PRId64" count %d type %d"
+paio_submit(void *acb, void *opaque, int64_t offset, int count, int type) "acb %p opaque %p offset %"PRId64" count %d type %d"
 
 # block/qcow2.c
 qcow2_writev_start_req(void *co, int64_t offset, int bytes) "co %p offset 0x%" PRIx64 " bytes %d"
@@ -153,6 +145,3 @@ nvme_free_req_queue_wait(void *q) "q %p"
 nvme_cmd_map_qiov(void *s, void *cmd, void *req, void *qiov, int entries) "s %p cmd %p req %p qiov %p entries %d"
 nvme_cmd_map_qiov_pages(void *s, int i, uint64_t page) "s %p page[%d] 0x%"PRIx64
 nvme_cmd_map_qiov_iov(void *s, int i, void *page, int pages) "s %p iov[%d] %p pages %d"
-
-# block/iscsi.c
-iscsi_xcopy(void *src_lun, uint64_t src_off, void *dst_lun, uint64_t dst_off, uint64_t bytes, int ret) "src_lun %p offset %"PRIu64" dst_lun %p offset %"PRIu64" bytes %"PRIu64" ret %d"

block/vdi.c

@@ -50,12 +50,8 @@
  */
 
 #include "qemu/osdep.h"
-#include "qemu/units.h"
 #include "qapi/error.h"
-#include "qapi/qobject-input-visitor.h"
-#include "qapi/qapi-visit-block-core.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "sysemu/block-backend.h"
 #include "qemu/module.h"
 #include "qemu/option.h"
@@ -84,6 +80,9 @@
 /* Command line option for static images. */
 #define BLOCK_OPT_STATIC "static"
 
+#define KiB     1024
+#define MiB     (KiB * KiB)
+
 #define SECTOR_SIZE 512
 #define DEFAULT_CLUSTER_SIZE (1 * MiB)
 
@@ -141,8 +140,6 @@
 #define VDI_DISK_SIZE_MAX        ((uint64_t)VDI_BLOCKS_IN_IMAGE_MAX * \
                                   (uint64_t)DEFAULT_CLUSTER_SIZE)
 
-static QemuOptsList vdi_create_opts;
-
 typedef struct {
     char text[0x40];
     uint32_t signature;
@@ -233,6 +230,7 @@ static void vdi_header_to_le(VdiHeader *header)
     qemu_uuid_bswap(&header->uuid_parent);
 }
 
+#if defined(CONFIG_VDI_DEBUG)
 static void vdi_header_print(VdiHeader *header)
 {
     char uuid[37];
@@ -254,15 +252,16 @@ static void vdi_header_print(VdiHeader *header)
     logout("block extra 0x%04x\n", header->block_extra);
     logout("blocks tot. 0x%04x\n", header->blocks_in_image);
     logout("blocks all. 0x%04x\n", header->blocks_allocated);
-    qemu_uuid_unparse(&header->uuid_image, uuid);
+    uuid_unparse(header->uuid_image, uuid);
     logout("uuid image  %s\n", uuid);
-    qemu_uuid_unparse(&header->uuid_last_snap, uuid);
+    uuid_unparse(header->uuid_last_snap, uuid);
     logout("uuid snap   %s\n", uuid);
-    qemu_uuid_unparse(&header->uuid_link, uuid);
+    uuid_unparse(header->uuid_link, uuid);
     logout("uuid link   %s\n", uuid);
-    qemu_uuid_unparse(&header->uuid_parent, uuid);
+    uuid_unparse(header->uuid_parent, uuid);
     logout("uuid parent %s\n", uuid);
 }
+#endif
 
 static int coroutine_fn vdi_co_check(BlockDriverState *bs, BdrvCheckResult *res,
                                      BdrvCheckMode fix)
@@ -383,9 +382,9 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     vdi_header_to_cpu(&header);
-    if (VDI_DEBUG) {
+#if defined(CONFIG_VDI_DEBUG)
     vdi_header_print(&header);
-    }
+#endif
 
     if (header.disk_size > VDI_DISK_SIZE_MAX) {
         error_setg(errp, "Unsupported VDI image size (size is 0x%" PRIx64
@@ -432,8 +431,7 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     } else if (header.block_size != DEFAULT_CLUSTER_SIZE) {
         error_setg(errp, "unsupported VDI image (block size %" PRIu32
-                         " is not %" PRIu64 ")",
-                   header.block_size, DEFAULT_CLUSTER_SIZE);
+                   " is not %u)", header.block_size, DEFAULT_CLUSTER_SIZE);
         ret = -ENOTSUP;
         goto fail;
     } else if (header.disk_size >
@@ -718,59 +716,36 @@ nonallocating_write:
     return ret;
 }
 
-static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options,
-                                         size_t block_size, Error **errp)
+static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts,
+                                           Error **errp)
 {
-    BlockdevCreateOptionsVdi *vdi_opts;
     int ret = 0;
     uint64_t bytes = 0;
     uint32_t blocks;
-    uint32_t image_type;
+    size_t block_size = DEFAULT_CLUSTER_SIZE;
+    uint32_t image_type = VDI_TYPE_DYNAMIC;
     VdiHeader header;
     size_t i;
     size_t bmap_size;
     int64_t offset = 0;
-    BlockDriverState *bs_file = NULL;
+    Error *local_err = NULL;
     BlockBackend *blk = NULL;
     uint32_t *bmap = NULL;
 
-    assert(create_options->driver == BLOCKDEV_DRIVER_VDI);
-    vdi_opts = &create_options->u.vdi;
-
     logout("\n");
 
-    /* Validate options and set default values */
-    bytes = vdi_opts->size;
-
-    if (!vdi_opts->has_preallocation) {
-        vdi_opts->preallocation = PREALLOC_MODE_OFF;
-    }
-    switch (vdi_opts->preallocation) {
-    case PREALLOC_MODE_OFF:
-        image_type = VDI_TYPE_DYNAMIC;
-        break;
-    case PREALLOC_MODE_METADATA:
-        image_type = VDI_TYPE_STATIC;
-        break;
-    default:
-        error_setg(errp, "Preallocation mode not supported for vdi");
-        return -EINVAL;
-    }
-
-#ifndef CONFIG_VDI_STATIC_IMAGE
-    if (image_type == VDI_TYPE_STATIC) {
-        ret = -ENOTSUP;
-        error_setg(errp, "Statically allocated images cannot be created in "
-                   "this build");
-        goto exit;
-    }
+    /* Read out options. */
+    bytes = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                     BDRV_SECTOR_SIZE);
+#if defined(CONFIG_VDI_BLOCK_SIZE)
+    /* TODO: Additional checks (SECTOR_SIZE * 2^n, ...). */
+    block_size = qemu_opt_get_size_del(opts,
+                                       BLOCK_OPT_CLUSTER_SIZE,
+                                       DEFAULT_CLUSTER_SIZE);
 #endif
-#ifndef CONFIG_VDI_BLOCK_SIZE
-    if (block_size != DEFAULT_CLUSTER_SIZE) {
-        ret = -ENOTSUP;
-        error_setg(errp,
-                   "A non-default cluster size is not supported in this build");
-        goto exit;
+#if defined(CONFIG_VDI_STATIC_IMAGE)
+    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_STATIC, false)) {
+        image_type = VDI_TYPE_STATIC;
     }
 #endif
 
@@ -782,16 +757,18 @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options,
         goto exit;
     }
 
-    /* Create BlockBackend to write to the image */
-    bs_file = bdrv_open_blockdev_ref(vdi_opts->file, errp);
-    if (!bs_file) {
-        ret = -EIO;
+    ret = bdrv_create_file(filename, opts, &local_err);
+    if (ret < 0) {
+        error_propagate(errp, local_err);
         goto exit;
     }
 
-    blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
-    ret = blk_insert_bs(blk, bs_file, errp);
-    if (ret < 0) {
+    blk = blk_new_open(filename, NULL, NULL,
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
+    if (blk == NULL) {
+        error_propagate(errp, local_err);
+        ret = -EIO;
         goto exit;
     }
 
@@ -822,13 +799,13 @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options,
     qemu_uuid_generate(&header.uuid_image);
     qemu_uuid_generate(&header.uuid_last_snap);
     /* There is no need to set header.uuid_link or header.uuid_parent here. */
-    if (VDI_DEBUG) {
+#if defined(CONFIG_VDI_DEBUG)
     vdi_header_print(&header);
-    }
+#endif
     vdi_header_to_le(&header);
     ret = blk_pwrite(blk, offset, &header, sizeof(header), 0);
     if (ret < 0) {
-        error_setg(errp, "Error writing header");
+        error_setg(errp, "Error writing header to %s", filename);
         goto exit;
     }
     offset += sizeof(header);
@@ -849,7 +826,7 @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options,
         }
         ret = blk_pwrite(blk, offset, bmap, bmap_size, 0);
         if (ret < 0) {
-            error_setg(errp, "Error writing bmap");
+            error_setg(errp, "Error writing bmap to %s", filename);
             goto exit;
         }
         offset += bmap_size;
@@ -859,108 +836,17 @@ static int coroutine_fn vdi_co_do_create(BlockdevCreateOptions *create_options,
         ret = blk_truncate(blk, offset + blocks * block_size,
                            PREALLOC_MODE_OFF, errp);
         if (ret < 0) {
-            error_prepend(errp, "Failed to statically allocate file");
+            error_prepend(errp, "Failed to statically allocate %s", filename);
             goto exit;
         }
     }
 
-    ret = 0;
 exit:
     blk_unref(blk);
-    bdrv_unref(bs_file);
     g_free(bmap);
     return ret;
 }
 
-static int coroutine_fn vdi_co_create(BlockdevCreateOptions *create_options,
-                                      Error **errp)
-{
-    return vdi_co_do_create(create_options, DEFAULT_CLUSTER_SIZE, errp);
-}
-
-static int coroutine_fn vdi_co_create_opts(const char *filename, QemuOpts *opts,
-                                           Error **errp)
-{
-    QDict *qdict = NULL;
-    BlockdevCreateOptions *create_options = NULL;
-    BlockDriverState *bs_file = NULL;
-    uint64_t block_size = DEFAULT_CLUSTER_SIZE;
-    bool is_static = false;
-    Visitor *v;
-    Error *local_err = NULL;
-    int ret;
-
-    /* Parse options and convert legacy syntax.
-     *
-     * Since CONFIG_VDI_BLOCK_SIZE is disabled by default,
-     * cluster-size is not part of the QAPI schema; therefore we have
-     * to parse it before creating the QAPI object. */
-#if defined(CONFIG_VDI_BLOCK_SIZE)
-    block_size = qemu_opt_get_size_del(opts,
-                                       BLOCK_OPT_CLUSTER_SIZE,
-                                       DEFAULT_CLUSTER_SIZE);
-    if (block_size < BDRV_SECTOR_SIZE || block_size > UINT32_MAX ||
-        !is_power_of_2(block_size))
-    {
-        error_setg(errp, "Invalid cluster size");
-        ret = -EINVAL;
-        goto done;
-    }
-#endif
-    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_STATIC, false)) {
-        is_static = true;
-    }
-
-    qdict = qemu_opts_to_qdict_filtered(opts, NULL, &vdi_create_opts, true);
-
-    /* Create and open the file (protocol layer) */
-    ret = bdrv_create_file(filename, opts, errp);
-    if (ret < 0) {
-        goto done;
-    }
-
-    bs_file = bdrv_open(filename, NULL, NULL,
-                        BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
-    if (!bs_file) {
-        ret = -EIO;
-        goto done;
-    }
-
-    qdict_put_str(qdict, "driver", "vdi");
-    qdict_put_str(qdict, "file", bs_file->node_name);
-    if (is_static) {
-        qdict_put_str(qdict, "preallocation", "metadata");
-    }
-
-    /* Get the QAPI object */
-    v = qobject_input_visitor_new_flat_confused(qdict, errp);
-    if (!v) {
-        ret = -EINVAL;
-        goto done;
-    }
-    visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err);
-    visit_free(v);
-
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto done;
-    }
-
-    /* Silently round up size */
-    assert(create_options->driver == BLOCKDEV_DRIVER_VDI);
-    create_options->u.vdi.size = ROUND_UP(create_options->u.vdi.size,
-                                          BDRV_SECTOR_SIZE);
-
-    /* Create the vdi image (format layer) */
-    ret = vdi_co_do_create(create_options, block_size, errp);
-done:
-    qobject_unref(qdict);
-    qapi_free_BlockdevCreateOptions(create_options);
-    bdrv_unref(bs_file);
-    return ret;
-}
-
 static void vdi_close(BlockDriverState *bs)
 {
     BDRVVdiState *s = bs->opaque;
@@ -1009,7 +895,6 @@ static BlockDriver bdrv_vdi = {
     .bdrv_close = vdi_close,
     .bdrv_reopen_prepare = vdi_reopen_prepare,
     .bdrv_child_perm          = bdrv_format_default_perms,
-    .bdrv_co_create      = vdi_co_create,
     .bdrv_co_create_opts = vdi_co_create_opts,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
     .bdrv_co_block_status = vdi_co_block_status,

block/vhdx-endian.c

@@ -19,7 +19,7 @@
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "qemu/bswap.h"
-#include "vhdx.h"
+#include "block/vhdx.h"
 
 /*
  * All the VHDX formats on disk are little endian - the following

block/vhdx-log.c

@@ -24,7 +24,7 @@
 #include "qemu/error-report.h"
 #include "qemu/module.h"
 #include "qemu/bswap.h"
-#include "vhdx.h"
+#include "block/vhdx.h"
 
 
 typedef struct VHDXLogSequence {

block/vhdx.c

@@ -18,18 +18,14 @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "sysemu/block-backend.h"
 #include "qemu/module.h"
 #include "qemu/option.h"
 #include "qemu/crc32c.h"
 #include "qemu/bswap.h"
-#include "vhdx.h"
+#include "block/vhdx.h"
 #include "migration/blocker.h"
 #include "qemu/uuid.h"
-#include "qapi/qmp/qdict.h"
-#include "qapi/qobject-input-visitor.h"
-#include "qapi/qapi-visit-block-core.h"
 
 /* Options for VHDX creation */
 
@@ -43,8 +39,6 @@ typedef enum VHDXImageType {
     VHDX_TYPE_DIFFERENCING,   /* Currently unsupported */
 } VHDXImageType;
 
-static QemuOptsList vhdx_create_opts;
-
 /* Several metadata and region table data entries are identified by
  * guids in  a MS-specific GUID format. */
 
@@ -1127,9 +1121,9 @@ static coroutine_fn int vhdx_co_readv(BlockDriverState *bs, int64_t sector_num,
                 break;
             case PAYLOAD_BLOCK_FULLY_PRESENT:
                 qemu_co_mutex_unlock(&s->lock);
-                ret = bdrv_co_preadv(bs->file, sinfo.file_offset,
-                                     sinfo.sectors_avail * BDRV_SECTOR_SIZE,
-                                     &hd_qiov, 0);
+                ret = bdrv_co_readv(bs->file,
+                                    sinfo.file_offset >> BDRV_SECTOR_BITS,
+                                    sinfo.sectors_avail, &hd_qiov);
                 qemu_co_mutex_lock(&s->lock);
                 if (ret < 0) {
                     goto exit;
@@ -1227,8 +1221,7 @@ int vhdx_user_visible_write(BlockDriverState *bs, BDRVVHDXState *s)
 }
 
 static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num,
-                                       int nb_sectors, QEMUIOVector *qiov,
-                                       int flags)
+                                      int nb_sectors, QEMUIOVector *qiov)
 {
     int ret = -ENOTSUP;
     BDRVVHDXState *s = bs->opaque;
@@ -1244,7 +1237,6 @@ static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num,
     uint64_t bat_prior_offset = 0;
     bool bat_update = false;
 
-    assert(!flags);
     qemu_iovec_init(&hd_qiov, qiov->niov);
 
     qemu_co_mutex_lock(&s->lock);
@@ -1349,9 +1341,9 @@ static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num,
                 }
                 /* block exists, so we can just overwrite it */
                 qemu_co_mutex_unlock(&s->lock);
-                ret = bdrv_co_pwritev(bs->file, sinfo.file_offset,
-                                      sectors_to_write * BDRV_SECTOR_SIZE,
-                                      &hd_qiov, 0);
+                ret = bdrv_co_writev(bs->file,
+                                    sinfo.file_offset >> BDRV_SECTOR_BITS,
+                                    sectors_to_write, &hd_qiov);
                 qemu_co_mutex_lock(&s->lock);
                 if (ret < 0) {
                     goto error_bat_restore;
@@ -1800,75 +1792,59 @@ exit:
  *    .---- ~ ----------- ~ ------------ ~ ---------------- ~ -----------.
  *   1MB
  */
-static int coroutine_fn vhdx_co_create(BlockdevCreateOptions *opts,
+static int coroutine_fn vhdx_co_create_opts(const char *filename, QemuOpts *opts,
                                             Error **errp)
 {
-    BlockdevCreateOptionsVhdx *vhdx_opts;
-    BlockBackend *blk = NULL;
-    BlockDriverState *bs = NULL;
-
     int ret = 0;
-    uint64_t image_size;
-    uint32_t log_size;
-    uint32_t block_size;
+    uint64_t image_size = (uint64_t) 2 * GiB;
+    uint32_t log_size   = 1 * MiB;
+    uint32_t block_size = 0;
     uint64_t signature;
     uint64_t metadata_offset;
     bool use_zero_blocks = false;
 
     gunichar2 *creator = NULL;
     glong creator_items;
+    BlockBackend *blk;
+    char *type = NULL;
     VHDXImageType image_type;
+    Error *local_err = NULL;
 
-    assert(opts->driver == BLOCKDEV_DRIVER_VHDX);
-    vhdx_opts = &opts->u.vhdx;
+    image_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
+    log_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_LOG_SIZE, 0);
+    block_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_BLOCK_SIZE, 0);
+    type = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
+    use_zero_blocks = qemu_opt_get_bool_del(opts, VHDX_BLOCK_OPT_ZERO, true);
 
-    /* Validate options and set default values */
-    image_size = vhdx_opts->size;
     if (image_size > VHDX_MAX_IMAGE_SIZE) {
-        error_setg(errp, "Image size too large; max of 64TB");
-        return -EINVAL;
+        error_setg_errno(errp, EINVAL, "Image size too large; max of 64TB");
+        ret = -EINVAL;
+        goto exit;
     }
 
-    if (!vhdx_opts->has_log_size) {
-        log_size = DEFAULT_LOG_SIZE;
-    } else {
-        if (vhdx_opts->log_size > UINT32_MAX) {
-            error_setg(errp, "Log size must be smaller than 4 GB");
-            return -EINVAL;
-        }
-        log_size = vhdx_opts->log_size;
-    }
-    if (log_size < MiB || (log_size % MiB) != 0) {
-        error_setg(errp, "Log size must be a multiple of 1 MB");
-        return -EINVAL;
+    if (type == NULL) {
+        type = g_strdup("dynamic");
     }
 
-    if (!vhdx_opts->has_block_state_zero) {
-        use_zero_blocks = true;
-    } else {
-        use_zero_blocks = vhdx_opts->block_state_zero;
-    }
-
-    if (!vhdx_opts->has_subformat) {
-        vhdx_opts->subformat = BLOCKDEV_VHDX_SUBFORMAT_DYNAMIC;
-    }
-
-    switch (vhdx_opts->subformat) {
-    case BLOCKDEV_VHDX_SUBFORMAT_DYNAMIC:
+    if (!strcmp(type, "dynamic")) {
         image_type = VHDX_TYPE_DYNAMIC;
-        break;
-    case BLOCKDEV_VHDX_SUBFORMAT_FIXED:
+    } else if (!strcmp(type, "fixed")) {
         image_type = VHDX_TYPE_FIXED;
-        break;
-    default:
-        g_assert_not_reached();
+    } else if (!strcmp(type, "differencing")) {
+        error_setg_errno(errp, ENOTSUP,
+                         "Differencing files not yet supported");
+        ret = -ENOTSUP;
+        goto exit;
+    } else {
+        error_setg(errp, "Invalid subformat '%s'", type);
+        ret = -EINVAL;
+        goto exit;
     }
 
     /* These are pretty arbitrary, and mainly designed to keep the BAT
      * size reasonable to load into RAM */
-    if (vhdx_opts->has_block_size) {
-        block_size = vhdx_opts->block_size;
-    } else {
+    if (block_size == 0) {
         if (image_size > 32 * TiB) {
             block_size = 64 * MiB;
         } else if (image_size > (uint64_t) 100 * GiB) {
@@ -1880,30 +1856,30 @@ static int coroutine_fn vhdx_co_create(BlockdevCreateOptions *opts,
         }
     }
 
-    if (block_size < MiB || (block_size % MiB) != 0) {
-        error_setg(errp, "Block size must be a multiple of 1 MB");
-        return -EINVAL;
-    }
-    if (!is_power_of_2(block_size)) {
-        error_setg(errp, "Block size must be a power of two");
-        return -EINVAL;
-    }
-    if (block_size > VHDX_BLOCK_SIZE_MAX) {
-        error_setg(errp, "Block size must not exceed %d", VHDX_BLOCK_SIZE_MAX);
-        return -EINVAL;
-    }
 
-    /* Create BlockBackend to write to the image */
-    bs = bdrv_open_blockdev_ref(vhdx_opts->file, errp);
-    if (bs == NULL) {
-        return -EIO;
-    }
+    /* make the log size close to what was specified, but must be
+     * min 1MB, and multiple of 1MB */
+    log_size = ROUND_UP(log_size, MiB);
 
-    blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
-    ret = blk_insert_bs(blk, bs, errp);
+    block_size = ROUND_UP(block_size, MiB);
+    block_size = block_size > VHDX_BLOCK_SIZE_MAX ? VHDX_BLOCK_SIZE_MAX :
+                                                    block_size;
+
+    ret = bdrv_create_file(filename, opts, &local_err);
     if (ret < 0) {
-        goto delete_and_exit;
+        error_propagate(errp, local_err);
+        goto exit;
     }
+
+    blk = blk_new_open(filename, NULL, NULL,
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
+    if (blk == NULL) {
+        error_propagate(errp, local_err);
+        ret = -EIO;
+        goto exit;
+    }
+
     blk_set_allow_write_beyond_eof(blk, true);
 
     /* Create (A) */
@@ -1952,108 +1928,15 @@ static int coroutine_fn vhdx_co_create(BlockdevCreateOptions *opts,
         goto delete_and_exit;
     }
 
-    ret = 0;
+
 delete_and_exit:
     blk_unref(blk);
-    bdrv_unref(bs);
+exit:
+    g_free(type);
     g_free(creator);
     return ret;
 }
 
-static int coroutine_fn vhdx_co_create_opts(const char *filename,
-                                            QemuOpts *opts,
-                                            Error **errp)
-{
-    BlockdevCreateOptions *create_options = NULL;
-    QDict *qdict;
-    Visitor *v;
-    BlockDriverState *bs = NULL;
-    Error *local_err = NULL;
-    int ret;
-
-    static const QDictRenames opt_renames[] = {
-        { VHDX_BLOCK_OPT_LOG_SIZE,      "log-size" },
-        { VHDX_BLOCK_OPT_BLOCK_SIZE,    "block-size" },
-        { VHDX_BLOCK_OPT_ZERO,          "block-state-zero" },
-        { NULL, NULL },
-    };
-
-    /* Parse options and convert legacy syntax */
-    qdict = qemu_opts_to_qdict_filtered(opts, NULL, &vhdx_create_opts, true);
-
-    if (!qdict_rename_keys(qdict, opt_renames, errp)) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* Create and open the file (protocol layer) */
-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto fail;
-    }
-
-    bs = bdrv_open(filename, NULL, NULL,
-                   BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
-    if (bs == NULL) {
-        ret = -EIO;
-        goto fail;
-    }
-
-    /* Now get the QAPI type BlockdevCreateOptions */
-    qdict_put_str(qdict, "driver", "vhdx");
-    qdict_put_str(qdict, "file", bs->node_name);
-
-    v = qobject_input_visitor_new_flat_confused(qdict, errp);
-    if (!v) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err);
-    visit_free(v);
-
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* Silently round up sizes:
-     * The image size is rounded to 512 bytes. Make the block and log size
-     * close to what was specified, but must be at least 1MB, and a multiple of
-     * 1 MB. Also respect VHDX_BLOCK_SIZE_MAX for block sizes. block_size = 0
-     * means auto, which is represented by a missing key in QAPI. */
-    assert(create_options->driver == BLOCKDEV_DRIVER_VHDX);
-    create_options->u.vhdx.size =
-        ROUND_UP(create_options->u.vhdx.size, BDRV_SECTOR_SIZE);
-
-    if (create_options->u.vhdx.has_log_size) {
-        create_options->u.vhdx.log_size =
-            ROUND_UP(create_options->u.vhdx.log_size, MiB);
-    }
-    if (create_options->u.vhdx.has_block_size) {
-        create_options->u.vhdx.block_size =
-            ROUND_UP(create_options->u.vhdx.block_size, MiB);
-
-        if (create_options->u.vhdx.block_size == 0) {
-            create_options->u.vhdx.has_block_size = false;
-        }
-        if (create_options->u.vhdx.block_size > VHDX_BLOCK_SIZE_MAX) {
-            create_options->u.vhdx.block_size = VHDX_BLOCK_SIZE_MAX;
-        }
-    }
-
-    /* Create the vhdx image (format layer) */
-    ret = vhdx_co_create(create_options, errp);
-
-fail:
-    qobject_unref(qdict);
-    bdrv_unref(bs);
-    qapi_free_BlockdevCreateOptions(create_options);
-    return ret;
-}
-
 /* If opened r/w, the VHDX driver will automatically replay the log,
  * if one is present, inside the vhdx_open() call.
  *
@@ -2122,7 +2005,6 @@ static BlockDriver bdrv_vhdx = {
     .bdrv_child_perm        = bdrv_format_default_perms,
     .bdrv_co_readv          = vhdx_co_readv,
     .bdrv_co_writev         = vhdx_co_writev,
-    .bdrv_co_create         = vhdx_co_create,
     .bdrv_co_create_opts    = vhdx_co_create_opts,
     .bdrv_get_info          = vhdx_get_info,
     .bdrv_co_check          = vhdx_co_check,

block/vmdk.c

@@ -47,8 +47,6 @@
 #define VMDK4_FLAG_MARKER (1 << 17)
 #define VMDK4_GD_AT_END 0xffffffffffffffffULL
 
-#define VMDK_EXTENT_MAX_SECTORS (1ULL << 32)
-
 #define VMDK_GTE_ZEROED 0x1
 
 /* VMDK internal error codes */
@@ -333,12 +331,6 @@ static int vmdk_is_cid_valid(BlockDriverState *bs)
     if (!s->cid_checked && bs->backing) {
         BlockDriverState *p_bs = bs->backing->bs;
 
-        if (strcmp(p_bs->drv->format_name, "vmdk")) {
-            /* Backing file is not in vmdk format, so it does not have
-             * a CID, which makes the overlay's parent CID invalid */
-            return 0;
-        }
-
         if (vmdk_read_cid(p_bs, 0, &cur_pcid) != 0) {
             /* read failure: report as not valid */
             return 0;
@@ -1258,10 +1250,6 @@ static int get_cluster_offset(BlockDriverState *bs,
             return zeroed ? VMDK_ZEROED : VMDK_UNALLOC;
         }
 
-        if (extent->next_cluster_sector >= VMDK_EXTENT_MAX_SECTORS) {
-            return VMDK_ERROR;
-        }
-
         cluster_sector = extent->next_cluster_sector;
         extent->next_cluster_sector += extent->cluster_sectors;
 

block/vpc.c

@@ -26,16 +26,12 @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "sysemu/block-backend.h"
 #include "qemu/module.h"
 #include "qemu/option.h"
 #include "migration/blocker.h"
 #include "qemu/bswap.h"
 #include "qemu/uuid.h"
-#include "qapi/qmp/qdict.h"
-#include "qapi/qobject-input-visitor.h"
-#include "qapi/qapi-visit-block-core.h"
 
 /**************************************************************/
 
@@ -170,8 +166,6 @@ static QemuOptsList vpc_runtime_opts = {
     }
 };
 
-static QemuOptsList vpc_create_opts;
-
 static uint32_t vpc_checksum(uint8_t* buf, size_t size)
 {
     uint32_t res = 0;
@@ -903,19 +897,60 @@ static int create_fixed_disk(BlockBackend *blk, uint8_t *buf,
     return ret;
 }
 
-static int calculate_rounded_image_size(BlockdevCreateOptionsVpc *vpc_opts,
-                                        uint16_t *out_cyls,
-                                        uint8_t *out_heads,
-                                        uint8_t *out_secs_per_cyl,
-                                        int64_t *out_total_sectors,
+static int coroutine_fn vpc_co_create_opts(const char *filename, QemuOpts *opts,
                                            Error **errp)
 {
-    int64_t total_size = vpc_opts->size;
+    uint8_t buf[1024];
+    VHDFooter *footer = (VHDFooter *) buf;
+    char *disk_type_param;
+    int i;
     uint16_t cyls = 0;
     uint8_t heads = 0;
     uint8_t secs_per_cyl = 0;
     int64_t total_sectors;
-    int i;
+    int64_t total_size;
+    int disk_type;
+    int ret = -EIO;
+    bool force_size;
+    Error *local_err = NULL;
+    BlockBackend *blk = NULL;
+
+    /* Read out options */
+    total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                          BDRV_SECTOR_SIZE);
+    disk_type_param = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
+    if (disk_type_param) {
+        if (!strcmp(disk_type_param, "dynamic")) {
+            disk_type = VHD_DYNAMIC;
+        } else if (!strcmp(disk_type_param, "fixed")) {
+            disk_type = VHD_FIXED;
+        } else {
+            error_setg(errp, "Invalid disk type, %s", disk_type_param);
+            ret = -EINVAL;
+            goto out;
+        }
+    } else {
+        disk_type = VHD_DYNAMIC;
+    }
+
+    force_size = qemu_opt_get_bool_del(opts, VPC_OPT_FORCE_SIZE, false);
+
+    ret = bdrv_create_file(filename, opts, &local_err);
+    if (ret < 0) {
+        error_propagate(errp, local_err);
+        goto out;
+    }
+
+    blk = blk_new_open(filename, NULL, NULL,
+                       BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+                       &local_err);
+    if (blk == NULL) {
+        error_propagate(errp, local_err);
+        ret = -EIO;
+        goto out;
+    }
+
+    blk_set_allow_write_beyond_eof(blk, true);
 
     /*
      * Calculate matching total_size and geometry. Increase the number of
@@ -926,7 +961,7 @@ static int calculate_rounded_image_size(BlockdevCreateOptionsVpc *vpc_opts,
      * we set the geometry to 65535 x 16 x 255 (CxHxS) sectors and use
      * the image size from the VHD footer to calculate total_sectors.
      */
-    if (vpc_opts->force_size) {
+    if (force_size) {
         /* This will force the use of total_size for sector count, below */
         cyls         = VHD_CHS_MAX_C;
         heads        = VHD_CHS_MAX_H;
@@ -943,95 +978,19 @@ static int calculate_rounded_image_size(BlockdevCreateOptionsVpc *vpc_opts,
         /* Allow a maximum disk size of 2040 GiB */
         if (total_sectors > VHD_MAX_SECTORS) {
             error_setg(errp, "Disk size is too large, max size is 2040 GiB");
-            return -EFBIG;
+            ret = -EFBIG;
+            goto out;
         }
     } else {
         total_sectors = (int64_t)cyls * heads * secs_per_cyl;
-    }
-
-    *out_total_sectors = total_sectors;
-    if (out_cyls) {
-        *out_cyls = cyls;
-        *out_heads = heads;
-        *out_secs_per_cyl = secs_per_cyl;
-    }
-
-    return 0;
-}
-
-static int coroutine_fn vpc_co_create(BlockdevCreateOptions *opts,
-                                      Error **errp)
-{
-    BlockdevCreateOptionsVpc *vpc_opts;
-    BlockBackend *blk = NULL;
-    BlockDriverState *bs = NULL;
-
-    uint8_t buf[1024];
-    VHDFooter *footer = (VHDFooter *) buf;
-    uint16_t cyls = 0;
-    uint8_t heads = 0;
-    uint8_t secs_per_cyl = 0;
-    int64_t total_sectors;
-    int64_t total_size;
-    int disk_type;
-    int ret = -EIO;
-
-    assert(opts->driver == BLOCKDEV_DRIVER_VPC);
-    vpc_opts = &opts->u.vpc;
-
-    /* Validate options and set default values */
-    total_size = vpc_opts->size;
-
-    if (!vpc_opts->has_subformat) {
-        vpc_opts->subformat = BLOCKDEV_VPC_SUBFORMAT_DYNAMIC;
-    }
-    switch (vpc_opts->subformat) {
-    case BLOCKDEV_VPC_SUBFORMAT_DYNAMIC:
-        disk_type = VHD_DYNAMIC;
-        break;
-    case BLOCKDEV_VPC_SUBFORMAT_FIXED:
-        disk_type = VHD_FIXED;
-        break;
-    default:
-        g_assert_not_reached();
-    }
-
-    /* Create BlockBackend to write to the image */
-    bs = bdrv_open_blockdev_ref(vpc_opts->file, errp);
-    if (bs == NULL) {
-        return -EIO;
-    }
-
-    blk = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
-    ret = blk_insert_bs(blk, bs, errp);
-    if (ret < 0) {
-        goto out;
-    }
-    blk_set_allow_write_beyond_eof(blk, true);
-
-    /* Get geometry and check that it matches the image size*/
-    ret = calculate_rounded_image_size(vpc_opts, &cyls, &heads, &secs_per_cyl,
-                                       &total_sectors, errp);
-    if (ret < 0) {
-        goto out;
-    }
-
-    if (total_size != total_sectors * BDRV_SECTOR_SIZE) {
-        error_setg(errp, "The requested image size cannot be represented in "
-                         "CHS geometry");
-        error_append_hint(errp, "Try size=%llu or force-size=on (the "
-                                "latter makes the image incompatible with "
-                                "Virtual PC)",
-                          total_sectors * BDRV_SECTOR_SIZE);
-        ret = -EINVAL;
-        goto out;
+        total_size = total_sectors * BDRV_SECTOR_SIZE;
     }
 
     /* Prepare the Hard Disk Footer */
     memset(buf, 0, 1024);
 
     memcpy(footer->creator, "conectix", 8);
-    if (vpc_opts->force_size) {
+    if (force_size) {
         memcpy(footer->creator_app, "qem2", 4);
     } else {
         memcpy(footer->creator_app, "qemu", 4);
@@ -1073,94 +1032,10 @@ static int coroutine_fn vpc_co_create(BlockdevCreateOptions *opts,
 
 out:
     blk_unref(blk);
-    bdrv_unref(bs);
+    g_free(disk_type_param);
     return ret;
 }
 
-static int coroutine_fn vpc_co_create_opts(const char *filename,
-                                           QemuOpts *opts, Error **errp)
-{
-    BlockdevCreateOptions *create_options = NULL;
-    QDict *qdict;
-    Visitor *v;
-    BlockDriverState *bs = NULL;
-    Error *local_err = NULL;
-    int ret;
-
-    static const QDictRenames opt_renames[] = {
-        { VPC_OPT_FORCE_SIZE,           "force-size" },
-        { NULL, NULL },
-    };
-
-    /* Parse options and convert legacy syntax */
-    qdict = qemu_opts_to_qdict_filtered(opts, NULL, &vpc_create_opts, true);
-
-    if (!qdict_rename_keys(qdict, opt_renames, errp)) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* Create and open the file (protocol layer) */
-    ret = bdrv_create_file(filename, opts, &local_err);
-    if (ret < 0) {
-        error_propagate(errp, local_err);
-        goto fail;
-    }
-
-    bs = bdrv_open(filename, NULL, NULL,
-                   BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
-    if (bs == NULL) {
-        ret = -EIO;
-        goto fail;
-    }
-
-    /* Now get the QAPI type BlockdevCreateOptions */
-    qdict_put_str(qdict, "driver", "vpc");
-    qdict_put_str(qdict, "file", bs->node_name);
-
-    v = qobject_input_visitor_new_flat_confused(qdict, errp);
-    if (!v) {
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    visit_type_BlockdevCreateOptions(v, NULL, &create_options, &local_err);
-    visit_free(v);
-
-    if (local_err) {
-        error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto fail;
-    }
-
-    /* Silently round up size */
-    assert(create_options->driver == BLOCKDEV_DRIVER_VPC);
-    create_options->u.vpc.size =
-        ROUND_UP(create_options->u.vpc.size, BDRV_SECTOR_SIZE);
-
-    if (!create_options->u.vpc.force_size) {
-        int64_t total_sectors;
-        ret = calculate_rounded_image_size(&create_options->u.vpc, NULL, NULL,
-                                           NULL, &total_sectors, errp);
-        if (ret < 0) {
-            goto fail;
-        }
-
-        create_options->u.vpc.size = total_sectors * BDRV_SECTOR_SIZE;
-    }
-
-
-    /* Create the vpc image (format layer) */
-    ret = vpc_co_create(create_options, errp);
-
-fail:
-    qobject_unref(qdict);
-    bdrv_unref(bs);
-    qapi_free_BlockdevCreateOptions(create_options);
-    return ret;
-}
-
-
 static int vpc_has_zero_init(BlockDriverState *bs)
 {
     BDRVVPCState *s = bs->opaque;
@@ -1221,7 +1096,6 @@ static BlockDriver bdrv_vpc = {
     .bdrv_close             = vpc_close,
     .bdrv_reopen_prepare    = vpc_reopen_prepare,
     .bdrv_child_perm        = bdrv_format_default_perms,
-    .bdrv_co_create         = vpc_co_create,
     .bdrv_co_create_opts    = vpc_co_create_opts,
 
     .bdrv_co_preadv             = vpc_co_preadv,

block/vvfat.c

@@ -27,7 +27,6 @@
 #include <dirent.h>
 #include "qapi/error.h"
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "qemu/module.h"
 #include "qemu/option.h"
 #include "qemu/bswap.h"
@@ -3130,11 +3129,10 @@ static void vvfat_qcow_options(int *child_flags, QDict *child_options,
                                int parent_flags, QDict *parent_options)
 {
     qdict_set_default_str(child_options, BDRV_OPT_READ_ONLY, "off");
-    qdict_set_default_str(child_options, BDRV_OPT_CACHE_NO_FLUSH, "on");
+    *child_flags = BDRV_O_NO_FLUSH;
 }
 
 static const BdrvChildRole child_vvfat_qcow = {
-    .parent_is_bds      = true,
     .inherit_options    = vvfat_qcow_options,
 };
 
@@ -3181,7 +3179,7 @@ static int enable_write_target(BlockDriverState *bs, Error **errp)
     qdict_put_str(options, "write-target.driver", "qcow");
     s->qcow = bdrv_open_child(s->qcow_filename, options, "write-target", bs,
                               &child_vvfat_qcow, false, errp);
-    qobject_unref(options);
+    QDECREF(options);
     if (!s->qcow) {
         ret = -EINVAL;
         goto err;

block/vxhs.c

@@ -12,7 +12,6 @@
 #include <qnio/qnio_api.h>
 #include <sys/param.h>
 #include "block/block_int.h"
-#include "block/qdict.h"
 #include "qapi/qmp/qerror.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qstring.h"
@@ -217,12 +216,6 @@ static void vxhs_parse_filename(const char *filename, QDict *options,
     }
 }
 
-static void vxhs_refresh_limits(BlockDriverState *bs, Error **errp)
-{
-    /* XXX Does VXHS support AIO on less than 512-byte alignment? */
-    bs->bl.request_alignment = 512;
-}
-
 static int vxhs_init_and_ref(void)
 {
     if (vxhs_ref++ == 0) {
@@ -403,7 +396,7 @@ static int vxhs_open(BlockDriverState *bs, QDict *options,
 
 out:
     g_free(of_vsa_addr);
-    qobject_unref(backing_options);
+    QDECREF(backing_options);
     qemu_opts_del(tcp_opts);
     qemu_opts_del(opts);
     g_free(cacert);
@@ -431,17 +424,21 @@ static const AIOCBInfo vxhs_aiocb_info = {
  * and is passed to QNIO. When QNIO completes the work,
  * it will be passed back through the callback.
  */
-static BlockAIOCB *vxhs_aio_rw(BlockDriverState *bs, uint64_t offset,
-                               QEMUIOVector *qiov, uint64_t size,
+static BlockAIOCB *vxhs_aio_rw(BlockDriverState *bs, int64_t sector_num,
+                               QEMUIOVector *qiov, int nb_sectors,
                                BlockCompletionFunc *cb, void *opaque,
                                VDISKAIOCmd iodir)
 {
     VXHSAIOCB *acb = NULL;
     BDRVVXHSState *s = bs->opaque;
+    size_t size;
+    uint64_t offset;
     int iio_flags = 0;
     int ret = 0;
     void *dev_handle = s->vdisk_hostinfo.dev_handle;
 
+    offset = sector_num * BDRV_SECTOR_SIZE;
+    size = nb_sectors * BDRV_SECTOR_SIZE;
     acb = qemu_aio_get(&vxhs_aiocb_info, bs, cb, opaque);
 
     /*
@@ -454,11 +451,11 @@ static BlockAIOCB *vxhs_aio_rw(BlockDriverState *bs, uint64_t offset,
     switch (iodir) {
     case VDISK_AIO_WRITE:
             ret = iio_writev(dev_handle, acb, qiov->iov, qiov->niov,
-                             offset, size, iio_flags);
+                             offset, (uint64_t)size, iio_flags);
             break;
     case VDISK_AIO_READ:
             ret = iio_readv(dev_handle, acb, qiov->iov, qiov->niov,
-                            offset, size, iio_flags);
+                            offset, (uint64_t)size, iio_flags);
             break;
     default:
             trace_vxhs_aio_rw_invalid(iodir);
@@ -477,20 +474,22 @@ errout:
     return NULL;
 }
 
-static BlockAIOCB *vxhs_aio_preadv(BlockDriverState *bs,
-                                   uint64_t offset, uint64_t bytes,
-                                   QEMUIOVector *qiov, int flags,
+static BlockAIOCB *vxhs_aio_readv(BlockDriverState *bs,
+                                   int64_t sector_num, QEMUIOVector *qiov,
+                                   int nb_sectors,
                                    BlockCompletionFunc *cb, void *opaque)
 {
-    return vxhs_aio_rw(bs, offset, qiov, bytes, cb, opaque, VDISK_AIO_READ);
+    return vxhs_aio_rw(bs, sector_num, qiov, nb_sectors, cb,
+                       opaque, VDISK_AIO_READ);
 }
 
-static BlockAIOCB *vxhs_aio_pwritev(BlockDriverState *bs,
-                                    uint64_t offset, uint64_t bytes,
-                                    QEMUIOVector *qiov, int flags,
+static BlockAIOCB *vxhs_aio_writev(BlockDriverState *bs,
+                                   int64_t sector_num, QEMUIOVector *qiov,
+                                   int nb_sectors,
                                    BlockCompletionFunc *cb, void *opaque)
 {
-    return vxhs_aio_rw(bs, offset, qiov, bytes, cb, opaque, VDISK_AIO_WRITE);
+    return vxhs_aio_rw(bs, sector_num, qiov, nb_sectors,
+                       cb, opaque, VDISK_AIO_WRITE);
 }
 
 static void vxhs_close(BlockDriverState *bs)
@@ -562,11 +561,10 @@ static BlockDriver bdrv_vxhs = {
     .instance_size                = sizeof(BDRVVXHSState),
     .bdrv_file_open               = vxhs_open,
     .bdrv_parse_filename          = vxhs_parse_filename,
-    .bdrv_refresh_limits          = vxhs_refresh_limits,
     .bdrv_close                   = vxhs_close,
     .bdrv_getlength               = vxhs_getlength,
-    .bdrv_aio_preadv              = vxhs_aio_preadv,
-    .bdrv_aio_pwritev             = vxhs_aio_pwritev,
+    .bdrv_aio_readv               = vxhs_aio_readv,
+    .bdrv_aio_writev              = vxhs_aio_writev,
 };
 
 static void bdrv_vxhs_init(void)

block/win32-aio.c

@@ -112,14 +112,15 @@ static const AIOCBInfo win32_aiocb_info = {
 
 BlockAIOCB *win32_aio_submit(BlockDriverState *bs,
         QEMUWin32AIOState *aio, HANDLE hfile,
-        uint64_t offset, uint64_t bytes, QEMUIOVector *qiov,
+        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
         BlockCompletionFunc *cb, void *opaque, int type)
 {
     struct QEMUWin32AIOCB *waiocb;
+    uint64_t offset = sector_num * 512;
     DWORD rc;
 
     waiocb = qemu_aio_get(&win32_aiocb_info, bs, cb, opaque);
-    waiocb->nbytes = bytes;
+    waiocb->nbytes = nb_sectors * 512;
     waiocb->qiov = qiov;
     waiocb->is_read = (type == QEMU_AIO_READ);
 

blockdev-nbd.c

@@ -220,26 +220,3 @@ void qmp_nbd_server_stop(Error **errp)
     nbd_server_free(nbd_server);
     nbd_server = NULL;
 }
-
-void qmp_x_nbd_server_add_bitmap(const char *name, const char *bitmap,
-                                 bool has_bitmap_export_name,
-                                 const char *bitmap_export_name,
-                                 Error **errp)
-{
-    NBDExport *exp;
-
-    if (!nbd_server) {
-        error_setg(errp, "NBD server not running");
-        return;
-    }
-
-    exp = nbd_export_find(name);
-    if (exp == NULL) {
-        error_setg(errp, "Export '%s' is not found", name);
-        return;
-    }
-
-    nbd_export_bitmap(exp, bitmap,
-                      has_bitmap_export_name ? bitmap_export_name : bitmap,
-                      errp);
-}

blockdev.c

@@ -35,7 +35,6 @@
 #include "sysemu/blockdev.h"
 #include "hw/block/block.h"
 #include "block/blockjob.h"
-#include "block/qdict.h"
 #include "block/throttle-groups.h"
 #include "monitor/monitor.h"
 #include "qemu/error-report.h"
@@ -151,7 +150,7 @@ void blockdev_mark_auto_del(BlockBackend *blk)
         aio_context_acquire(aio_context);
 
         if (bs->job) {
-            job_cancel(&bs->job->job, false);
+            block_job_cancel(bs->job);
         }
 
         aio_context_release(aio_context);
@@ -335,8 +334,7 @@ static bool parse_stats_intervals(BlockAcctStats *stats, QList *intervals,
 
         case QTYPE_QSTRING: {
             unsigned long long length;
-            const char *str = qstring_get_str(qobject_to(QString,
-                                                         entry->value));
+            const char *str = qstring_get_str(qobject_to_qstring(entry->value));
             if (parse_uint_full(str, &length, 10) == 0 &&
                 length > 0 && length <= UINT_MAX) {
                 block_acct_add_interval(stats, (unsigned) length);
@@ -348,7 +346,7 @@ static bool parse_stats_intervals(BlockAcctStats *stats, QList *intervals,
         }
 
         case QTYPE_QNUM: {
-            int64_t length = qnum_get_int(qobject_to(QNum, entry->value));
+            int64_t length = qnum_get_int(qobject_to_qnum(entry->value));
 
             if (length > 0 && length <= UINT_MAX) {
                 block_acct_add_interval(stats, (unsigned) length);
@@ -577,7 +575,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
         blk_rs->read_only     = read_only;
         blk_rs->detect_zeroes = detect_zeroes;
 
-        qobject_unref(bs_opts);
+        QDECREF(bs_opts);
     } else {
         if (file && !*file) {
             file = NULL;
@@ -633,16 +631,16 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
 
 err_no_bs_opts:
     qemu_opts_del(opts);
-    qobject_unref(interval_dict);
-    qobject_unref(interval_list);
+    QDECREF(interval_dict);
+    QDECREF(interval_list);
     return blk;
 
 early_err:
     qemu_opts_del(opts);
-    qobject_unref(interval_dict);
-    qobject_unref(interval_list);
+    QDECREF(interval_dict);
+    QDECREF(interval_list);
 err_no_opts:
-    qobject_unref(bs_opts);
+    QDECREF(bs_opts);
     return NULL;
 }
 
@@ -1131,7 +1129,7 @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type)
 
 fail:
     qemu_opts_del(legacy_opts);
-    qobject_unref(bs_opts);
+    QDECREF(bs_opts);
     return dinfo;
 }
 
@@ -1447,7 +1445,7 @@ typedef struct BlkActionOps {
 struct BlkActionState {
     TransactionAction *action;
     const BlkActionOps *ops;
-    JobTxn *block_job_txn;
+    BlockJobTxn *block_job_txn;
     TransactionProperties *txn_props;
     QSIMPLEQ_ENTRY(BlkActionState) entry;
 };
@@ -1865,7 +1863,7 @@ typedef struct DriveBackupState {
     BlockJob *job;
 } DriveBackupState;
 
-static BlockJob *do_drive_backup(DriveBackup *backup, JobTxn *txn,
+static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn,
                             Error **errp);
 
 static void drive_backup_prepare(BlkActionState *common, Error **errp)
@@ -1911,7 +1909,7 @@ static void drive_backup_commit(BlkActionState *common)
     aio_context_acquire(aio_context);
 
     assert(state->job);
-    job_start(&state->job->job);
+    block_job_start(state->job);
 
     aio_context_release(aio_context);
 }
@@ -1926,7 +1924,7 @@ static void drive_backup_abort(BlkActionState *common)
         aio_context = bdrv_get_aio_context(state->bs);
         aio_context_acquire(aio_context);
 
-        job_cancel_sync(&state->job->job);
+        block_job_cancel_sync(state->job);
 
         aio_context_release(aio_context);
     }
@@ -1955,7 +1953,7 @@ typedef struct BlockdevBackupState {
     BlockJob *job;
 } BlockdevBackupState;
 
-static BlockJob *do_blockdev_backup(BlockdevBackup *backup, JobTxn *txn,
+static BlockJob *do_blockdev_backup(BlockdevBackup *backup, BlockJobTxn *txn,
                                     Error **errp);
 
 static void blockdev_backup_prepare(BlkActionState *common, Error **errp)
@@ -1969,7 +1967,7 @@ static void blockdev_backup_prepare(BlkActionState *common, Error **errp)
     assert(common->action->type == TRANSACTION_ACTION_KIND_BLOCKDEV_BACKUP);
     backup = common->action->u.blockdev_backup.data;
 
-    bs = bdrv_lookup_bs(backup->device, backup->device, errp);
+    bs = qmp_get_root_bs(backup->device, errp);
     if (!bs) {
         return;
     }
@@ -2009,7 +2007,7 @@ static void blockdev_backup_commit(BlkActionState *common)
     aio_context_acquire(aio_context);
 
     assert(state->job);
-    job_start(&state->job->job);
+    block_job_start(state->job);
 
     aio_context_release(aio_context);
 }
@@ -2024,7 +2022,7 @@ static void blockdev_backup_abort(BlkActionState *common)
         aio_context = bdrv_get_aio_context(state->bs);
         aio_context_acquire(aio_context);
 
-        job_cancel_sync(&state->job->job);
+        block_job_cancel_sync(state->job);
 
         aio_context_release(aio_context);
     }
@@ -2053,7 +2051,6 @@ typedef struct BlockDirtyBitmapState {
     BlockDriverState *bs;
     HBitmap *backup;
     bool prepared;
-    bool was_enabled;
 } BlockDirtyBitmapState;
 
 static void block_dirty_bitmap_add_prepare(BlkActionState *common,
@@ -2074,7 +2071,6 @@ static void block_dirty_bitmap_add_prepare(BlkActionState *common,
                                action->has_granularity, action->granularity,
                                action->has_persistent, action->persistent,
                                action->has_autoload, action->autoload,
-                               action->has_x_disabled, action->x_disabled,
                                &local_err);
 
     if (!local_err) {
@@ -2122,9 +2118,6 @@ static void block_dirty_bitmap_clear_prepare(BlkActionState *common,
     if (bdrv_dirty_bitmap_frozen(state->bitmap)) {
         error_setg(errp, "Cannot modify a frozen bitmap");
         return;
-    } else if (bdrv_dirty_bitmap_qmp_locked(state->bitmap)) {
-        error_setg(errp, "Cannot modify a locked bitmap");
-        return;
     } else if (!bdrv_dirty_bitmap_enabled(state->bitmap)) {
         error_setg(errp, "Cannot clear a disabled bitmap");
         return;
@@ -2154,74 +2147,6 @@ static void block_dirty_bitmap_clear_commit(BlkActionState *common)
     hbitmap_free(state->backup);
 }
 
-static void block_dirty_bitmap_enable_prepare(BlkActionState *common,
-                                              Error **errp)
-{
-    BlockDirtyBitmap *action;
-    BlockDirtyBitmapState *state = DO_UPCAST(BlockDirtyBitmapState,
-                                             common, common);
-
-    if (action_check_completion_mode(common, errp) < 0) {
-        return;
-    }
-
-    action = common->action->u.x_block_dirty_bitmap_enable.data;
-    state->bitmap = block_dirty_bitmap_lookup(action->node,
-                                              action->name,
-                                              NULL,
-                                              errp);
-    if (!state->bitmap) {
-        return;
-    }
-
-    state->was_enabled = bdrv_dirty_bitmap_enabled(state->bitmap);
-    bdrv_enable_dirty_bitmap(state->bitmap);
-}
-
-static void block_dirty_bitmap_enable_abort(BlkActionState *common)
-{
-    BlockDirtyBitmapState *state = DO_UPCAST(BlockDirtyBitmapState,
-                                             common, common);
-
-    if (!state->was_enabled) {
-        bdrv_disable_dirty_bitmap(state->bitmap);
-    }
-}
-
-static void block_dirty_bitmap_disable_prepare(BlkActionState *common,
-                                               Error **errp)
-{
-    BlockDirtyBitmap *action;
-    BlockDirtyBitmapState *state = DO_UPCAST(BlockDirtyBitmapState,
-                                             common, common);
-
-    if (action_check_completion_mode(common, errp) < 0) {
-        return;
-    }
-
-    action = common->action->u.x_block_dirty_bitmap_disable.data;
-    state->bitmap = block_dirty_bitmap_lookup(action->node,
-                                              action->name,
-                                              NULL,
-                                              errp);
-    if (!state->bitmap) {
-        return;
-    }
-
-    state->was_enabled = bdrv_dirty_bitmap_enabled(state->bitmap);
-    bdrv_disable_dirty_bitmap(state->bitmap);
-}
-
-static void block_dirty_bitmap_disable_abort(BlkActionState *common)
-{
-    BlockDirtyBitmapState *state = DO_UPCAST(BlockDirtyBitmapState,
-                                             common, common);
-
-    if (state->was_enabled) {
-        bdrv_enable_dirty_bitmap(state->bitmap);
-    }
-}
-
 static void abort_prepare(BlkActionState *common, Error **errp)
 {
     error_setg(errp, "Transaction aborted using Abort action");
@@ -2282,16 +2207,6 @@ static const BlkActionOps actions[] = {
         .prepare = block_dirty_bitmap_clear_prepare,
         .commit = block_dirty_bitmap_clear_commit,
         .abort = block_dirty_bitmap_clear_abort,
-    },
-    [TRANSACTION_ACTION_KIND_X_BLOCK_DIRTY_BITMAP_ENABLE] = {
-        .instance_size = sizeof(BlockDirtyBitmapState),
-        .prepare = block_dirty_bitmap_enable_prepare,
-        .abort = block_dirty_bitmap_enable_abort,
-    },
-    [TRANSACTION_ACTION_KIND_X_BLOCK_DIRTY_BITMAP_DISABLE] = {
-        .instance_size = sizeof(BlockDirtyBitmapState),
-        .prepare = block_dirty_bitmap_disable_prepare,
-        .abort = block_dirty_bitmap_disable_abort,
     }
 };
 
@@ -2324,7 +2239,7 @@ void qmp_transaction(TransactionActionList *dev_list,
                      Error **errp)
 {
     TransactionActionList *dev_entry = dev_list;
-    JobTxn *block_job_txn = NULL;
+    BlockJobTxn *block_job_txn = NULL;
     BlkActionState *state, *next;
     Error *local_err = NULL;
 
@@ -2332,11 +2247,11 @@ void qmp_transaction(TransactionActionList *dev_list,
     QSIMPLEQ_INIT(&snap_bdrv_states);
 
     /* Does this transaction get canceled as a group on failure?
-     * If not, we don't really need to make a JobTxn.
+     * If not, we don't really need to make a BlockJobTxn.
      */
     props = get_transaction_properties(props);
     if (props->completion_mode != ACTION_COMPLETION_MODE_INDIVIDUAL) {
-        block_job_txn = job_txn_new();
+        block_job_txn = block_job_txn_new();
     }
 
     /* drain all i/o before any operations */
@@ -2395,7 +2310,7 @@ exit:
     if (!has_props) {
         qapi_free_TransactionProperties(props);
     }
-    job_txn_unref(block_job_txn);
+    block_job_txn_unref(block_job_txn);
 }
 
 void qmp_eject(bool has_device, const char *device,
@@ -2882,7 +2797,6 @@ void qmp_block_dirty_bitmap_add(const char *node, const char *name,
                                 bool has_granularity, uint32_t granularity,
                                 bool has_persistent, bool persistent,
                                 bool has_autoload, bool autoload,
-                                bool has_disabled, bool disabled,
                                 Error **errp)
 {
     BlockDriverState *bs;
@@ -2917,10 +2831,6 @@ void qmp_block_dirty_bitmap_add(const char *node, const char *name,
         warn_report("Autoload option is deprecated and its value is ignored");
     }
 
-    if (!has_disabled) {
-        disabled = false;
-    }
-
     if (persistent &&
         !bdrv_can_store_new_dirty_bitmap(bs, name, granularity, errp))
     {
@@ -2932,10 +2842,6 @@ void qmp_block_dirty_bitmap_add(const char *node, const char *name,
         return;
     }
 
-    if (disabled) {
-        bdrv_disable_dirty_bitmap(bitmap);
-    }
-
     bdrv_dirty_bitmap_set_persistance(bitmap, persistent);
 }
 
@@ -2956,11 +2862,6 @@ void qmp_block_dirty_bitmap_remove(const char *node, const char *name,
                    "Bitmap '%s' is currently frozen and cannot be removed",
                    name);
         return;
-    } else if (bdrv_dirty_bitmap_qmp_locked(bitmap)) {
-        error_setg(errp,
-                   "Bitmap '%s' is currently locked and cannot be removed",
-                   name);
-        return;
     }
 
     if (bdrv_dirty_bitmap_get_persistance(bitmap)) {
@@ -2971,6 +2872,7 @@ void qmp_block_dirty_bitmap_remove(const char *node, const char *name,
         }
     }
 
+    bdrv_dirty_bitmap_make_anon(bitmap);
     bdrv_release_dirty_bitmap(bs, bitmap);
 }
 
@@ -2994,11 +2896,6 @@ void qmp_block_dirty_bitmap_clear(const char *node, const char *name,
                    "Bitmap '%s' is currently frozen and cannot be modified",
                    name);
         return;
-    } else if (bdrv_dirty_bitmap_qmp_locked(bitmap)) {
-        error_setg(errp,
-                   "Bitmap '%s' is currently locked and cannot be modified",
-                   name);
-        return;
     } else if (!bdrv_dirty_bitmap_enabled(bitmap)) {
         error_setg(errp,
                    "Bitmap '%s' is currently disabled and cannot be cleared",
@@ -3012,78 +2909,6 @@ void qmp_block_dirty_bitmap_clear(const char *node, const char *name,
     bdrv_clear_dirty_bitmap(bitmap, NULL);
 }
 
-void qmp_x_block_dirty_bitmap_enable(const char *node, const char *name,
-                                   Error **errp)
-{
-    BlockDriverState *bs;
-    BdrvDirtyBitmap *bitmap;
-
-    bitmap = block_dirty_bitmap_lookup(node, name, &bs, errp);
-    if (!bitmap) {
-        return;
-    }
-
-    if (bdrv_dirty_bitmap_frozen(bitmap)) {
-        error_setg(errp,
-                   "Bitmap '%s' is currently frozen and cannot be enabled",
-                   name);
-        return;
-    }
-
-    bdrv_enable_dirty_bitmap(bitmap);
-}
-
-void qmp_x_block_dirty_bitmap_disable(const char *node, const char *name,
-                                    Error **errp)
-{
-    BlockDriverState *bs;
-    BdrvDirtyBitmap *bitmap;
-
-    bitmap = block_dirty_bitmap_lookup(node, name, &bs, errp);
-    if (!bitmap) {
-        return;
-    }
-
-    if (bdrv_dirty_bitmap_frozen(bitmap)) {
-        error_setg(errp,
-                   "Bitmap '%s' is currently frozen and cannot be disabled",
-                   name);
-        return;
-    }
-
-    bdrv_disable_dirty_bitmap(bitmap);
-}
-
-void qmp_x_block_dirty_bitmap_merge(const char *node, const char *dst_name,
-                                    const char *src_name, Error **errp)
-{
-    BlockDriverState *bs;
-    BdrvDirtyBitmap *dst, *src;
-
-    dst = block_dirty_bitmap_lookup(node, dst_name, &bs, errp);
-    if (!dst) {
-        return;
-    }
-
-    if (bdrv_dirty_bitmap_frozen(dst)) {
-        error_setg(errp, "Bitmap '%s' is frozen and cannot be modified",
-                   dst_name);
-        return;
-    } else if (bdrv_dirty_bitmap_readonly(dst)) {
-        error_setg(errp, "Bitmap '%s' is readonly and cannot be modified",
-                   dst_name);
-        return;
-    }
-
-    src = bdrv_find_dirty_bitmap(bs, src_name);
-    if (!src) {
-        error_setg(errp, "Dirty bitmap '%s' not found", src_name);
-        return;
-    }
-
-    bdrv_merge_dirty_bitmap(dst, src, errp);
-}
-
 BlockDirtyBitmapSha256 *qmp_x_debug_block_dirty_bitmap_sha256(const char *node,
                                                               const char *name,
                                                               Error **errp)
@@ -3405,7 +3230,7 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
             goto out;
         }
         commit_active_start(has_job_id ? job_id : NULL, bs, base_bs,
-                            JOB_DEFAULT, speed, on_error,
+                            BLOCK_JOB_DEFAULT, speed, on_error,
                             filter_node_name, NULL, NULL, false, &local_err);
     } else {
         BlockDriverState *overlay_bs = bdrv_find_overlay(bs, top_bs);
@@ -3425,7 +3250,7 @@ out:
     aio_context_release(aio_context);
 }
 
-static BlockJob *do_drive_backup(DriveBackup *backup, JobTxn *txn,
+static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn,
                                  Error **errp)
 {
     BlockDriverState *bs;
@@ -3436,7 +3261,7 @@ static BlockJob *do_drive_backup(DriveBackup *backup, JobTxn *txn,
     AioContext *aio_context;
     QDict *options = NULL;
     Error *local_err = NULL;
-    int flags, job_flags = JOB_DEFAULT;
+    int flags;
     int64_t size;
     bool set_backing_hd = false;
 
@@ -3455,12 +3280,6 @@ static BlockJob *do_drive_backup(DriveBackup *backup, JobTxn *txn,
     if (!backup->has_job_id) {
         backup->job_id = NULL;
     }
-    if (!backup->has_auto_finalize) {
-        backup->auto_finalize = true;
-    }
-    if (!backup->has_auto_dismiss) {
-        backup->auto_dismiss = true;
-    }
     if (!backup->has_compress) {
         backup->compress = false;
     }
@@ -3551,24 +3370,12 @@ static BlockJob *do_drive_backup(DriveBackup *backup, JobTxn *txn,
             bdrv_unref(target_bs);
             goto out;
         }
-        if (bdrv_dirty_bitmap_qmp_locked(bmap)) {
-            error_setg(errp,
-                       "Bitmap '%s' is currently locked and cannot be used for "
-                       "backup", backup->bitmap);
-            goto out;
-        }
-    }
-    if (!backup->auto_finalize) {
-        job_flags |= JOB_MANUAL_FINALIZE;
-    }
-    if (!backup->auto_dismiss) {
-        job_flags |= JOB_MANUAL_DISMISS;
     }
 
     job = backup_job_create(backup->job_id, bs, target_bs, backup->speed,
                             backup->sync, bmap, backup->compress,
                             backup->on_source_error, backup->on_target_error,
-                            job_flags, NULL, NULL, txn, &local_err);
+                            BLOCK_JOB_DEFAULT, NULL, NULL, txn, &local_err);
     bdrv_unref(target_bs);
     if (local_err != NULL) {
         error_propagate(errp, local_err);
@@ -3586,7 +3393,7 @@ void qmp_drive_backup(DriveBackup *arg, Error **errp)
     BlockJob *job;
     job = do_drive_backup(arg, NULL, errp);
     if (job) {
-        job_start(&job->job);
+        block_job_start(job);
     }
 }
 
@@ -3595,7 +3402,7 @@ BlockDeviceInfoList *qmp_query_named_block_nodes(Error **errp)
     return bdrv_named_nodes_list(errp);
 }
 
-BlockJob *do_blockdev_backup(BlockdevBackup *backup, JobTxn *txn,
+BlockJob *do_blockdev_backup(BlockdevBackup *backup, BlockJobTxn *txn,
                              Error **errp)
 {
     BlockDriverState *bs;
@@ -3603,7 +3410,6 @@ BlockJob *do_blockdev_backup(BlockdevBackup *backup, JobTxn *txn,
     Error *local_err = NULL;
     AioContext *aio_context;
     BlockJob *job = NULL;
-    int job_flags = JOB_DEFAULT;
 
     if (!backup->has_speed) {
         backup->speed = 0;
@@ -3617,17 +3423,11 @@ BlockJob *do_blockdev_backup(BlockdevBackup *backup, JobTxn *txn,
     if (!backup->has_job_id) {
         backup->job_id = NULL;
     }
-    if (!backup->has_auto_finalize) {
-        backup->auto_finalize = true;
-    }
-    if (!backup->has_auto_dismiss) {
-        backup->auto_dismiss = true;
-    }
     if (!backup->has_compress) {
         backup->compress = false;
     }
 
-    bs = bdrv_lookup_bs(backup->device, backup->device, errp);
+    bs = qmp_get_root_bs(backup->device, errp);
     if (!bs) {
         return NULL;
     }
@@ -3651,16 +3451,10 @@ BlockJob *do_blockdev_backup(BlockdevBackup *backup, JobTxn *txn,
             goto out;
         }
     }
-    if (!backup->auto_finalize) {
-        job_flags |= JOB_MANUAL_FINALIZE;
-    }
-    if (!backup->auto_dismiss) {
-        job_flags |= JOB_MANUAL_DISMISS;
-    }
     job = backup_job_create(backup->job_id, bs, target_bs, backup->speed,
                             backup->sync, NULL, backup->compress,
                             backup->on_source_error, backup->on_target_error,
-                            job_flags, NULL, NULL, txn, &local_err);
+                            BLOCK_JOB_DEFAULT, NULL, NULL, txn, &local_err);
     if (local_err != NULL) {
         error_propagate(errp, local_err);
     }
@@ -3674,7 +3468,7 @@ void qmp_blockdev_backup(BlockdevBackup *arg, Error **errp)
     BlockJob *job;
     job = do_blockdev_backup(arg, NULL, errp);
     if (job) {
-        job_start(&job->job);
+        block_job_start(job);
     }
 }
 
@@ -3696,7 +3490,6 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
                                    bool has_unmap, bool unmap,
                                    bool has_filter_node_name,
                                    const char *filter_node_name,
-                                   bool has_copy_mode, MirrorCopyMode copy_mode,
                                    Error **errp)
 {
 
@@ -3721,9 +3514,6 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
     if (!has_filter_node_name) {
         filter_node_name = NULL;
     }
-    if (!has_copy_mode) {
-        copy_mode = MIRROR_COPY_MODE_BACKGROUND;
-    }
 
     if (granularity != 0 && (granularity < 512 || granularity > 1048576 * 64)) {
         error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "granularity",
@@ -3754,7 +3544,7 @@ static void blockdev_mirror_common(const char *job_id, BlockDriverState *bs,
                  has_replaces ? replaces : NULL,
                  speed, granularity, buf_size, sync, backing_mode,
                  on_source_error, on_target_error, unmap, filter_node_name,
-                 copy_mode, errp);
+                 errp);
 }
 
 void qmp_drive_mirror(DriveMirror *arg, Error **errp)
@@ -3900,7 +3690,6 @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp)
                            arg->has_on_target_error, arg->on_target_error,
                            arg->has_unmap, arg->unmap,
                            false, NULL,
-                           arg->has_copy_mode, arg->copy_mode,
                            &local_err);
     bdrv_unref(target_bs);
     error_propagate(errp, local_err);
@@ -3921,7 +3710,6 @@ void qmp_blockdev_mirror(bool has_job_id, const char *job_id,
                          BlockdevOnError on_target_error,
                          bool has_filter_node_name,
                          const char *filter_node_name,
-                         bool has_copy_mode, MirrorCopyMode copy_mode,
                          Error **errp)
 {
     BlockDriverState *bs;
@@ -3954,7 +3742,6 @@ void qmp_blockdev_mirror(bool has_job_id, const char *job_id,
                            has_on_target_error, on_target_error,
                            true, true,
                            has_filter_node_name, filter_node_name,
-                           has_copy_mode, copy_mode,
                            &local_err);
     error_propagate(errp, local_err);
 
@@ -4012,14 +3799,14 @@ void qmp_block_job_cancel(const char *device,
         force = false;
     }
 
-    if (job_user_paused(&job->job) && !force) {
+    if (block_job_user_paused(job) && !force) {
         error_setg(errp, "The block job for device '%s' is currently paused",
                    device);
         goto out;
     }
 
     trace_qmp_block_job_cancel(job);
-    job_user_cancel(&job->job, force, errp);
+    block_job_cancel(job);
 out:
     aio_context_release(aio_context);
 }
@@ -4029,12 +3816,12 @@ void qmp_block_job_pause(const char *device, Error **errp)
     AioContext *aio_context;
     BlockJob *job = find_block_job(device, &aio_context, errp);
 
-    if (!job) {
+    if (!job || block_job_user_paused(job)) {
         return;
     }
 
     trace_qmp_block_job_pause(job);
-    job_user_pause(&job->job, errp);
+    block_job_user_pause(job);
     aio_context_release(aio_context);
 }
 
@@ -4043,12 +3830,12 @@ void qmp_block_job_resume(const char *device, Error **errp)
     AioContext *aio_context;
     BlockJob *job = find_block_job(device, &aio_context, errp);
 
-    if (!job) {
+    if (!job || !block_job_user_paused(job)) {
         return;
     }
 
     trace_qmp_block_job_resume(job);
-    job_user_resume(&job->job, errp);
+    block_job_user_resume(job);
     aio_context_release(aio_context);
 }
 
@@ -4062,37 +3849,7 @@ void qmp_block_job_complete(const char *device, Error **errp)
     }
 
     trace_qmp_block_job_complete(job);
-    job_complete(&job->job, errp);
-    aio_context_release(aio_context);
-}
-
-void qmp_block_job_finalize(const char *id, Error **errp)
-{
-    AioContext *aio_context;
-    BlockJob *job = find_block_job(id, &aio_context, errp);
-
-    if (!job) {
-        return;
-    }
-
-    trace_qmp_block_job_finalize(job);
-    job_finalize(&job->job, errp);
-    aio_context_release(aio_context);
-}
-
-void qmp_block_job_dismiss(const char *id, Error **errp)
-{
-    AioContext *aio_context;
-    BlockJob *bjob = find_block_job(id, &aio_context, errp);
-    Job *job;
-
-    if (!bjob) {
-        return;
-    }
-
-    trace_qmp_block_job_dismiss(bjob);
-    job = &bjob->job;
-    job_dismiss(&job, errp);
+    block_job_complete(job, errp);
     aio_context_release(aio_context);
 }
 
@@ -4192,7 +3949,7 @@ void hmp_drive_add_node(Monitor *mon, const char *optstr)
     qdict = qemu_opts_to_qdict(opts, NULL);
 
     if (!qdict_get_try_str(qdict, "node-name")) {
-        qobject_unref(qdict);
+        QDECREF(qdict);
         error_report("'node-name' needs to be specified");
         goto out;
     }
@@ -4215,6 +3972,7 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
     QObject *obj;
     Visitor *v = qobject_output_visitor_new(&obj);
     QDict *qdict;
+    const QDictEntry *ent;
     Error *local_err = NULL;
 
     visit_type_BlockdevOptions(v, NULL, &options, &local_err);
@@ -4224,10 +3982,23 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
     }
 
     visit_complete(v, &obj);
-    qdict = qobject_to(QDict, obj);
+    qdict = qobject_to_qdict(obj);
 
     qdict_flatten(qdict);
 
+    /*
+     * Rewrite "backing": null to "backing": ""
+     * TODO Rewrite "" to null instead, and perhaps not even here
+     */
+    for (ent = qdict_first(qdict); ent; ent = qdict_next(qdict, ent)) {
+        char *dot = strrchr(ent->key, '.');
+
+        if (!strcmp(dot ? dot + 1 : ent->key, "backing")
+            && qobject_type(ent->value) == QTYPE_QNULL) {
+            qdict_put(qdict, ent->key, qstring_new());
+        }
+    }
+
     if (!qdict_get_try_str(qdict, "node-name")) {
         error_setg(errp, "'node-name' must be specified for the root node");
         goto fail;
@@ -4409,49 +4180,6 @@ void qmp_x_blockdev_set_iothread(const char *node_name, StrOrNull *iothread,
     aio_context_release(old_context);
 }
 
-void qmp_x_block_latency_histogram_set(
-    const char *device,
-    bool has_boundaries, uint64List *boundaries,
-    bool has_boundaries_read, uint64List *boundaries_read,
-    bool has_boundaries_write, uint64List *boundaries_write,
-    bool has_boundaries_flush, uint64List *boundaries_flush,
-    Error **errp)
-{
-    BlockBackend *blk = blk_by_name(device);
-    BlockAcctStats *stats;
-
-    if (!blk) {
-        error_setg(errp, "Device '%s' not found", device);
-        return;
-    }
-    stats = blk_get_stats(blk);
-
-    if (!has_boundaries && !has_boundaries_read && !has_boundaries_write &&
-        !has_boundaries_flush)
-    {
-        block_latency_histograms_clear(stats);
-        return;
-    }
-
-    if (has_boundaries || has_boundaries_read) {
-        block_latency_histogram_set(
-            stats, BLOCK_ACCT_READ,
-            has_boundaries_read ? boundaries_read : boundaries);
-    }
-
-    if (has_boundaries || has_boundaries_write) {
-        block_latency_histogram_set(
-            stats, BLOCK_ACCT_WRITE,
-            has_boundaries_write ? boundaries_write : boundaries);
-    }
-
-    if (has_boundaries || has_boundaries_flush) {
-        block_latency_histogram_set(
-            stats, BLOCK_ACCT_FLUSH,
-            has_boundaries_flush ? boundaries_flush : boundaries);
-    }
-}
-
 QemuOptsList qemu_common_drive_opts = {
     .name = "drive",
     .head = QTAILQ_HEAD_INITIALIZER(qemu_common_drive_opts.head),

bsd-user/main.c

@@ -17,7 +17,6 @@
  *  along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 #include "qemu/osdep.h"
-#include "qemu/units.h"
 #include "qemu-version.h"
 #include <machine/trap.h>
 
@@ -650,7 +649,7 @@ void cpu_loop(CPUSPARCState *env)
 
 static void usage(void)
 {
-    printf("qemu-" TARGET_NAME " version " QEMU_FULL_VERSION
+    printf("qemu-" TARGET_NAME " version " QEMU_VERSION QEMU_PKGVERSION
            "\n" QEMU_COPYRIGHT "\n"
            "usage: qemu-" TARGET_NAME " [options] program [arguments...]\n"
            "BSD CPU emulator (compiled for %s emulation)\n"
@@ -724,7 +723,6 @@ int main(int argc, char **argv)
 {
     const char *filename;
     const char *cpu_model;
-    const char *cpu_type;
     const char *log_file = NULL;
     const char *log_mask = NULL;
     struct target_pt_regs regs1, *regs = &regs1;
@@ -796,9 +794,9 @@ int main(int argc, char **argv)
             if (x86_stack_size <= 0)
                 usage();
             if (*r == 'M')
-                x86_stack_size *= MiB;
+                x86_stack_size *= 1024 * 1024;
             else if (*r == 'k' || *r == 'K')
-                x86_stack_size *= KiB;
+                x86_stack_size *= 1024;
         } else if (!strcmp(r, "L")) {
             interp_prefix = argv[optind++];
         } else if (!strcmp(r, "p")) {
@@ -899,12 +897,10 @@ int main(int argc, char **argv)
         cpu_model = "any";
 #endif
     }
-
-    /* init tcg before creating CPUs and to get qemu_host_page_size */
     tcg_exec_init(0);
-
-    cpu_type = parse_cpu_model(cpu_model);
-    cpu = cpu_create(cpu_type);
+    /* NOTE: we need to init the CPU at this stage to get
+       qemu_host_page_size */
+    cpu = cpu_init(cpu_model);
     env = cpu->env_ptr;
 #if defined(TARGET_SPARC) || defined(TARGET_PPC)
     cpu_reset(cpu);
@@ -919,7 +915,7 @@ int main(int argc, char **argv)
     envlist_free(envlist);
 
     /*
-     * Now that page sizes are configured in tcg_exec_init() we can do
+     * Now that page sizes are configured in cpu_init() we can do
      * proper page alignment for guest_base.
      */
     guest_base = HOST_PAGE_ALIGN(guest_base);

bsd-user/mmap.c

@@ -21,7 +21,6 @@
 #include "qemu.h"
 #include "qemu-common.h"
 #include "bsd-mman.h"
-#include "exec/exec-all.h"
 
 //#define DEBUG_MMAP
 

bsd-user/qemu.h

@@ -19,6 +19,7 @@
 
 
 #include "cpu.h"
+#include "exec/exec-all.h"
 #include "exec/cpu_ldst.h"
 
 #undef DEBUG_REMAP