MAINTAINERS: Add Python scripts

Cleber and I are volunteering to review and queue patches for the
Python scripts and modules in scripts/.

I'm setting "M: Odd fixes" because not all scripts are actively
maintained.

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <20170915230744.22942-1-ehabkost@redhat.com>
[ehabkost: add tests/*.py too]
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>

.editorconfig

@@ -0,0 +1,15 @@
+# http://editorconfig.org
+root = true
+
+[*]
+end_of_line = lf
+insert_final_newline = true
+charset = utf-8
+
+[Makefile*]
+indent_style = tab
+indent_size = 8
+
+[*.{c,h}]
+indent_style = space
+indent_size = 4

.gitignore

@@ -116,6 +116,8 @@ tags
 TAGS
 docker-src.*
 *~
+*.ast_raw
+*.depend_raw
 trace.h
 trace.c
 trace-ust.h

.gitmodules

@@ -22,9 +22,6 @@
 [submodule "roms/sgabios"]
 	path = roms/sgabios
 	url = git://git.qemu-project.org/sgabios.git
-[submodule "pixman"]
-	path = pixman
-	url = git://anongit.freedesktop.org/pixman
 [submodule "dtc"]
 	path = dtc
 	url = git://git.qemu-project.org/dtc.git

.shippable.yml

@@ -5,15 +5,28 @@ env:
   global:
     - LC_ALL=C
   matrix:
+    - IMAGE=debian-amd64
+      TARGET_LIST=x86_64-softmmu,x86_64-linux-user
+    - IMAGE=debian-win32-cross
+      TARGET_LIST=arm-softmmu,i386-softmmu,lm32-softmmu
+    - IMAGE=debian-win64-cross
+      TARGET_LIST=aarch64-softmmu,sparc64-softmmu,x86_64-softmmu
+    - IMAGE=debian-armel-cross
+      TARGET_LIST=arm-softmmu,arm-linux-user,armeb-linux-user
     - IMAGE=debian-armhf-cross
       TARGET_LIST=arm-softmmu,arm-linux-user,armeb-linux-user
     - IMAGE=debian-arm64-cross
       TARGET_LIST=aarch64-softmmu,aarch64-linux-user
     - IMAGE=debian-s390x-cross
       TARGET_LIST=s390x-softmmu,s390x-linux-user
-    # mips64el-softmmu disabled due to libfdt problem
-    - IMAGE=debian-mipsel-cross
-      TARGET_LIST=mipsel-softmmu,mipsel-linux-user,mips64el-linux-user
+    - IMAGE=debian-mips-cross
+      TARGET_LIST=mips-softmmu,mipsel-linux-user
+    - IMAGE=debian-mips64el-cross
+      TARGET_LIST=mips64el-softmmu,mips64el-linux-user
+    - IMAGE=debian-powerpc-cross
+      TARGET_LIST=ppc-softmmu,ppcemb-softmmu,ppc-linux-user
+    - IMAGE=debian-ppc64el-cross
+      TARGET_LIST=ppc64-softmmu,ppc64-linux-user,ppc64abi32-linux-user
 build:
   pre_ci:
     - make docker-image-${IMAGE} V=1

.travis.yml

@@ -46,6 +46,7 @@ notifications:
 env:
   global:
     - TEST_CMD="make check"
+    - MAKEFLAGS="-j3"
   matrix:
     - CONFIG=""
     - CONFIG="--enable-debug --enable-debug-tcg --enable-trace-backends=log"
@@ -64,7 +65,7 @@ before_install:
 before_script:
   - ./configure ${CONFIG}
 script:
-  - make -j3 && ${TEST_CMD}
+  - make ${MAKEFLAGS} && ${TEST_CMD}
 matrix:
   include:
     # Test with CLang for compile portability

CODING_STYLE

@@ -123,3 +123,38 @@ 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.
+
+8. trace-events style
+
+8.1 0x prefix
+
+In trace-events files, use a '0x' prefix to specify hex numbers, as in:
+
+some_trace(unsigned x, uint64_t y) "x 0x%x y 0x" PRIx64
+
+An exception is made for groups of numbers that are hexadecimal by
+convention and separated by the symbols '.', '/', ':', or ' ' (such as
+PCI bus id):
+
+another_trace(int cssid, int ssid, int dev_num) "bus id: %x.%x.%04x"
+
+However, you can use '0x' for such groups if you want. Anyway, be sure that
+it is obvious that numbers are in hex, ex.:
+
+data_dump(uint8_t c1, uint8_t c2, uint8_t c3) "bytes (in hex): %02x %02x %02x"
+
+Rationale: hex numbers are hard to read in logs when there is no 0x prefix,
+especially when (occasionally) the representation doesn't contain any letters
+and especially in one line with other decimal numbers. Number groups are allowed
+to not use '0x' because for some things notations like %x.%x.%x are used not
+only in Qemu. Also dumping raw data bytes with '0x' is less readable.
+
+8.2 '#' printf flag
+
+Do not use printf flag '#', like '%#x'.
+
+Rationale: there are two ways to add a '0x' prefix to printed number: '0x%...'
+and '%#...'. For consistency the only one way should be used. Arguments for
+'0x%' are:
+ - it is more popular
+ - '%#' omits the 0x for the value 0 which makes output inconsistent

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.

MAINTAINERS

@@ -86,7 +86,6 @@ M: Richard Henderson <rth@twiddle.net>
 S: Maintained
 F: cpus.c
 F: exec.c
-F: softmmu_template.h
 F: accel/tcg/
 F: include/exec/cpu*.h
 F: include/exec/exec-all.h
@@ -250,6 +249,7 @@ S: Maintained
 F: target/i386/
 F: hw/i386/
 F: disas/i386.c
+T: git git://github.com/ehabkost/qemu.git x86-next
 
 Xtensa
 M: Max Filippov <jcmvbkbc@gmail.com>
@@ -353,7 +353,7 @@ NETBSD
 L: qemu-devel@nongnu.org
 M: Kamil Rytarowski <kamil@netbsd.org>
 S: Maintained
-K: (?i)NetBSD
+K: ^Subject:.*(?i)NetBSD
 
 W32, W64
 L: qemu-devel@nongnu.org
@@ -790,6 +790,7 @@ M: Christian Borntraeger <borntraeger@de.ibm.com>
 M: Alexander Graf <agraf@suse.de>
 S: Supported
 F: hw/char/sclp*.[hc]
+F: hw/char/terminal3270.c
 F: hw/s390x/
 F: include/hw/s390x/
 F: pc-bios/s390-ccw/
@@ -858,6 +859,7 @@ S: Supported
 F: hw/core/machine.c
 F: hw/core/null-machine.c
 F: include/hw/boards.h
+T: git git://github.com/ehabkost/qemu.git machine-next
 
 Xtensa Machines
 ---------------
@@ -969,7 +971,9 @@ SCSI
 M: Paolo Bonzini <pbonzini@redhat.com>
 S: Supported
 F: include/hw/scsi/*
+F: include/scsi/*
 F: hw/scsi/*
+F: util/scsi*
 F: tests/virtio-scsi-test.c
 T: git git://github.com/bonzini/qemu.git scsi-next
 
@@ -999,6 +1003,7 @@ F: docs/usb2.txt
 F: docs/usb-storage.txt
 F: include/hw/usb.h
 F: include/hw/usb/
+F: default-configs/usb.mak
 
 USB (serial adapter)
 M: Gerd Hoffmann <kraxel@redhat.com>
@@ -1101,11 +1106,12 @@ F: hw/block/nvme*
 F: tests/nvme-test.c
 
 megasas
-M: Hannes Reinecke <hare@suse.de>
+M: Hannes Reinecke <hare@suse.com>
 L: qemu-block@nongnu.org
 S: Supported
 F: hw/scsi/megasas.c
 F: hw/scsi/mfi.h
+F: tests/megasas-test.c
 
 Network packet abstractions
 M: Dmitry Fleytman <dmitry@daynix.com>
@@ -1129,7 +1135,7 @@ F: tests/rocker/
 F: docs/specs/rocker.txt
 
 NVDIMM
-M: Xiao Guangrong <guangrong.xiao@linux.intel.com>
+M: Xiao Guangrong <xiaoguangrong.eric@gmail.com>
 S: Maintained
 F: hw/acpi/nvdimm.c
 F: hw/mem/nvdimm.c
@@ -1213,6 +1219,13 @@ F: migration/block*
 F: include/block/aio.h
 T: git git://github.com/stefanha/qemu.git block
 
+Block SCSI subsystem
+M: Paolo Bonzini <pbonzini@redhat.com>
+L: qemu-block@nongnu.org
+S: Supported
+F: include/scsi/*
+F: scsi/*
+
 Block Jobs
 M: Jeff Cody <jcody@redhat.com>
 L: qemu-block@nongnu.org
@@ -1231,6 +1244,7 @@ S: Supported
 F: blockdev.c
 F: block/qapi.c
 F: qapi/block*.json
+F: qapi/transaction.json
 T: git git://repo.or.cz/qemu/armbru.git block-next
 
 Dirty Bitmaps
@@ -1253,6 +1267,7 @@ M: Marc-André Lureau <marcandre.lureau@redhat.com>
 S: Maintained
 F: chardev/
 F: include/chardev/
+F: qapi/char.json
 
 Character Devices (Braille)
 M: Samuel Thibault <samuel.thibault@ens-lyon.org>
@@ -1319,12 +1334,14 @@ F: include/ui/spice-display.h
 F: ui/spice-*.c
 F: audio/spiceaudio.c
 F: hw/display/qxl*
+F: qapi/ui.json
 
 Graphics
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Odd Fixes
 F: ui/
 F: include/ui/
+F: qapi/ui.json
 
 Cocoa graphics
 M: Peter Maydell <peter.maydell@linaro.org>
@@ -1338,6 +1355,7 @@ F: cpus.c
 F: util/main-loop.c
 F: util/qemu-timer.c
 F: vl.c
+F: qapi/run-state.json
 
 Human Monitor (HMP)
 M: Dr. David Alan Gilbert <dgilbert@redhat.com>
@@ -1346,6 +1364,7 @@ F: monitor.c
 F: hmp.[ch]
 F: hmp-commands*.hx
 F: include/monitor/hmp-target.h
+F: tests/test-hmp.c
 
 Network device backends
 M: Jason Wang <jasowang@redhat.com>
@@ -1353,6 +1372,7 @@ S: Maintained
 F: net/
 F: include/net/
 T: git git://github.com/jasowang/qemu.git net
+F: qapi/net.json
 
 Netmap network backend
 M: Luigi Rizzo <rizzo@iet.unipi.it>
@@ -1367,7 +1387,7 @@ M: Eduardo Habkost <ehabkost@redhat.com>
 S: Maintained
 F: numa.c
 F: include/sysemu/numa.h
-T: git git://github.com/ehabkost/qemu.git numa
+T: git git://github.com/ehabkost/qemu.git machine-next
 
 Host Memory Backends
 M: Eduardo Habkost <ehabkost@redhat.com>
@@ -1375,6 +1395,7 @@ M: Igor Mammedov <imammedo@redhat.com>
 S: Maintained
 F: backends/hostmem*.c
 F: include/sysemu/hostmem.h
+T: git git://github.com/ehabkost/qemu.git machine-next
 
 Cryptodev Backends
 M: Gonglei <arei.gonglei@huawei.com>
@@ -1382,6 +1403,14 @@ S: Maintained
 F: include/sysemu/cryptodev*.h
 F: backends/cryptodev*.c
 
+Python scripts
+M: Eduardo Habkost <ehabkost@redhat.com>
+M: Cleber Rosa <crosa@redhat.com>
+S: Odd fixes
+F: scripts/qmp/*
+F: scripts/*.py
+F: tests/*.py
+
 QAPI
 M: Markus Armbruster <armbru@redhat.com>
 M: Michael Roth <mdroth@linux.vnet.ibm.com>
@@ -1479,6 +1508,14 @@ F: scripts/tracetool/
 F: docs/tracing.txt
 T: git git://github.com/stefanha/qemu.git tracing
 
+TPM
+S: Orphan
+F: tpm.c
+F: hw/tpm/*
+F: include/hw/acpi/tpm.h
+F: include/sysemu/tpm*
+F: qapi/tpm.json
+
 Checkpatch
 S: Odd Fixes
 F: scripts/checkpatch.pl
@@ -1492,6 +1529,7 @@ F: migration/
 F: scripts/vmstate-static-checker.py
 F: tests/vmstate-static-checker-data/
 F: docs/migration.txt
+F: qapi/migration.json
 
 Seccomp
 M: Eduardo Otubo <otubo@redhat.com>
@@ -1534,6 +1572,7 @@ M: Paolo Bonzini <pbonzini@redhat.com>
 S: Maintained
 F: include/qemu/sockets.h
 F: util/qemu-sockets.c
+F: qapi/sockets.json
 
 Throttling infrastructure
 M: Alberto Garcia <berto@igalia.com>
@@ -1560,7 +1599,7 @@ F: include/migration/failover.h
 F: docs/COLO-FT.txt
 
 COLO Proxy
-M: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
+M: Zhang Chen <zhangckid@gmail.com>
 M: Li Zhijian <lizhijian@cn.fujitsu.com>
 S: Supported
 F: docs/colo-proxy.txt
@@ -1586,8 +1625,7 @@ Overall
 M: Riku Voipio <riku.voipio@iki.fi>
 S: Maintained
 F: thunk.c
-F: user-exec.c
-F: user-exec-stub.c
+F: accel/tcg/user-exec*.c
 
 BSD user
 S: Orphan
@@ -1630,12 +1668,6 @@ S: Maintained
 F: tcg/i386/
 F: disas/i386.c
 
-IA64 target
-M: Aurelien Jarno <aurelien@aurel32.net>
-S: Maintained
-F: tcg/ia64/
-F: disas/ia64.c
-
 MIPS target
 M: Aurelien Jarno <aurelien@aurel32.net>
 S: Maintained

Makefile

@@ -281,9 +281,7 @@ dummy := $(call unnest-vars,, \
                 common-obj-m \
                 trace-obj-y)
 
-ifneq ($(wildcard config-host.mak),)
 include $(SRC_PATH)/tests/Makefile.include
-endif
 
 all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all modules
 
@@ -327,15 +325,6 @@ $(SOFTMMU_SUBDIR_RULES): config-all-devices.mak
 subdir-%:
 	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C $* V="$(V)" TARGET_DIR="$*/" all,)
 
-subdir-pixman: pixman/Makefile
-	$(call quiet-command,$(MAKE) $(SUBDIR_MAKEFLAGS) -C pixman V="$(V)" all,)
-
-pixman/Makefile: $(SRC_PATH)/pixman/configure
-	(cd pixman; CFLAGS="$(CFLAGS) -fPIC $(extra_cflags) $(extra_ldflags)" $(SRC_PATH)/pixman/configure $(AUTOCONF_HOST) --disable-gtk --disable-shared --enable-static)
-
-$(SRC_PATH)/pixman/configure:
-	(cd $(SRC_PATH)/pixman; autoreconf -v --install)
-
 DTC_MAKE_ARGS=-I$(SRC_PATH)/dtc VPATH=$(SRC_PATH)/dtc -C dtc V="$(V)" LIBFDT_srcdir=$(SRC_PATH)/dtc/libfdt
 DTC_CFLAGS=$(CFLAGS) $(QEMU_CFLAGS)
 DTC_CPPFLAGS=-I$(BUILD_DIR)/dtc -I$(SRC_PATH)/dtc -I$(SRC_PATH)/dtc/libfdt
@@ -346,7 +335,7 @@ subdir-dtc:dtc/libfdt dtc/tests
 dtc/%:
 	mkdir -p $@
 
-$(SUBDIR_RULES): libqemuutil.a libqemustub.a $(common-obj-y) $(chardev-obj-y) \
+$(SUBDIR_RULES): libqemuutil.a $(common-obj-y) $(chardev-obj-y) \
 	$(qom-obj-y) $(crypto-aes-obj-$(CONFIG_USER_ONLY))
 
 ROMSUBDIR_RULES=$(patsubst %,romsubdir-%, $(ROMS))
@@ -366,12 +355,11 @@ Makefile: $(version-obj-y)
 ######################################################################
 # Build libraries
 
-libqemustub.a: $(stub-obj-y)
-libqemuutil.a: $(util-obj-y) $(trace-obj-y)
+libqemuutil.a: $(util-obj-y) $(trace-obj-y) $(stub-obj-y)
 
 ######################################################################
 
-COMMON_LDADDS = libqemuutil.a libqemustub.a
+COMMON_LDADDS = libqemuutil.a
 
 qemu-img.o: qemu-img-cmds.h
 
@@ -412,9 +400,18 @@ $(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
 
 qapi-modules = $(SRC_PATH)/qapi-schema.json $(SRC_PATH)/qapi/common.json \
                $(SRC_PATH)/qapi/block.json $(SRC_PATH)/qapi/block-core.json \
-               $(SRC_PATH)/qapi/event.json $(SRC_PATH)/qapi/introspect.json \
-               $(SRC_PATH)/qapi/crypto.json $(SRC_PATH)/qapi/rocker.json \
-               $(SRC_PATH)/qapi/trace.json
+               $(SRC_PATH)/qapi/char.json \
+               $(SRC_PATH)/qapi/crypto.json \
+               $(SRC_PATH)/qapi/introspect.json \
+               $(SRC_PATH)/qapi/migration.json \
+               $(SRC_PATH)/qapi/net.json \
+               $(SRC_PATH)/qapi/rocker.json \
+               $(SRC_PATH)/qapi/run-state.json \
+               $(SRC_PATH)/qapi/sockets.json \
+               $(SRC_PATH)/qapi/tpm.json \
+               $(SRC_PATH)/qapi/trace.json \
+               $(SRC_PATH)/qapi/transaction.json \
+               $(SRC_PATH)/qapi/ui.json
 
 qapi-types.c qapi-types.h :\
 $(qapi-modules) $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
@@ -443,7 +440,7 @@ $(qapi-modules) $(SRC_PATH)/scripts/qapi-introspect.py $(qapi-py)
 		"GEN","$@")
 
 QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
-$(qga-obj-y) qemu-ga.o: $(QGALIB_GEN)
+$(qga-obj-y): $(QGALIB_GEN)
 
 qemu-ga$(EXESUF): $(qga-obj-y) $(COMMON_LDADDS)
 	$(call LINK, $^)
@@ -470,10 +467,12 @@ ifneq ($(EXESUF),)
 qemu-ga: qemu-ga$(EXESUF) $(QGA_VSS_PROVIDER) $(QEMU_GA_MSI)
 endif
 
+ifdef CONFIG_IVSHMEM
 ivshmem-client$(EXESUF): $(ivshmem-client-obj-y) $(COMMON_LDADDS)
 	$(call LINK, $^)
 ivshmem-server$(EXESUF): $(ivshmem-server-obj-y) $(COMMON_LDADDS)
 	$(call LINK, $^)
+endif
 vhost-user-scsi$(EXESUF): $(vhost-user-scsi-obj-y)
 	$(call LINK, $^)
 
@@ -532,7 +531,6 @@ distclean: clean
 	rm -rf $$d || exit 1 ; \
         done
 	rm -Rf .sdk
-	if test -f pixman/config.log; then $(MAKE) -C pixman distclean; fi
 	if test -f dtc/version_gen.h; then $(MAKE) $(DTC_MAKE_ARGS) clean; fi
 
 KEYMAPS=da     en-gb  et  fr     fr-ch  is  lt  modifiers  no  pt-br  sv \

Makefile.objs

@@ -11,7 +11,7 @@ chardev-obj-y = chardev/
 
 block-obj-y += nbd/
 block-obj-y += block.o blockjob.o
-block-obj-y += block/
+block-obj-y += block/ scsi/
 block-obj-y += qemu-io-cmds.o
 block-obj-$(CONFIG_REPLICATION) += replication.o
 
@@ -70,6 +70,8 @@ common-obj-y += backends/
 common-obj-y += chardev/
 
 common-obj-$(CONFIG_SECCOMP) += qemu-seccomp.o
+qemu-seccomp.o-cflags := $(SECCOMP_CFLAGS)
+qemu-seccomp.o-libs := $(SECCOMP_LIBS)
 
 common-obj-$(CONFIG_FDT) += device_tree.o
 
@@ -107,8 +109,8 @@ qga-vss-dll-obj-y = qga/
 
 ######################################################################
 # contrib
-ivshmem-client-obj-y = contrib/ivshmem-client/
-ivshmem-server-obj-y = contrib/ivshmem-server/
+ivshmem-client-obj-$(CONFIG_IVSHMEM) = contrib/ivshmem-client/
+ivshmem-server-obj-$(CONFIG_IVSHMEM) = contrib/ivshmem-server/
 libvhost-user-obj-y = contrib/libvhost-user/
 vhost-user-scsi.o-cflags := $(LIBISCSI_CFLAGS)
 vhost-user-scsi.o-libs := $(LIBISCSI_LIBS)
@@ -153,6 +155,7 @@ trace-events-subdirs += hw/acpi
 trace-events-subdirs += hw/arm
 trace-events-subdirs += hw/alpha
 trace-events-subdirs += hw/xen
+trace-events-subdirs += hw/ide
 trace-events-subdirs += ui
 trace-events-subdirs += audio
 trace-events-subdirs += net

Makefile.target

@@ -48,7 +48,10 @@ else
 TARGET_TYPE=system
 endif
 
-$(QEMU_PROG).stp-installed: $(BUILD_DIR)/trace-events-all
+tracetool-y = $(SRC_PATH)/scripts/tracetool.py
+tracetool-y += $(shell find $(SRC_PATH)/scripts/tracetool -name "*.py")
+
+$(QEMU_PROG).stp-installed: $(BUILD_DIR)/trace-events-all $(tracetool-y)
 	$(call quiet-command,$(TRACETOOL) \
 		--group=all \
 		--format=stap \
@@ -58,7 +61,7 @@ $(QEMU_PROG).stp-installed: $(BUILD_DIR)/trace-events-all
 		--target-type=$(TARGET_TYPE) \
 		$< > $@,"GEN","$(TARGET_DIR)$(QEMU_PROG).stp-installed")
 
-$(QEMU_PROG).stp: $(BUILD_DIR)/trace-events-all
+$(QEMU_PROG).stp: $(BUILD_DIR)/trace-events-all $(tracetool-y)
 	$(call quiet-command,$(TRACETOOL) \
 		--group=all \
 		--format=stap \
@@ -68,7 +71,7 @@ $(QEMU_PROG).stp: $(BUILD_DIR)/trace-events-all
 		--target-type=$(TARGET_TYPE) \
 		$< > $@,"GEN","$(TARGET_DIR)$(QEMU_PROG).stp")
 
-$(QEMU_PROG)-simpletrace.stp: $(BUILD_DIR)/trace-events-all
+$(QEMU_PROG)-simpletrace.stp: $(BUILD_DIR)/trace-events-all $(tracetool-y)
 	$(call quiet-command,$(TRACETOOL) \
 		--group=all \
 		--format=simpletrace-stap \
@@ -91,14 +94,13 @@ all: $(PROGS) stap
 obj-y += exec.o
 obj-y += accel/
 obj-$(CONFIG_TCG) += tcg/tcg.o tcg/tcg-op.o tcg/optimize.o
-obj-$(CONFIG_TCG) += tcg/tcg-common.o tcg/tcg-runtime.o
+obj-$(CONFIG_TCG) += tcg/tcg-common.o
 obj-$(CONFIG_TCG_INTERPRETER) += tcg/tci.o
 obj-$(CONFIG_TCG_INTERPRETER) += disas/tci.o
 obj-y += fpu/softfloat.o
 obj-y += target/$(TARGET_BASE_ARCH)/
 obj-y += disas.o
 obj-$(call notempty,$(TARGET_XML_FILES)) += gdbstub-xml.o
-obj-$(call lnot,$(CONFIG_HAX)) += hax-stub.o
 
 obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decContext.o
 obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decNumber.o
@@ -116,7 +118,7 @@ QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) \
              -I$(SRC_PATH)/linux-user
 
 obj-y += linux-user/
-obj-y += gdbstub.o thunk.o user-exec.o user-exec-stub.o
+obj-y += gdbstub.o thunk.o
 
 endif #CONFIG_LINUX_USER
 
@@ -129,7 +131,7 @@ QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR) \
 			 -I$(SRC_PATH)/bsd-user/$(HOST_VARIANT_DIR)
 
 obj-y += bsd-user/
-obj-y += gdbstub.o user-exec.o user-exec-stub.o
+obj-y += gdbstub.o
 
 endif #CONFIG_BSD_USER
 
@@ -190,7 +192,7 @@ all-obj-$(CONFIG_SOFTMMU) += $(io-obj-y)
 
 $(QEMU_PROG_BUILD): config-devices.mak
 
-COMMON_LDADDS = ../libqemuutil.a ../libqemustub.a
+COMMON_LDADDS = ../libqemuutil.a
 
 # build either PROG or PROGW
 $(QEMU_PROG_BUILD): $(all-obj-y) $(COMMON_LDADDS)

VERSION

@@ -1 +1 @@
-2.9.50
+2.10.50

accel/accel.c

@@ -33,6 +33,7 @@
 #include "sysemu/qtest.h"
 #include "hw/xen/xen.h"
 #include "qom/object.h"
+#include "qemu/error-report.h"
 
 static const TypeInfo accel_type = {
     .name = TYPE_ACCEL,
@@ -69,19 +70,20 @@ static int accel_init_machine(AccelClass *acc, MachineState *ms)
 
 void configure_accelerator(MachineState *ms)
 {
-    const char *p;
+    const char *accel, *p;
     char buf[10];
     int ret;
     bool accel_initialised = false;
     bool init_failed = false;
     AccelClass *acc = NULL;
 
-    p = qemu_opt_get(qemu_get_machine_opts(), "accel");
-    if (p == NULL) {
+    accel = qemu_opt_get(qemu_get_machine_opts(), "accel");
+    if (accel == NULL) {
         /* Use the default "accelerator", tcg */
-        p = "tcg";
+        accel = "tcg";
     }
 
+    p = accel;
     while (!accel_initialised && *p != '\0') {
         if (*p == ':') {
             p++;
@@ -89,7 +91,6 @@ void configure_accelerator(MachineState *ms)
         p = get_opt_name(buf, sizeof(buf), p, ':');
         acc = accel_find(buf);
         if (!acc) {
-            fprintf(stderr, "\"%s\" accelerator not found.\n", buf);
             continue;
         }
         if (acc->available && !acc->available()) {
@@ -100,9 +101,8 @@ void configure_accelerator(MachineState *ms)
         ret = accel_init_machine(acc, ms);
         if (ret < 0) {
             init_failed = true;
-            fprintf(stderr, "failed to initialize %s: %s\n",
-                    acc->name,
-                    strerror(-ret));
+            error_report("failed to initialize %s: %s",
+                         acc->name, strerror(-ret));
         } else {
             accel_initialised = true;
         }
@@ -110,13 +110,13 @@ void configure_accelerator(MachineState *ms)
 
     if (!accel_initialised) {
         if (!init_failed) {
-            fprintf(stderr, "No accelerator found!\n");
+            error_report("-machine accel=%s: No accelerator found", accel);
         }
         exit(1);
     }
 
     if (init_failed) {
-        fprintf(stderr, "Back to %s accelerator.\n", acc->name);
+        error_report("Back to %s accelerator", acc->name);
     }
 }
 

accel/kvm/kvm-all.c

@@ -79,7 +79,6 @@ struct KVMState
     int coalesced_mmio;
     struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
     bool coalesced_flush_in_progress;
-    int broken_set_mem_region;
     int vcpu_events;
     int robust_singlestep;
     int debugregs;
@@ -127,6 +126,7 @@ static bool kvm_immediate_exit;
 static const KVMCapabilityInfo kvm_required_capabilites[] = {
     KVM_CAP_INFO(USER_MEMORY),
     KVM_CAP_INFO(DESTROY_MEMORY_REGION_WORKS),
+    KVM_CAP_INFO(JOIN_MEMORY_REGIONS_WORKS),
     KVM_CAP_LAST_INFO
 };
 
@@ -172,7 +172,7 @@ static KVMSlot *kvm_alloc_slot(KVMMemoryListener *kml)
 
 static KVMSlot *kvm_lookup_matching_slot(KVMMemoryListener *kml,
                                          hwaddr start_addr,
-                                         hwaddr end_addr)
+                                         hwaddr size)
 {
     KVMState *s = kvm_state;
     int i;
@@ -180,8 +180,7 @@ static KVMSlot *kvm_lookup_matching_slot(KVMMemoryListener *kml,
     for (i = 0; i < s->nr_slots; i++) {
         KVMSlot *mem = &kml->slots[i];
 
-        if (start_addr == mem->start_addr &&
-            end_addr == mem->start_addr + mem->memory_size) {
+        if (start_addr == mem->start_addr && size == mem->memory_size) {
             return mem;
         }
     }
@@ -190,31 +189,33 @@ static KVMSlot *kvm_lookup_matching_slot(KVMMemoryListener *kml,
 }
 
 /*
- * Find overlapping slot with lowest start address
+ * Calculate and align the start address and the size of the section.
+ * Return the size. If the size is 0, the aligned section is empty.
  */
-static KVMSlot *kvm_lookup_overlapping_slot(KVMMemoryListener *kml,
-                                            hwaddr start_addr,
-                                            hwaddr end_addr)
+static hwaddr kvm_align_section(MemoryRegionSection *section,
+                                hwaddr *start)
 {
-    KVMState *s = kvm_state;
-    KVMSlot *found = NULL;
-    int i;
+    hwaddr size = int128_get64(section->size);
+    hwaddr delta;
 
-    for (i = 0; i < s->nr_slots; i++) {
-        KVMSlot *mem = &kml->slots[i];
+    *start = section->offset_within_address_space;
 
-        if (mem->memory_size == 0 ||
-            (found && found->start_addr < mem->start_addr)) {
-            continue;
-        }
-
-        if (end_addr > mem->start_addr &&
-            start_addr < mem->start_addr + mem->memory_size) {
-            found = mem;
-        }
+    /* kvm works in page size chunks, but the function may be called
+       with sub-page size and unaligned start address. Pad the start
+       address to next and truncate size to previous page boundary. */
+    delta = qemu_real_host_page_size - (*start & ~qemu_real_host_page_mask);
+    delta &= ~qemu_real_host_page_mask;
+    *start += delta;
+    if (delta > size) {
+        return 0;
+    }
+    size -= delta;
+    size &= qemu_real_host_page_mask;
+    if (*start & ~qemu_real_host_page_mask) {
+        return 0;
     }
 
-    return found;
+    return size;
 }
 
 int kvm_physical_memory_addr_from_host(KVMState *s, void *ram,
@@ -382,15 +383,21 @@ static int kvm_slot_update_flags(KVMMemoryListener *kml, KVMSlot *mem,
 static int kvm_section_update_flags(KVMMemoryListener *kml,
                                     MemoryRegionSection *section)
 {
-    hwaddr phys_addr = section->offset_within_address_space;
-    ram_addr_t size = int128_get64(section->size);
-    KVMSlot *mem = kvm_lookup_matching_slot(kml, phys_addr, phys_addr + size);
+    hwaddr start_addr, size;
+    KVMSlot *mem;
 
-    if (mem == NULL)  {
+    size = kvm_align_section(section, &start_addr);
+    if (!size) {
         return 0;
-    } else {
-        return kvm_slot_update_flags(kml, mem, section->mr);
     }
+
+    mem = kvm_lookup_matching_slot(kml, start_addr, size);
+    if (!mem) {
+        fprintf(stderr, "%s: error finding slot\n", __func__);
+        abort();
+    }
+
+    return kvm_slot_update_flags(kml, mem, section->mr);
 }
 
 static void kvm_log_start(MemoryListener *listener,
@@ -454,18 +461,16 @@ static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml,
                                           MemoryRegionSection *section)
 {
     KVMState *s = kvm_state;
-    unsigned long size, allocated_size = 0;
     struct kvm_dirty_log d = {};
     KVMSlot *mem;
-    int ret = 0;
-    hwaddr start_addr = section->offset_within_address_space;
-    hwaddr end_addr = start_addr + int128_get64(section->size);
+    hwaddr start_addr, size;
 
-    d.dirty_bitmap = NULL;
-    while (start_addr < end_addr) {
-        mem = kvm_lookup_overlapping_slot(kml, start_addr, end_addr);
-        if (mem == NULL) {
-            break;
+    size = kvm_align_section(section, &start_addr);
+    if (size) {
+        mem = kvm_lookup_matching_slot(kml, start_addr, size);
+        if (!mem) {
+            fprintf(stderr, "%s: error finding slot\n", __func__);
+            abort();
         }
 
         /* XXX bad kernel interface alert
@@ -482,27 +487,20 @@ static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml,
          */
         size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS),
                      /*HOST_LONG_BITS*/ 64) / 8;
-        if (!d.dirty_bitmap) {
-            d.dirty_bitmap = g_malloc(size);
-        } else if (size > allocated_size) {
-            d.dirty_bitmap = g_realloc(d.dirty_bitmap, size);
-        }
-        allocated_size = size;
-        memset(d.dirty_bitmap, 0, allocated_size);
+        d.dirty_bitmap = g_malloc0(size);
 
         d.slot = mem->slot | (kml->as_id << 16);
         if (kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d) == -1) {
             DPRINTF("ioctl failed %d\n", errno);
-            ret = -1;
-            break;
+            g_free(d.dirty_bitmap);
+            return -1;
         }
 
         kvm_get_dirty_pages_log_range(section, d.dirty_bitmap);
-        start_addr = mem->start_addr + mem->memory_size;
+        g_free(d.dirty_bitmap);
     }
-    g_free(d.dirty_bitmap);
 
-    return ret;
+    return 0;
 }
 
 static void kvm_coalesce_mmio_region(MemoryListener *listener,
@@ -696,30 +694,12 @@ kvm_check_extension_list(KVMState *s, const KVMCapabilityInfo *list)
 static void kvm_set_phys_mem(KVMMemoryListener *kml,
                              MemoryRegionSection *section, bool add)
 {
-    KVMState *s = kvm_state;
-    KVMSlot *mem, old;
+    KVMSlot *mem;
     int err;
     MemoryRegion *mr = section->mr;
     bool writeable = !mr->readonly && !mr->rom_device;
-    hwaddr start_addr = section->offset_within_address_space;
-    ram_addr_t size = int128_get64(section->size);
-    void *ram = NULL;
-    unsigned delta;
-
-    /* kvm works in page size chunks, but the function may be called
-       with sub-page size and unaligned start address. Pad the start
-       address to next and truncate size to previous page boundary. */
-    delta = qemu_real_host_page_size - (start_addr & ~qemu_real_host_page_mask);
-    delta &= ~qemu_real_host_page_mask;
-    if (delta > size) {
-        return;
-    }
-    start_addr += delta;
-    size -= delta;
-    size &= qemu_real_host_page_mask;
-    if (!size || (start_addr & ~qemu_real_host_page_mask)) {
-        return;
-    }
+    hwaddr start_addr, size;
+    void *ram;
 
     if (!memory_region_is_ram(mr)) {
         if (writeable || !kvm_readonly_mem_allowed) {
@@ -731,30 +711,25 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
         }
     }
 
-    ram = memory_region_get_ram_ptr(mr) + section->offset_within_region + delta;
+    size = kvm_align_section(section, &start_addr);
+    if (!size) {
+        return;
+    }
 
-    while (1) {
-        mem = kvm_lookup_overlapping_slot(kml, start_addr, start_addr + size);
+    ram = memory_region_get_ram_ptr(mr) + section->offset_within_region +
+          (section->offset_within_address_space - start_addr);
+
+    mem = kvm_lookup_matching_slot(kml, start_addr, size);
+    if (!add) {
         if (!mem) {
-            break;
-        }
-
-        if (add && start_addr >= mem->start_addr &&
-            (start_addr + size <= mem->start_addr + mem->memory_size) &&
-            (ram - start_addr == mem->ram - mem->start_addr)) {
-            /* The new slot fits into the existing one and comes with
-             * identical parameters - update flags and done. */
-            kvm_slot_update_flags(kml, mem, mr);
+            g_assert(!memory_region_is_ram(mr) && !writeable && !mr->romd_mode);
             return;
         }
-
-        old = *mem;
-
         if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
             kvm_physical_sync_dirty_bitmap(kml, section);
         }
 
-        /* unregister the overlapping slot */
+        /* unregister the slot */
         mem->memory_size = 0;
         err = kvm_set_user_memory_region(kml, mem);
         if (err) {
@@ -762,84 +737,16 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
                     __func__, strerror(-err));
             abort();
         }
-
-        /* Workaround for older KVM versions: we can't join slots, even not by
-         * unregistering the previous ones and then registering the larger
-         * slot. We have to maintain the existing fragmentation. Sigh.
-         *
-         * This workaround assumes that the new slot starts at the same
-         * address as the first existing one. If not or if some overlapping
-         * slot comes around later, we will fail (not seen in practice so far)
-         * - and actually require a recent KVM version. */
-        if (s->broken_set_mem_region &&
-            old.start_addr == start_addr && old.memory_size < size && add) {
-            mem = kvm_alloc_slot(kml);
-            mem->memory_size = old.memory_size;
-            mem->start_addr = old.start_addr;
-            mem->ram = old.ram;
-            mem->flags = kvm_mem_flags(mr);
-
-            err = kvm_set_user_memory_region(kml, mem);
-            if (err) {
-                fprintf(stderr, "%s: error updating slot: %s\n", __func__,
-                        strerror(-err));
-                abort();
-            }
-
-            start_addr += old.memory_size;
-            ram += old.memory_size;
-            size -= old.memory_size;
-            continue;
-        }
-
-        /* register prefix slot */
-        if (old.start_addr < start_addr) {
-            mem = kvm_alloc_slot(kml);
-            mem->memory_size = start_addr - old.start_addr;
-            mem->start_addr = old.start_addr;
-            mem->ram = old.ram;
-            mem->flags =  kvm_mem_flags(mr);
-
-            err = kvm_set_user_memory_region(kml, mem);
-            if (err) {
-                fprintf(stderr, "%s: error registering prefix slot: %s\n",
-                        __func__, strerror(-err));
-#ifdef TARGET_PPC
-                fprintf(stderr, "%s: This is probably because your kernel's " \
-                                "PAGE_SIZE is too big. Please try to use 4k " \
-                                "PAGE_SIZE!\n", __func__);
-#endif
-                abort();
-            }
-        }
-
-        /* register suffix slot */
-        if (old.start_addr + old.memory_size > start_addr + size) {
-            ram_addr_t size_delta;
-
-            mem = kvm_alloc_slot(kml);
-            mem->start_addr = start_addr + size;
-            size_delta = mem->start_addr - old.start_addr;
-            mem->memory_size = old.memory_size - size_delta;
-            mem->ram = old.ram + size_delta;
-            mem->flags = kvm_mem_flags(mr);
-
-            err = kvm_set_user_memory_region(kml, mem);
-            if (err) {
-                fprintf(stderr, "%s: error registering suffix slot: %s\n",
-                        __func__, strerror(-err));
-                abort();
-            }
-        }
-    }
-
-    /* in case the KVM bug workaround already "consumed" the new slot */
-    if (!size) {
         return;
     }
-    if (!add) {
+
+    if (mem) {
+        /* update the slot */
+        kvm_slot_update_flags(kml, mem, mr);
         return;
     }
+
+    /* register the new slot */
     mem = kvm_alloc_slot(kml);
     mem->memory_size = size;
     mem->start_addr = start_addr;
@@ -1248,7 +1155,7 @@ int kvm_irqchip_add_msi_route(KVMState *s, int vector, PCIDevice *dev)
     int virq;
     MSIMessage msg = {0, 0};
 
-    if (dev) {
+    if (pci_available && dev) {
         msg = pci_get_msi_message(dev, vector);
     }
 
@@ -1271,7 +1178,7 @@ int kvm_irqchip_add_msi_route(KVMState *s, int vector, PCIDevice *dev)
     kroute.u.msi.address_lo = (uint32_t)msg.address;
     kroute.u.msi.address_hi = msg.address >> 32;
     kroute.u.msi.data = le32_to_cpu(msg.data);
-    if (kvm_msi_devid_required()) {
+    if (pci_available && kvm_msi_devid_required()) {
         kroute.flags = KVM_MSI_VALID_DEVID;
         kroute.u.msi.devid = pci_requester_id(dev);
     }
@@ -1309,7 +1216,7 @@ int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg,
     kroute.u.msi.address_lo = (uint32_t)msg.address;
     kroute.u.msi.address_hi = msg.address >> 32;
     kroute.u.msi.data = le32_to_cpu(msg.data);
-    if (kvm_msi_devid_required()) {
+    if (pci_available && kvm_msi_devid_required()) {
         kroute.flags = KVM_MSI_VALID_DEVID;
         kroute.u.msi.devid = pci_requester_id(dev);
     }
@@ -1629,10 +1536,9 @@ static int kvm_init(MachineState *ms)
 
     while (nc->name) {
         if (nc->num > soft_vcpus_limit) {
-            fprintf(stderr,
-                    "Warning: Number of %s cpus requested (%d) exceeds "
-                    "the recommended cpus supported by KVM (%d)\n",
-                    nc->name, nc->num, soft_vcpus_limit);
+            warn_report("Number of %s cpus requested (%d) exceeds "
+                        "the recommended cpus supported by KVM (%d)",
+                        nc->name, nc->num, soft_vcpus_limit);
 
             if (nc->num > hard_vcpus_limit) {
                 fprintf(stderr, "Number of %s cpus requested (%d) exceeds "
@@ -1692,12 +1598,6 @@ static int kvm_init(MachineState *ms)
 
     s->coalesced_mmio = kvm_check_extension(s, KVM_CAP_COALESCED_MMIO);
 
-    s->broken_set_mem_region = 1;
-    ret = kvm_check_extension(s, KVM_CAP_JOIN_MEMORY_REGIONS_WORKS);
-    if (ret > 0) {
-        s->broken_set_mem_region = 0;
-    }
-
 #ifdef KVM_CAP_VCPU_EVENTS
     s->vcpu_events = kvm_check_extension(s, KVM_CAP_VCPU_EVENTS);
 #endif

accel/stubs/Makefile.objs

@@ -1,2 +1,3 @@
+obj-$(call lnot,$(CONFIG_HAX)) += hax-stub.o
 obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o
 obj-$(call lnot,$(CONFIG_TCG)) += tcg-stub.o

accel/tcg/Makefile.objs

@@ -1,3 +1,8 @@
 obj-$(CONFIG_SOFTMMU) += tcg-all.o
 obj-$(CONFIG_SOFTMMU) += cputlb.o
+obj-y += tcg-runtime.o
 obj-y += cpu-exec.o cpu-exec-common.o translate-all.o
+obj-y += translator.o
+
+obj-$(CONFIG_USER_ONLY) += user-exec.o
+obj-$(call lnot,$(CONFIG_SOFTMMU)) += user-exec-stub.o

accel/tcg/cpu-exec.c

@@ -329,6 +329,41 @@ TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
     return qht_lookup(&tcg_ctx.tb_ctx.htable, tb_cmp, &desc, h);
 }
 
+void tb_set_jmp_target(TranslationBlock *tb, int n, uintptr_t addr)
+{
+    if (TCG_TARGET_HAS_direct_jump) {
+        uintptr_t offset = tb->jmp_target_arg[n];
+        uintptr_t tc_ptr = (uintptr_t)tb->tc_ptr;
+        tb_target_set_jmp_target(tc_ptr, tc_ptr + offset, addr);
+    } else {
+        tb->jmp_target_arg[n] = addr;
+    }
+}
+
+/* Called with tb_lock held.  */
+static inline void tb_add_jump(TranslationBlock *tb, int n,
+                               TranslationBlock *tb_next)
+{
+    assert(n < ARRAY_SIZE(tb->jmp_list_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;
+    }
+    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);
+
+    /* 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,
                                         TranslationBlock *last_tb,
                                         int tb_exit)

accel/tcg/cputlb.c

@@ -747,6 +747,7 @@ 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, int size)
 {
     CPUState *cpu = ENV_GET_CPU(env);
@@ -754,6 +755,7 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
     MemoryRegion *mr = iotlb_to_region(cpu, physaddr, iotlbentry->attrs);
     uint64_t val;
     bool locked = false;
+    MemTxResult r;
 
     physaddr = (physaddr & TARGET_PAGE_MASK) + addr;
     cpu->mem_io_pc = retaddr;
@@ -767,7 +769,12 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
         qemu_mutex_lock_iothread();
         locked = true;
     }
-    memory_region_dispatch_read(mr, physaddr, &val, size, iotlbentry->attrs);
+    r = memory_region_dispatch_read(mr, physaddr,
+                                    &val, size, iotlbentry->attrs);
+    if (r != MEMTX_OK) {
+        cpu_transaction_failed(cpu, physaddr, addr, size, MMU_DATA_LOAD,
+                               mmu_idx, iotlbentry->attrs, r, retaddr);
+    }
     if (locked) {
         qemu_mutex_unlock_iothread();
     }
@@ -776,6 +783,7 @@ 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, int size)
 {
@@ -783,6 +791,7 @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
     hwaddr physaddr = iotlbentry->addr;
     MemoryRegion *mr = iotlb_to_region(cpu, physaddr, iotlbentry->attrs);
     bool locked = false;
+    MemTxResult r;
 
     physaddr = (physaddr & TARGET_PAGE_MASK) + addr;
     if (mr != &io_mem_rom && mr != &io_mem_notdirty && !cpu->can_do_io) {
@@ -795,7 +804,12 @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
         qemu_mutex_lock_iothread();
         locked = true;
     }
-    memory_region_dispatch_write(mr, physaddr, val, size, iotlbentry->attrs);
+    r = memory_region_dispatch_write(mr, physaddr,
+                                     val, size, iotlbentry->attrs);
+    if (r != MEMTX_OK) {
+        cpu_transaction_failed(cpu, physaddr, addr, size, MMU_DATA_STORE,
+                               mmu_idx, iotlbentry->attrs, r, retaddr);
+    }
     if (locked) {
         qemu_mutex_unlock_iothread();
     }
@@ -845,6 +859,7 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr)
     MemoryRegion *mr;
     CPUState *cpu = ENV_GET_CPU(env);
     CPUIOTLBEntry *iotlbentry;
+    hwaddr physaddr;
 
     index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
     mmu_idx = cpu_mmu_index(env, true);
@@ -868,6 +883,19 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr)
         }
         qemu_mutex_unlock_iothread();
 
+        /* Give the new-style cpu_transaction_failed() hook first chance
+         * to handle this.
+         * This is not the ideal place to detect and generate CPU
+         * exceptions for instruction fetch failure (for instance
+         * we don't know the length of the access that the CPU would
+         * use, and it would be better to go ahead and try the access
+         * and use the MemTXResult it produced). However it is the
+         * simplest place we have currently available for the check.
+         */
+        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);
+
         cpu_unassigned_access(cpu, addr, false, true, 0, 4);
         /* The CPU's unassigned access hook might have longjumped out
          * with an exception. If it didn't (or there was no hook) then

accel/tcg/softmmu_template.h

@@ -101,7 +101,7 @@ static inline DATA_TYPE glue(io_read, SUFFIX)(CPUArchState *env,
                                               uintptr_t retaddr)
 {
     CPUIOTLBEntry *iotlbentry = &env->iotlb[mmu_idx][index];
-    return io_readx(env, iotlbentry, addr, retaddr, DATA_SIZE);
+    return io_readx(env, iotlbentry, mmu_idx, addr, retaddr, DATA_SIZE);
 }
 #endif
 
@@ -262,7 +262,7 @@ static inline void glue(io_write, SUFFIX)(CPUArchState *env,
                                           uintptr_t retaddr)
 {
     CPUIOTLBEntry *iotlbentry = &env->iotlb[mmu_idx][index];
-    return io_writex(env, iotlbentry, val, addr, retaddr, 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,

accel/tcg/tcg-runtime.c

@@ -178,57 +178,3 @@ void HELPER(exit_atomic)(CPUArchState *env)
 {
     cpu_loop_exit_atomic(ENV_GET_CPU(env), GETPC());
 }
-
-#ifndef CONFIG_SOFTMMU
-/* The softmmu versions of these helpers are in cputlb.c.  */
-
-/* Do not allow unaligned operations to proceed.  Return the host address.  */
-static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
-                               int size, uintptr_t retaddr)
-{
-    /* Enforce qemu required alignment.  */
-    if (unlikely(addr & (size - 1))) {
-        cpu_loop_exit_atomic(ENV_GET_CPU(env), retaddr);
-    }
-    return g2h(addr);
-}
-
-/* Macro to call the above, with local variables from the use context.  */
-#define ATOMIC_MMU_LOOKUP  atomic_mmu_lookup(env, addr, DATA_SIZE, GETPC())
-
-#define ATOMIC_NAME(X)   HELPER(glue(glue(atomic_ ## X, SUFFIX), END))
-#define EXTRA_ARGS
-
-#define DATA_SIZE 1
-#include "atomic_template.h"
-
-#define DATA_SIZE 2
-#include "atomic_template.h"
-
-#define DATA_SIZE 4
-#include "atomic_template.h"
-
-#ifdef CONFIG_ATOMIC64
-#define DATA_SIZE 8
-#include "atomic_template.h"
-#endif
-
-/* The following is only callable from other helpers, and matches up
-   with the softmmu version.  */
-
-#ifdef CONFIG_ATOMIC128
-
-#undef EXTRA_ARGS
-#undef ATOMIC_NAME
-#undef ATOMIC_MMU_LOOKUP
-
-#define EXTRA_ARGS     , TCGMemOpIdx oi, uintptr_t retaddr
-#define ATOMIC_NAME(X) \
-    HELPER(glue(glue(glue(atomic_ ## X, SUFFIX), END), _mmu))
-#define ATOMIC_MMU_LOOKUP  atomic_mmu_lookup(env, addr, DATA_SIZE, retaddr)
-
-#define DATA_SIZE 16
-#include "atomic_template.h"
-#endif /* CONFIG_ATOMIC128 */
-
-#endif /* !CONFIG_SOFTMMU */

accel/tcg/trace-events

@@ -4,7 +4,7 @@
 # cpu-exec.c
 disable exec_tb(void *tb, uintptr_t pc) "tb:%p pc=0x%"PRIxPTR
 disable exec_tb_nocache(void *tb, uintptr_t pc) "tb:%p pc=0x%"PRIxPTR
-disable exec_tb_exit(void *last_tb, unsigned int flags) "tb:%p flags=%x"
+disable exec_tb_exit(void *last_tb, unsigned int flags) "tb:%p flags=0x%x"
 
 # translate-all.c
 translate_block(void *tb, uintptr_t pc, uint8_t *tb_code) "tb:%p, pc:0x%"PRIxPTR", tb_code:%p"

accel/tcg/translate-all.c

@@ -1280,7 +1280,7 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
     tcg_func_start(&tcg_ctx);
 
     tcg_ctx.cpu = ENV_GET_CPU(env);
-    gen_intermediate_code(env, tb);
+    gen_intermediate_code(cpu, tb);
     tcg_ctx.cpu = NULL;
 
     trace_translate_block(tb, tb->pc, tb->tc_ptr);
@@ -1289,13 +1289,13 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
     tb->jmp_reset_offset[0] = TB_JMP_RESET_OFFSET_INVALID;
     tb->jmp_reset_offset[1] = TB_JMP_RESET_OFFSET_INVALID;
     tcg_ctx.tb_jmp_reset_offset = tb->jmp_reset_offset;
-#ifdef USE_DIRECT_JUMP
-    tcg_ctx.tb_jmp_insn_offset = tb->jmp_insn_offset;
-    tcg_ctx.tb_jmp_target_addr = NULL;
-#else
-    tcg_ctx.tb_jmp_insn_offset = NULL;
-    tcg_ctx.tb_jmp_target_addr = tb->jmp_target_addr;
-#endif
+    if (TCG_TARGET_HAS_direct_jump) {
+        tcg_ctx.tb_jmp_insn_offset = tb->jmp_target_arg;
+        tcg_ctx.tb_jmp_target_addr = NULL;
+    } else {
+        tcg_ctx.tb_jmp_insn_offset = NULL;
+        tcg_ctx.tb_jmp_target_addr = tb->jmp_target_arg;
+    }
 
 #ifdef CONFIG_PROFILER
     tcg_ctx.tb_count++;
@@ -1329,7 +1329,27 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
         qemu_log_in_addr_range(tb->pc)) {
         qemu_log_lock();
         qemu_log("OUT: [size=%d]\n", gen_code_size);
-        log_disas(tb->tc_ptr, gen_code_size);
+        if (tcg_ctx.data_gen_ptr) {
+            size_t code_size = tcg_ctx.data_gen_ptr - tb->tc_ptr;
+            size_t data_size = gen_code_size - code_size;
+            size_t i;
+
+            log_disas(tb->tc_ptr, code_size);
+
+            for (i = 0; i < data_size; i += sizeof(tcg_target_ulong)) {
+                if (sizeof(tcg_target_ulong) == 8) {
+                    qemu_log("0x%08" PRIxPTR ":  .quad  0x%016" PRIx64 "\n",
+                             (uintptr_t)tcg_ctx.data_gen_ptr + i,
+                             *(uint64_t *)(tcg_ctx.data_gen_ptr + i));
+                } else {
+                    qemu_log("0x%08" PRIxPTR ":  .long  0x%08x\n",
+                             (uintptr_t)tcg_ctx.data_gen_ptr + i,
+                             *(uint32_t *)(tcg_ctx.data_gen_ptr + i));
+                }
+            }
+        } else {
+            log_disas(tb->tc_ptr, gen_code_size);
+        }
         qemu_log("\n");
         qemu_log_flush();
         qemu_log_unlock();

accel/tcg/translator.c

@@ -0,0 +1,138 @@
+/*
+ * Generic intermediate code generation.
+ *
+ * Copyright (C) 2016-2017 Lluís Vilanova <vilanova@ac.upc.edu>
+ *
+ * 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 "qemu/error-report.h"
+#include "cpu.h"
+#include "tcg/tcg.h"
+#include "tcg/tcg-op.h"
+#include "exec/exec-all.h"
+#include "exec/gen-icount.h"
+#include "exec/log.h"
+#include "exec/translator.h"
+
+/* Pairs with tcg_clear_temp_count.
+   To be called by #TranslatorOps.{translate_insn,tb_stop} if
+   (1) the target is sufficiently clean to support reporting,
+   (2) as and when all temporaries are known to be consumed.
+   For most targets, (2) is at the end of translate_insn.  */
+void translator_loop_temp_check(DisasContextBase *db)
+{
+    if (tcg_check_temp_count()) {
+        qemu_log("warning: TCG temporary leaks before "
+                 TARGET_FMT_lx "\n", db->pc_next);
+    }
+}
+
+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;
+    db->pc_next = db->pc_first;
+    db->is_jmp = DISAS_NEXT;
+    db->num_insns = 0;
+    db->singlestep_enabled = cpu->singlestep_enabled;
+
+    /* Instruction counting */
+    max_insns = db->tb->cflags & CF_COUNT_MASK;
+    if (max_insns == 0) {
+        max_insns = CF_COUNT_MASK;
+    }
+    if (max_insns > TCG_MAX_INSNS) {
+        max_insns = TCG_MAX_INSNS;
+    }
+    if (db->singlestep_enabled || singlestep) {
+        max_insns = 1;
+    }
+
+    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 */
+    tcg_clear_temp_count();
+
+    /* Start translating.  */
+    gen_tb_start(db->tb);
+    ops->tb_start(db, cpu);
+    tcg_debug_assert(db->is_jmp == DISAS_NEXT);  /* no early exit */
+
+    while (true) {
+        db->num_insns++;
+        ops->insn_start(db, cpu);
+        tcg_debug_assert(db->is_jmp == DISAS_NEXT);  /* no early exit */
+
+        /* Pass breakpoint hits to target for further processing */
+        if (unlikely(!QTAILQ_EMPTY(&cpu->breakpoints))) {
+            CPUBreakpoint *bp;
+            QTAILQ_FOREACH(bp, &cpu->breakpoints, entry) {
+                if (bp->pc == db->pc_next) {
+                    if (ops->breakpoint_check(db, cpu, bp)) {
+                        break;
+                    }
+                }
+            }
+            /* The breakpoint_check hook may use DISAS_TOO_MANY to indicate
+               that only one more instruction is to be executed.  Otherwise
+               it should use DISAS_NORETURN when generating an exception,
+               but may use a DISAS_TARGET_* value for Something Else.  */
+            if (db->is_jmp > DISAS_TOO_MANY) {
+                break;
+            }
+        }
+
+        /* Disassemble one instruction.  The translate_insn hook should
+           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 == max_insns && (db->tb->cflags & CF_LAST_IO)) {
+            /* Accept I/O on the last instruction.  */
+            gen_io_start();
+            ops->translate_insn(db, cpu);
+            gen_io_end();
+        } else {
+            ops->translate_insn(db, cpu);
+        }
+
+        /* Stop translation if translate_insn so indicated.  */
+        if (db->is_jmp != DISAS_NEXT) {
+            break;
+        }
+
+        /* 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 >= max_insns) {
+            db->is_jmp = DISAS_TOO_MANY;
+            break;
+        }
+    }
+
+    /* Emit code to exit the TB, as indicated by db->is_jmp.  */
+    ops->tb_stop(db, cpu);
+    gen_tb_end(db->tb, db->num_insns);
+
+    /* The disas_log hook may use these values rather than recompute.  */
+    db->tb->size = db->pc_next - db->pc_first;
+    db->tb->icount = db->num_insns;
+
+#ifdef DEBUG_DISAS
+    if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)
+        && qemu_log_in_addr_range(db->pc_first)) {
+        qemu_log_lock();
+        qemu_log("----------------\n");
+        ops->disas_log(db, cpu);
+        qemu_log("\n");
+        qemu_log_unlock();
+    }
+#endif
+}

accel/tcg/user-exec.c

@@ -24,6 +24,7 @@
 #include "qemu/bitops.h"
 #include "exec/cpu_ldst.h"
 #include "translate-all.h"
+#include "exec/helper-proto.h"
 
 #undef EAX
 #undef ECX
@@ -167,7 +168,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
 #elif defined(__OpenBSD__)
     struct sigcontext *uc = puc;
 #else
-    struct ucontext *uc = puc;
+    ucontext_t *uc = puc;
 #endif
     unsigned long pc;
     int trapno;
@@ -222,7 +223,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
 #elif defined(__OpenBSD__)
     struct sigcontext *uc = puc;
 #else
-    struct ucontext *uc = puc;
+    ucontext_t *uc = puc;
 #endif
 
     pc = PC_sig(uc);
@@ -289,7 +290,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
 #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
     ucontext_t *uc = puc;
 #else
-    struct ucontext *uc = puc;
+    ucontext_t *uc = puc;
 #endif
     unsigned long pc;
     int is_write;
@@ -316,7 +317,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
                            void *puc)
 {
     siginfo_t *info = pinfo;
-    struct ucontext *uc = puc;
+    ucontext_t *uc = puc;
     uint32_t *pc = uc->uc_mcontext.sc_pc;
     uint32_t insn = *pc;
     int is_write = 0;
@@ -414,7 +415,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
 #if defined(__NetBSD__)
     ucontext_t *uc = puc;
 #else
-    struct ucontext *uc = puc;
+    ucontext_t *uc = puc;
 #endif
     unsigned long pc;
     int is_write;
@@ -441,7 +442,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
 int cpu_signal_handler(int host_signum, void *pinfo, void *puc)
 {
     siginfo_t *info = pinfo;
-    struct ucontext *uc = puc;
+    ucontext_t *uc = puc;
     uintptr_t pc = uc->uc_mcontext.pc;
     uint32_t insn = *(uint32_t *)pc;
     bool is_write;
@@ -474,7 +475,7 @@ int cpu_signal_handler(int host_signum, void *pinfo, void *puc)
 int cpu_signal_handler(int host_signum, void *pinfo, void *puc)
 {
     siginfo_t *info = pinfo;
-    struct ucontext *uc = puc;
+    ucontext_t *uc = puc;
     unsigned long ip;
     int is_write = 0;
 
@@ -505,7 +506,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
                        void *puc)
 {
     siginfo_t *info = pinfo;
-    struct ucontext *uc = puc;
+    ucontext_t *uc = puc;
     unsigned long pc;
     uint16_t *pinsn;
     int is_write = 0;
@@ -558,7 +559,7 @@ int cpu_signal_handler(int host_signum, void *pinfo,
                        void *puc)
 {
     siginfo_t *info = pinfo;
-    struct ucontext *uc = puc;
+    ucontext_t *uc = puc;
     greg_t pc = uc->uc_mcontext.pc;
     int is_write;
 
@@ -573,3 +574,54 @@ int cpu_signal_handler(int host_signum, void *pinfo,
 #error host CPU specific signal handler needed
 
 #endif
+
+/* The softmmu versions of these helpers are in cputlb.c.  */
+
+/* Do not allow unaligned operations to proceed.  Return the host address.  */
+static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr,
+                               int size, uintptr_t retaddr)
+{
+    /* Enforce qemu required alignment.  */
+    if (unlikely(addr & (size - 1))) {
+        cpu_loop_exit_atomic(ENV_GET_CPU(env), retaddr);
+    }
+    return g2h(addr);
+}
+
+/* Macro to call the above, with local variables from the use context.  */
+#define ATOMIC_MMU_LOOKUP  atomic_mmu_lookup(env, addr, DATA_SIZE, GETPC())
+
+#define ATOMIC_NAME(X)   HELPER(glue(glue(atomic_ ## X, SUFFIX), END))
+#define EXTRA_ARGS
+
+#define DATA_SIZE 1
+#include "atomic_template.h"
+
+#define DATA_SIZE 2
+#include "atomic_template.h"
+
+#define DATA_SIZE 4
+#include "atomic_template.h"
+
+#ifdef CONFIG_ATOMIC64
+#define DATA_SIZE 8
+#include "atomic_template.h"
+#endif
+
+/* The following is only callable from other helpers, and matches up
+   with the softmmu version.  */
+
+#ifdef CONFIG_ATOMIC128
+
+#undef EXTRA_ARGS
+#undef ATOMIC_NAME
+#undef ATOMIC_MMU_LOOKUP
+
+#define EXTRA_ARGS     , TCGMemOpIdx oi, uintptr_t retaddr
+#define ATOMIC_NAME(X) \
+    HELPER(glue(glue(glue(atomic_ ## X, SUFFIX), END), _mmu))
+#define ATOMIC_MMU_LOOKUP  atomic_mmu_lookup(env, addr, DATA_SIZE, retaddr)
+
+#define DATA_SIZE 16
+#include "atomic_template.h"
+#endif /* CONFIG_ATOMIC128 */

audio/trace-events

@@ -1,9 +1,9 @@
-# See docs/tracing.txt for syntax documentation.
+# See docs/devel/tracing.txt for syntax documentation.
 
 # audio/alsaaudio.c
 alsa_revents(int revents) "revents = %d"
 alsa_pollout(int i, int fd) "i = %d fd = %d"
-alsa_set_handler(int events, int index, int fd, int err) "events=%#x index=%d fd=%d err=%d"
+alsa_set_handler(int events, int index, int fd, int err) "events=0x%x index=%d fd=%d err=%d"
 alsa_wrote_zero(int len) "Failed to write %d frames (wrote zero)"
 alsa_read_zero(long len) "Failed to read %ld frames (read zero)"
 alsa_xrun_out(void) "Recovering from playback xrun"
@@ -13,5 +13,5 @@ alsa_resume_in(void) "Resuming suspended input stream"
 alsa_no_frames(int state) "No frames available and ALSA state is %d"
 
 # audio/ossaudio.c
-oss_version(int version) "OSS version = %#x"
+oss_version(int version) "OSS version = 0x%x"
 oss_invalid_available_size(int size, int bufsize) "Invalid available size, size=%d bufsize=%d"

backends/cryptodev.c

@@ -215,7 +215,7 @@ bool cryptodev_backend_is_ready(CryptoDevBackend *backend)
 }
 
 static bool
-cryptodev_backend_can_be_deleted(UserCreatable *uc, Error **errp)
+cryptodev_backend_can_be_deleted(UserCreatable *uc)
 {
     return !cryptodev_backend_is_used(CRYPTODEV_BACKEND(uc));
 }

backends/hostmem-file.c

@@ -32,6 +32,7 @@ struct HostMemoryBackendFile {
     HostMemoryBackend parent_obj;
 
     bool share;
+    bool discard_data;
     char *mem_path;
 };
 
@@ -103,16 +104,44 @@ static void file_memory_backend_set_share(Object *o, bool value, Error **errp)
     fb->share = value;
 }
 
+static bool file_memory_backend_get_discard_data(Object *o, Error **errp)
+{
+    return MEMORY_BACKEND_FILE(o)->discard_data;
+}
+
+static void file_memory_backend_set_discard_data(Object *o, bool value,
+                                               Error **errp)
+{
+    MEMORY_BACKEND_FILE(o)->discard_data = value;
+}
+
+static void file_backend_unparent(Object *obj)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(obj);
+
+    if (host_memory_backend_mr_inited(backend) && fb->discard_data) {
+        void *ptr = memory_region_get_ram_ptr(&backend->mr);
+        uint64_t sz = memory_region_size(&backend->mr);
+
+        qemu_madvise(ptr, sz, QEMU_MADV_REMOVE);
+    }
+}
+
 static void
 file_backend_class_init(ObjectClass *oc, void *data)
 {
     HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
 
     bc->alloc = file_backend_memory_alloc;
+    oc->unparent = file_backend_unparent;
 
     object_class_property_add_bool(oc, "share",
         file_memory_backend_get_share, file_memory_backend_set_share,
         &error_abort);
+    object_class_property_add_bool(oc, "discard-data",
+        file_memory_backend_get_discard_data, file_memory_backend_set_discard_data,
+        &error_abort);
     object_class_property_add_str(oc, "mem-path",
         get_mem_path, set_mem_path,
         &error_abort);

backends/hostmem.c

@@ -304,7 +304,7 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
             return;
         } else if (maxnode == 0 && backend->policy != MPOL_DEFAULT) {
             error_setg(errp, "host-nodes must be set for policy %s",
-                       HostMemPolicy_lookup[backend->policy]);
+                       HostMemPolicy_str(backend->policy));
             return;
         }
 
@@ -342,7 +342,7 @@ out:
 }
 
 static bool
-host_memory_backend_can_be_deleted(UserCreatable *uc, Error **errp)
+host_memory_backend_can_be_deleted(UserCreatable *uc)
 {
     if (host_memory_backend_is_mapped(MEMORY_BACKEND(uc))) {
         return false;
@@ -395,7 +395,7 @@ host_memory_backend_class_init(ObjectClass *oc, void *data)
         host_memory_backend_set_host_nodes,
         NULL, NULL, &error_abort);
     object_class_property_add_enum(oc, "policy", "HostMemPolicy",
-        HostMemPolicy_lookup,
+        &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);

block.c

@@ -42,7 +42,6 @@
 #include "qapi-event.h"
 #include "qemu/cutils.h"
 #include "qemu/id.h"
-#include "qapi/util.h"
 
 #ifdef CONFIG_BSD
 #include <sys/ioctl.h>
@@ -246,7 +245,8 @@ bool bdrv_is_writable(BlockDriverState *bs)
     return !bdrv_is_read_only(bs) && !(bs->open_flags & BDRV_O_INACTIVE);
 }
 
-int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
+int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only,
+                           bool ignore_allow_rdw, Error **errp)
 {
     /* Do not set read_only if copy_on_read is enabled */
     if (bs->copy_on_read && read_only) {
@@ -256,7 +256,9 @@ int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
     }
 
     /* Do not clear read_only if it is prohibited */
-    if (!read_only && !(bs->open_flags & BDRV_O_ALLOW_RDWR)) {
+    if (!read_only && !(bs->open_flags & BDRV_O_ALLOW_RDWR) &&
+        !ignore_allow_rdw)
+    {
         error_setg(errp, "Node '%s' is read only",
                    bdrv_get_device_or_node_name(bs));
         return -EPERM;
@@ -269,7 +271,7 @@ int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
 {
     int ret = 0;
 
-    ret = bdrv_can_set_read_only(bs, read_only, errp);
+    ret = bdrv_can_set_read_only(bs, read_only, false, errp);
     if (ret < 0) {
         return ret;
     }
@@ -494,6 +496,8 @@ int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
 
     if (drv && drv->bdrv_probe_blocksizes) {
         return drv->bdrv_probe_blocksizes(bs, bsz);
+    } else if (drv && drv->is_filter && bs->file) {
+        return bdrv_probe_blocksizes(bs->file->bs, bsz);
     }
 
     return -ENOTSUP;
@@ -511,6 +515,8 @@ int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo)
 
     if (drv && drv->bdrv_probe_geometry) {
         return drv->bdrv_probe_geometry(bs, geo);
+    } else if (drv && drv->is_filter && bs->file) {
+        return bdrv_probe_geometry(bs->file->bs, geo);
     }
 
     return -ENOTSUP;
@@ -1119,20 +1125,19 @@ static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv,
         } else {
             error_setg_errno(errp, -ret, "Could not open image");
         }
-        goto free_and_fail;
+        goto open_failed;
     }
 
     ret = refresh_total_sectors(bs, bs->total_sectors);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not refresh total sector count");
-        goto free_and_fail;
+        return ret;
     }
 
     bdrv_refresh_limits(bs, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
-        ret = -EINVAL;
-        goto free_and_fail;
+        return -EINVAL;
     }
 
     assert(bdrv_opt_mem_align(bs) != 0);
@@ -1140,12 +1145,14 @@ static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv,
     assert(is_power_of_2(bs->bl.request_alignment));
 
     return 0;
-
-free_and_fail:
-    /* FIXME Close bs first if already opened*/
+open_failed:
+    bs->drv = NULL;
+    if (bs->file != NULL) {
+        bdrv_unref_child(bs, bs->file);
+        bs->file = NULL;
+    }
     g_free(bs->opaque);
     bs->opaque = NULL;
-    bs->drv = NULL;
     return ret;
 }
 
@@ -1166,7 +1173,9 @@ 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) {
         QDECREF(bs->explicit_options);
+        bs->explicit_options = NULL;
         QDECREF(bs->options);
+        bs->options = NULL;
         bdrv_unref(bs);
         return NULL;
     }
@@ -1327,9 +1336,8 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file,
     detect_zeroes = qemu_opt_get(opts, "detect-zeroes");
     if (detect_zeroes) {
         BlockdevDetectZeroesOptions value =
-            qapi_enum_parse(BlockdevDetectZeroesOptions_lookup,
+            qapi_enum_parse(&BlockdevDetectZeroesOptions_lookup,
                             detect_zeroes,
-                            BLOCKDEV_DETECT_ZEROES_OPTIONS__MAX,
                             BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
                             &local_err);
         if (local_err) {
@@ -1930,6 +1938,8 @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
     BlockDriverState *old_bs = child->bs;
     uint64_t perm, shared_perm;
 
+    bdrv_replace_child_noperm(child, new_bs);
+
     if (old_bs) {
         /* Update permissions for old node. This is guaranteed to succeed
          * because we're just taking a parent away, so we're loosening
@@ -1939,8 +1949,6 @@ static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
         bdrv_set_perm(old_bs, perm, shared_perm);
     }
 
-    bdrv_replace_child_noperm(child, new_bs);
-
     if (new_bs) {
         bdrv_get_cumulative_perm(new_bs, &perm, &shared_perm);
         bdrv_set_perm(new_bs, perm, shared_perm);
@@ -2600,14 +2608,12 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
 
 fail:
     blk_unref(file);
-    if (bs->file != NULL) {
-        bdrv_unref_child(bs, bs->file);
-    }
     QDECREF(snapshot_options);
     QDECREF(bs->explicit_options);
     QDECREF(bs->options);
     QDECREF(options);
     bs->options = NULL;
+    bs->explicit_options = NULL;
     bdrv_unref(bs);
     error_propagate(errp, local_err);
     return NULL;
@@ -2725,8 +2731,11 @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
     bdrv_join_options(bs, options, old_options);
     QDECREF(old_options);
 
-    /* bdrv_open() masks this flag out */
+    /* bdrv_open_inherit() sets and clears some additional flags internally */
     flags &= ~BDRV_O_PROTOCOL;
+    if (flags & BDRV_O_RDWR) {
+        flags |= BDRV_O_ALLOW_RDWR;
+    }
 
     QLIST_FOREACH(child, &bs->children, next) {
         QDict *new_child_options;
@@ -2906,7 +2915,7 @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
      * to r/w. Attempting to set to r/w may fail if either BDRV_O_ALLOW_RDWR is
      * not set, or if the BDS still has copy_on_read enabled */
     read_only = !(reopen_state->flags & BDRV_O_RDWR);
-    ret = bdrv_can_set_read_only(reopen_state->bs, read_only, &local_err);
+    ret = bdrv_can_set_read_only(reopen_state->bs, read_only, true, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         goto error;
@@ -3087,6 +3096,7 @@ static void bdrv_close(BlockDriverState *bs)
         QDECREF(bs->options);
         QDECREF(bs->explicit_options);
         bs->options = NULL;
+        bs->explicit_options = NULL;
         QDECREF(bs->full_open_options);
         bs->full_open_options = NULL;
     }
@@ -3420,11 +3430,15 @@ int bdrv_truncate(BdrvChild *child, int64_t offset, PreallocMode prealloc,
 
     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 (!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;
     }
@@ -3761,6 +3775,9 @@ int bdrv_has_zero_init(BlockDriverState *bs)
     if (bs->drv->bdrv_has_zero_init) {
         return bs->drv->bdrv_has_zero_init(bs);
     }
+    if (bs->file && bs->drv->is_filter) {
+        return bdrv_has_zero_init(bs->file->bs);
+    }
 
     /* safe default */
     return 0;
@@ -3815,10 +3832,16 @@ void bdrv_get_backing_filename(BlockDriverState *bs,
 int bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
     BlockDriver *drv = bs->drv;
-    if (!drv)
+    /* if bs->drv == NULL, bs is closed, so there's nothing to do here */
+    if (!drv) {
         return -ENOMEDIUM;
-    if (!drv->bdrv_get_info)
+    }
+    if (!drv->bdrv_get_info) {
+        if (bs->file && drv->is_filter) {
+            return bdrv_get_info(bs->file->bs, bdi);
+        }
         return -ENOTSUP;
+    }
     memset(bdi, 0, sizeof(*bdi));
     return drv->bdrv_get_info(bs, bdi);
 }
@@ -3973,19 +3996,6 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
     return retval;
 }
 
-int bdrv_get_backing_file_depth(BlockDriverState *bs)
-{
-    if (!bs->drv) {
-        return 0;
-    }
-
-    if (!bs->backing) {
-        return 0;
-    }
-
-    return 1 + bdrv_get_backing_file_depth(bs->backing->bs);
-}
-
 void bdrv_init(void)
 {
     module_call_init(MODULE_INIT_BLOCK);
@@ -4090,21 +4100,20 @@ static int bdrv_inactivate_recurse(BlockDriverState *bs,
         }
     }
 
-    if (setting_flag) {
+    if (setting_flag && !(bs->open_flags & BDRV_O_INACTIVE)) {
         uint64_t perm, shared_perm;
 
-        bs->open_flags |= BDRV_O_INACTIVE;
-
         QLIST_FOREACH(parent, &bs->parents, next_parent) {
             if (parent->role->inactivate) {
                 ret = parent->role->inactivate(parent);
                 if (ret < 0) {
-                    bs->open_flags &= ~BDRV_O_INACTIVE;
                     return ret;
                 }
             }
         }
 
+        bs->open_flags |= BDRV_O_INACTIVE;
+
         /* Update permissions, they may differ for inactive nodes */
         bdrv_get_cumulative_perm(bs, &perm, &shared_perm);
         bdrv_check_perm(bs, perm, shared_perm, NULL, &error_abort);
@@ -4182,20 +4191,6 @@ bool bdrv_is_inserted(BlockDriverState *bs)
     return true;
 }
 
-/**
- * Return whether the media changed since the last call to this
- * function, or -ENOTSUP if we don't know.  Most drivers don't know.
- */
-int bdrv_media_changed(BlockDriverState *bs)
-{
-    BlockDriver *drv = bs->drv;
-
-    if (drv && drv->bdrv_media_changed) {
-        return drv->bdrv_media_changed(bs);
-    }
-    return -ENOTSUP;
-}
-
 /**
  * If eject_flag is TRUE, eject the media. Otherwise, close the tray
  */

block/Makefile.objs

@@ -25,6 +25,7 @@ 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
 
 block-obj-y += crypto.o
 

block/backup.c

@@ -596,7 +596,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
         error_setg(errp,
                    "a sync_bitmap was provided to backup_run, "
                    "but received an incompatible sync_mode (%s)",
-                   MirrorSyncMode_lookup[sync_mode]);
+                   MirrorSyncMode_str(sync_mode));
         return NULL;
     }
 

block/blkdebug.c

@@ -149,20 +149,6 @@ static QemuOptsList *config_groups[] = {
     NULL
 };
 
-static int get_event_by_name(const char *name, BlkdebugEvent *event)
-{
-    int i;
-
-    for (i = 0; i < BLKDBG__MAX; i++) {
-        if (!strcmp(BlkdebugEvent_lookup[i], name)) {
-            *event = i;
-            return 0;
-        }
-    }
-
-    return -1;
-}
-
 struct add_rule_data {
     BDRVBlkdebugState *s;
     int action;
@@ -173,7 +159,7 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
     struct add_rule_data *d = opaque;
     BDRVBlkdebugState *s = d->s;
     const char* event_name;
-    BlkdebugEvent event;
+    int event;
     struct BlkdebugRule *rule;
     int64_t sector;
 
@@ -182,8 +168,9 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
     if (!event_name) {
         error_setg(errp, "Missing event name for rule");
         return -1;
-    } else if (get_event_by_name(event_name, &event) < 0) {
-        error_setg(errp, "Invalid event name \"%s\"", event_name);
+    }
+    event = qapi_enum_parse(&BlkdebugEvent_lookup, event_name, -1, errp);
+    if (event < 0) {
         return -1;
     }
 
@@ -641,16 +628,6 @@ static int coroutine_fn blkdebug_co_pdiscard(BlockDriverState *bs,
     return bdrv_co_pdiscard(bs->file->bs, offset, bytes);
 }
 
-static int64_t coroutine_fn blkdebug_co_get_block_status(
-    BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum,
-    BlockDriverState **file)
-{
-    *pnum = nb_sectors;
-    *file = bs->file->bs;
-    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID |
-        (sector_num << BDRV_SECTOR_BITS);
-}
-
 static void blkdebug_close(BlockDriverState *bs)
 {
     BDRVBlkdebugState *s = bs->opaque;
@@ -743,13 +720,13 @@ static int blkdebug_debug_breakpoint(BlockDriverState *bs, const char *event,
 {
     BDRVBlkdebugState *s = bs->opaque;
     struct BlkdebugRule *rule;
-    BlkdebugEvent blkdebug_event;
+    int blkdebug_event;
 
-    if (get_event_by_name(event, &blkdebug_event) < 0) {
+    blkdebug_event = qapi_enum_parse(&BlkdebugEvent_lookup, event, -1, NULL);
+    if (blkdebug_event < 0) {
         return -ENOENT;
     }
 
-
     rule = g_malloc(sizeof(*rule));
     *rule = (struct BlkdebugRule) {
         .event  = blkdebug_event,
@@ -821,12 +798,6 @@ static int64_t blkdebug_getlength(BlockDriverState *bs)
     return bdrv_getlength(bs->file->bs);
 }
 
-static int blkdebug_truncate(BlockDriverState *bs, int64_t offset,
-                             PreallocMode prealloc, Error **errp)
-{
-    return bdrv_truncate(bs->file, offset, prealloc, errp);
-}
-
 static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
 {
     BDRVBlkdebugState *s = bs->opaque;
@@ -909,6 +880,7 @@ static BlockDriver bdrv_blkdebug = {
     .format_name            = "blkdebug",
     .protocol_name          = "blkdebug",
     .instance_size          = sizeof(BDRVBlkdebugState),
+    .is_filter              = true,
 
     .bdrv_parse_filename    = blkdebug_parse_filename,
     .bdrv_file_open         = blkdebug_open,
@@ -917,7 +889,6 @@ static BlockDriver bdrv_blkdebug = {
     .bdrv_child_perm        = bdrv_filter_default_perms,
 
     .bdrv_getlength         = blkdebug_getlength,
-    .bdrv_truncate          = blkdebug_truncate,
     .bdrv_refresh_filename  = blkdebug_refresh_filename,
     .bdrv_refresh_limits    = blkdebug_refresh_limits,
 
@@ -926,7 +897,7 @@ static BlockDriver bdrv_blkdebug = {
     .bdrv_co_flush_to_disk  = blkdebug_co_flush,
     .bdrv_co_pwrite_zeroes  = blkdebug_co_pwrite_zeroes,
     .bdrv_co_pdiscard       = blkdebug_co_pdiscard,
-    .bdrv_co_get_block_status = blkdebug_co_get_block_status,
+    .bdrv_co_get_block_status = bdrv_co_get_block_status_from_file,
 
     .bdrv_debug_event           = blkdebug_debug_event,
     .bdrv_debug_breakpoint      = blkdebug_debug_breakpoint,

block/block-backend.c

@@ -20,6 +20,7 @@
 #include "qapi-event.h"
 #include "qemu/id.h"
 #include "trace.h"
+#include "migration/misc.h"
 
 /* Number of coroutines to reserve per attached device model */
 #define COROUTINE_POOL_RESERVATION 64
@@ -68,6 +69,8 @@ struct BlockBackend {
     NotifierList remove_bs_notifiers, insert_bs_notifiers;
 
     int quiesce_counter;
+    VMChangeStateEntry *vmsh;
+    bool force_allow_inactivate;
 };
 
 typedef struct BlockBackendAIOCB {
@@ -129,6 +132,23 @@ static const char *blk_root_get_name(BdrvChild *child)
     return blk_name(child->opaque);
 }
 
+static void blk_vm_state_changed(void *opaque, int running, RunState state)
+{
+    Error *local_err = NULL;
+    BlockBackend *blk = opaque;
+
+    if (state == RUN_STATE_INMIGRATE) {
+        return;
+    }
+
+    qemu_del_vm_change_state_handler(blk->vmsh);
+    blk->vmsh = NULL;
+    blk_set_perm(blk, blk->perm, blk->shared_perm, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+    }
+}
+
 /*
  * Notifies the user of the BlockBackend that migration has completed. qdev
  * devices can tighten their permissions in response (specifically revoke
@@ -147,6 +167,24 @@ static void blk_root_activate(BdrvChild *child, Error **errp)
 
     blk->disable_perm = false;
 
+    blk_set_perm(blk, blk->perm, BLK_PERM_ALL, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        blk->disable_perm = true;
+        return;
+    }
+
+    if (runstate_check(RUN_STATE_INMIGRATE)) {
+        /* Activation can happen when migration process is still active, for
+         * example when nbd_server_add is called during non-shared storage
+         * migration. Defer the shared_perm update to migration completion. */
+        if (!blk->vmsh) {
+            blk->vmsh = qemu_add_vm_change_state_handler(blk_vm_state_changed,
+                                                         blk);
+        }
+        return;
+    }
+
     blk_set_perm(blk, blk->perm, blk->shared_perm, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
@@ -155,6 +193,30 @@ static void blk_root_activate(BdrvChild *child, Error **errp)
     }
 }
 
+void blk_set_force_allow_inactivate(BlockBackend *blk)
+{
+    blk->force_allow_inactivate = true;
+}
+
+static bool blk_can_inactivate(BlockBackend *blk)
+{
+    /* If it is a guest device, inactivate is ok. */
+    if (blk->dev || blk_name(blk)[0]) {
+        return true;
+    }
+
+    /* Inactivating means no more writes to the image can be done,
+     * even if those writes would be changes invisible to the
+     * guest.  For block job BBs that satisfy this, we can just allow
+     * it.  This is the case for mirror job source, which is required
+     * by libvirt non-shared block migration. */
+    if (!(blk->perm & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED))) {
+        return true;
+    }
+
+    return blk->force_allow_inactivate;
+}
+
 static int blk_root_inactivate(BdrvChild *child)
 {
     BlockBackend *blk = child->opaque;
@@ -163,11 +225,7 @@ static int blk_root_inactivate(BdrvChild *child)
         return 0;
     }
 
-    /* Only inactivate BlockBackends for guest devices (which are inactive at
-     * this point because the VM is stopped) and unattached monitor-owned
-     * BlockBackends. If there is still any other user like a block job, then
-     * we simply can't inactivate the image. */
-    if (!blk->dev && !blk_name(blk)[0]) {
+    if (!blk_can_inactivate(blk)) {
         return -EPERM;
     }
 
@@ -215,9 +273,6 @@ BlockBackend *blk_new(uint64_t perm, uint64_t shared_perm)
     blk->shared_perm = shared_perm;
     blk_set_enable_write_cache(blk, true);
 
-    qemu_co_mutex_init(&blk->public.throttled_reqs_lock);
-    qemu_co_queue_init(&blk->public.throttled_reqs[0]);
-    qemu_co_queue_init(&blk->public.throttled_reqs[1]);
     block_acct_init(&blk->stats);
 
     notifier_list_init(&blk->remove_bs_notifiers);
@@ -285,12 +340,16 @@ static void blk_delete(BlockBackend *blk)
     assert(!blk->refcnt);
     assert(!blk->name);
     assert(!blk->dev);
-    if (blk->public.throttle_state) {
+    if (blk->public.throttle_group_member.throttle_state) {
         blk_io_limits_disable(blk);
     }
     if (blk->root) {
         blk_remove_bs(blk);
     }
+    if (blk->vmsh) {
+        qemu_del_vm_change_state_handler(blk->vmsh);
+        blk->vmsh = NULL;
+    }
     assert(QLIST_EMPTY(&blk->remove_bs_notifiers.notifiers));
     assert(QLIST_EMPTY(&blk->insert_bs_notifiers.notifiers));
     QTAILQ_REMOVE(&block_backends, blk, link);
@@ -596,9 +655,12 @@ BlockBackend *blk_by_public(BlockBackendPublic *public)
  */
 void blk_remove_bs(BlockBackend *blk)
 {
+    ThrottleTimers *tt;
+
     notifier_list_notify(&blk->remove_bs_notifiers, blk);
-    if (blk->public.throttle_state) {
-        throttle_timers_detach_aio_context(&blk->public.throttle_timers);
+    if (blk->public.throttle_group_member.throttle_state) {
+        tt = &blk->public.throttle_group_member.throttle_timers;
+        throttle_timers_detach_aio_context(tt);
     }
 
     blk_update_root_state(blk);
@@ -620,9 +682,10 @@ int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp)
     bdrv_ref(bs);
 
     notifier_list_notify(&blk->insert_bs_notifiers, blk);
-    if (blk->public.throttle_state) {
+    if (blk->public.throttle_group_member.throttle_state) {
         throttle_timers_attach_aio_context(
-            &blk->public.throttle_timers, bdrv_get_aio_context(bs));
+            &blk->public.throttle_group_member.throttle_timers,
+            bdrv_get_aio_context(bs));
     }
 
     return 0;
@@ -984,8 +1047,9 @@ int coroutine_fn blk_co_preadv(BlockBackend *blk, int64_t offset,
     bdrv_inc_in_flight(bs);
 
     /* throttling disk I/O */
-    if (blk->public.throttle_state) {
-        throttle_group_co_io_limits_intercept(blk, bytes, false);
+    if (blk->public.throttle_group_member.throttle_state) {
+        throttle_group_co_io_limits_intercept(&blk->public.throttle_group_member,
+                bytes, false);
     }
 
     ret = bdrv_co_preadv(blk->root, offset, bytes, qiov, flags);
@@ -1008,10 +1072,10 @@ int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
     }
 
     bdrv_inc_in_flight(bs);
-
     /* throttling disk I/O */
-    if (blk->public.throttle_state) {
-        throttle_group_co_io_limits_intercept(blk, bytes, true);
+    if (blk->public.throttle_group_member.throttle_state) {
+        throttle_group_co_io_limits_intercept(&blk->public.throttle_group_member,
+                bytes, true);
     }
 
     if (!blk->enable_write_cache) {
@@ -1680,16 +1744,14 @@ static AioContext *blk_aiocb_get_aio_context(BlockAIOCB *acb)
 void blk_set_aio_context(BlockBackend *blk, AioContext *new_context)
 {
     BlockDriverState *bs = blk_bs(blk);
+    ThrottleGroupMember *tgm = &blk->public.throttle_group_member;
 
     if (bs) {
-        if (blk->public.throttle_state) {
-            throttle_timers_detach_aio_context(&blk->public.throttle_timers);
+        if (tgm->throttle_state) {
+            throttle_group_detach_aio_context(tgm);
+            throttle_group_attach_aio_context(tgm, new_context);
         }
         bdrv_set_aio_context(bs, new_context);
-        if (blk->public.throttle_state) {
-            throttle_timers_attach_aio_context(&blk->public.throttle_timers,
-                                               new_context);
-        }
     }
 }
 
@@ -1907,33 +1969,35 @@ int blk_commit_all(void)
 /* throttling disk I/O limits */
 void blk_set_io_limits(BlockBackend *blk, ThrottleConfig *cfg)
 {
-    throttle_group_config(blk, cfg);
+    throttle_group_config(&blk->public.throttle_group_member, cfg);
 }
 
 void blk_io_limits_disable(BlockBackend *blk)
 {
-    assert(blk->public.throttle_state);
+    assert(blk->public.throttle_group_member.throttle_state);
     bdrv_drained_begin(blk_bs(blk));
-    throttle_group_unregister_blk(blk);
+    throttle_group_unregister_tgm(&blk->public.throttle_group_member);
     bdrv_drained_end(blk_bs(blk));
 }
 
 /* should be called before blk_set_io_limits if a limit is set */
 void blk_io_limits_enable(BlockBackend *blk, const char *group)
 {
-    assert(!blk->public.throttle_state);
-    throttle_group_register_blk(blk, group);
+    assert(!blk->public.throttle_group_member.throttle_state);
+    throttle_group_register_tgm(&blk->public.throttle_group_member,
+                                group, blk_get_aio_context(blk));
 }
 
 void blk_io_limits_update_group(BlockBackend *blk, const char *group)
 {
     /* this BB is not part of any group */
-    if (!blk->public.throttle_state) {
+    if (!blk->public.throttle_group_member.throttle_state) {
         return;
     }
 
     /* this BB is a part of the same group than the one we want */
-    if (!g_strcmp0(throttle_group_get_name(blk), group)) {
+    if (!g_strcmp0(throttle_group_get_name(&blk->public.throttle_group_member),
+                group)) {
         return;
     }
 
@@ -1955,8 +2019,8 @@ static void blk_root_drained_begin(BdrvChild *child)
     /* Note that blk->root may not be accessible here yet if we are just
      * attaching to a BlockDriverState that is drained. Use child instead. */
 
-    if (atomic_fetch_inc(&blk->public.io_limits_disabled) == 0) {
-        throttle_group_restart_blk(blk);
+    if (atomic_fetch_inc(&blk->public.throttle_group_member.io_limits_disabled) == 0) {
+        throttle_group_restart_tgm(&blk->public.throttle_group_member);
     }
 }
 
@@ -1965,8 +2029,8 @@ static void blk_root_drained_end(BdrvChild *child)
     BlockBackend *blk = child->opaque;
     assert(blk->quiesce_counter);
 
-    assert(blk->public.io_limits_disabled);
-    atomic_dec(&blk->public.io_limits_disabled);
+    assert(blk->public.throttle_group_member.io_limits_disabled);
+    atomic_dec(&blk->public.throttle_group_member.io_limits_disabled);
 
     if (--blk->quiesce_counter == 0) {
         if (blk->dev_ops && blk->dev_ops->drained_end) {

block/commit.c

@@ -244,16 +244,6 @@ static int coroutine_fn bdrv_commit_top_preadv(BlockDriverState *bs,
     return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
 }
 
-static int64_t coroutine_fn bdrv_commit_top_get_block_status(
-    BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum,
-    BlockDriverState **file)
-{
-    *pnum = nb_sectors;
-    *file = bs->backing->bs;
-    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID |
-           (sector_num << BDRV_SECTOR_BITS);
-}
-
 static void bdrv_commit_top_refresh_filename(BlockDriverState *bs, QDict *opts)
 {
     bdrv_refresh_filename(bs->backing->bs);
@@ -279,7 +269,7 @@ static void bdrv_commit_top_child_perm(BlockDriverState *bs, BdrvChild *c,
 static BlockDriver bdrv_commit_top = {
     .format_name                = "commit_top",
     .bdrv_co_preadv             = bdrv_commit_top_preadv,
-    .bdrv_co_get_block_status   = bdrv_commit_top_get_block_status,
+    .bdrv_co_get_block_status   = bdrv_co_get_block_status_from_backing,
     .bdrv_refresh_filename      = bdrv_commit_top_refresh_filename,
     .bdrv_close                 = bdrv_commit_top_close,
     .bdrv_child_perm            = bdrv_commit_top_child_perm,
@@ -346,6 +336,9 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     if (commit_top_bs == NULL) {
         goto fail;
     }
+    if (!filter_node_name) {
+        commit_top_bs->implicit = true;
+    }
     commit_top_bs->total_sectors = top->total_sectors;
     bdrv_set_aio_context(commit_top_bs, bdrv_get_aio_context(top));
 

block/dirty-bitmap.c

@@ -461,7 +461,7 @@ BlockDirtyInfoList *bdrv_query_dirty_bitmaps(BlockDriverState *bs)
     QLIST_FOREACH(bm, &bs->dirty_bitmaps, list) {
         BlockDirtyInfo *info = g_new0(BlockDirtyInfo, 1);
         BlockDirtyInfoList *entry = g_new0(BlockDirtyInfoList, 1);
-        info->count = bdrv_get_dirty_count(bm);
+        info->count = bdrv_get_dirty_count(bm) << BDRV_SECTOR_BITS;
         info->granularity = bdrv_dirty_bitmap_granularity(bm);
         info->has_name = !!bm->name;
         info->name = g_strdup(bm->name);

block/dmg.c

@@ -111,7 +111,7 @@ static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,
         uncompressed_sectors = s->sectorcounts[chunk];
         break;
     case 1: /* copy */
-        uncompressed_sectors = (s->lengths[chunk] + 511) / 512;
+        uncompressed_sectors = DIV_ROUND_UP(s->lengths[chunk], 512);
         break;
     case 2: /* zero */
         /* as the all-zeroes block may be large, it is treated specially: the

block/file-posix.c

@@ -31,7 +31,6 @@
 #include "block/thread-pool.h"
 #include "qemu/iov.h"
 #include "block/raw-aio.h"
-#include "qapi/util.h"
 #include "qapi/qmp/qstring.h"
 
 #if defined(__APPLE__) && (__MACH__)
@@ -438,8 +437,9 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
     aio_default = (bdrv_flags & BDRV_O_NATIVE_AIO)
                   ? BLOCKDEV_AIO_OPTIONS_NATIVE
                   : BLOCKDEV_AIO_OPTIONS_THREADS;
-    aio = qapi_enum_parse(BlockdevAioOptions_lookup, qemu_opt_get(opts, "aio"),
-                          BLOCKDEV_AIO_OPTIONS__MAX, aio_default, &local_err);
+    aio = qapi_enum_parse(&BlockdevAioOptions_lookup,
+                          qemu_opt_get(opts, "aio"),
+                          aio_default, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         ret = -EINVAL;
@@ -447,8 +447,9 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
     }
     s->use_linux_aio = (aio == BLOCKDEV_AIO_OPTIONS_NATIVE);
 
-    locking = qapi_enum_parse(OnOffAuto_lookup, qemu_opt_get(opts, "locking"),
-                              ON_OFF_AUTO__MAX, ON_OFF_AUTO_AUTO, &local_err);
+    locking = qapi_enum_parse(&OnOffAuto_lookup,
+                              qemu_opt_get(opts, "locking"),
+                              ON_OFF_AUTO_AUTO, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         ret = -EINVAL;
@@ -457,22 +458,19 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
     switch (locking) {
     case ON_OFF_AUTO_ON:
         s->use_lock = true;
-#ifndef F_OFD_SETLK
-        fprintf(stderr,
-                "File lock requested but OFD locking syscall is unavailable, "
-                "falling back to POSIX file locks.\n"
-                "Due to the implementation, locks can be lost unexpectedly.\n");
-#endif
+        if (!qemu_has_ofd_lock()) {
+            fprintf(stderr,
+                    "File lock requested but OFD locking syscall is "
+                    "unavailable, falling back to POSIX file locks.\n"
+                    "Due to the implementation, locks can be lost "
+                    "unexpectedly.\n");
+        }
         break;
     case ON_OFF_AUTO_OFF:
         s->use_lock = false;
         break;
     case ON_OFF_AUTO_AUTO:
-#ifdef F_OFD_SETLK
-        s->use_lock = true;
-#else
-        s->use_lock = false;
-#endif
+        s->use_lock = qemu_has_ofd_lock();
         break;
     default:
         abort();
@@ -1339,6 +1337,9 @@ static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
 #if defined(CONFIG_FALLOCATE) || defined(CONFIG_XFS)
     BDRVRawState *s = aiocb->bs->opaque;
 #endif
+#ifdef CONFIG_FALLOCATE
+    int64_t len;
+#endif
 
     if (aiocb->aio_type & QEMU_AIO_BLKDEV) {
         return handle_aiocb_write_zeroes_block(aiocb);
@@ -1381,7 +1382,10 @@ static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
 #endif
 
 #ifdef CONFIG_FALLOCATE
-    if (s->has_fallocate && aiocb->aio_offset >= bdrv_getlength(aiocb->bs)) {
+    /* Last resort: we are trying to extend the file with zeroed data. This
+     * can be done via fallocate(fd, 0) */
+    len = bdrv_getlength(aiocb->bs);
+    if (s->has_fallocate && len >= 0 && aiocb->aio_offset >= len) {
         int ret = do_fallocate(s->fd, 0, aiocb->aio_offset, aiocb->aio_nbytes);
         if (ret == 0 || ret != -ENOTSUP) {
             return ret;
@@ -1722,7 +1726,7 @@ static int raw_regular_truncate(int fd, int64_t offset, PreallocMode prealloc,
     default:
         result = -ENOTSUP;
         error_setg(errp, "Unsupported preallocation mode: %s",
-                   PreallocMode_lookup[prealloc]);
+                   PreallocMode_str(prealloc));
         return result;
     }
 
@@ -1757,7 +1761,7 @@ static int raw_truncate(BlockDriverState *bs, int64_t offset,
 
     if (prealloc != PREALLOC_MODE_OFF) {
         error_setg(errp, "Preallocation mode '%s' unsupported for this "
-                   "non-regular file", PreallocMode_lookup[prealloc]);
+                   "non-regular file", PreallocMode_str(prealloc));
         return -ENOTSUP;
     }
 
@@ -1971,9 +1975,8 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
                           BDRV_SECTOR_SIZE);
     nocow = qemu_opt_get_bool(opts, BLOCK_OPT_NOCOW, false);
     buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
-    prealloc = qapi_enum_parse(PreallocMode_lookup, buf,
-                               PREALLOC_MODE__MAX, PREALLOC_MODE_OFF,
-                               &local_err);
+    prealloc = qapi_enum_parse(&PreallocMode_lookup, buf,
+                               PREALLOC_MODE_OFF, &local_err);
     g_free(buf);
     if (local_err) {
         error_propagate(errp, local_err);

block/file-win32.c

@@ -31,7 +31,6 @@
 #include "block/thread-pool.h"
 #include "qemu/iov.h"
 #include "qapi/qmp/qstring.h"
-#include "qapi/util.h"
 #include <windows.h>
 #include <winioctl.h>
 
@@ -303,8 +302,8 @@ static bool get_aio_option(QemuOpts *opts, int flags, Error **errp)
 
     aio_default = (flags & BDRV_O_NATIVE_AIO) ? BLOCKDEV_AIO_OPTIONS_NATIVE
                                               : BLOCKDEV_AIO_OPTIONS_THREADS;
-    aio = qapi_enum_parse(BlockdevAioOptions_lookup, qemu_opt_get(opts, "aio"),
-                          BLOCKDEV_AIO_OPTIONS__MAX, aio_default, errp);
+    aio = qapi_enum_parse(&BlockdevAioOptions_lookup, qemu_opt_get(opts, "aio"),
+                          aio_default, errp);
 
     switch (aio) {
     case BLOCKDEV_AIO_OPTIONS_NATIVE:
@@ -470,7 +469,7 @@ static int raw_truncate(BlockDriverState *bs, int64_t offset,
 
     if (prealloc != PREALLOC_MODE_OFF) {
         error_setg(errp, "Unsupported preallocation mode '%s'",
-                   PreallocMode_lookup[prealloc]);
+                   PreallocMode_str(prealloc));
         return -ENOTSUP;
     }
 

block/gluster.c

@@ -12,7 +12,6 @@
 #include "block/block_int.h"
 #include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
-#include "qapi/util.h"
 #include "qemu/uri.h"
 #include "qemu/error-report.h"
 #include "qemu/cutils.h"
@@ -544,8 +543,7 @@ static int qemu_gluster_parse_json(BlockdevOptionsGluster *gconf,
         if (!strcmp(ptr, "tcp")) {
             ptr = "inet";       /* accept legacy "tcp" */
         }
-        type = qapi_enum_parse(SocketAddressType_lookup, ptr,
-                               SOCKET_ADDRESS_TYPE__MAX, -1, NULL);
+        type = qapi_enum_parse(&SocketAddressType_lookup, ptr, -1, NULL);
         if (type != SOCKET_ADDRESS_TYPE_INET
             && type != SOCKET_ADDRESS_TYPE_UNIX) {
             error_setg(&local_err,
@@ -1002,8 +1000,7 @@ static int qemu_gluster_create(const char *filename,
                           BDRV_SECTOR_SIZE);
 
     tmp = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
-    prealloc = qapi_enum_parse(PreallocMode_lookup, tmp,
-                               PREALLOC_MODE__MAX, PREALLOC_MODE_OFF,
+    prealloc = qapi_enum_parse(&PreallocMode_lookup, tmp, PREALLOC_MODE_OFF,
                                &local_err);
     g_free(tmp);
     if (local_err) {
@@ -1050,7 +1047,7 @@ static int qemu_gluster_create(const char *filename,
     default:
         ret = -EINVAL;
         error_setg(errp, "Unsupported preallocation mode: %s",
-                   PreallocMode_lookup[prealloc]);
+                   PreallocMode_str(prealloc));
         break;
     }
 
@@ -1102,7 +1099,7 @@ static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset,
 
     if (prealloc != PREALLOC_MODE_OFF) {
         error_setg(errp, "Unsupported preallocation mode '%s'",
-                   PreallocMode_lookup[prealloc]);
+                   PreallocMode_str(prealloc));
         return -ENOTSUP;
     }
 

block/io.c

@@ -1135,6 +1135,8 @@ int coroutine_fn bdrv_co_preadv(BdrvChild *child,
     bool use_local_qiov = false;
     int ret;
 
+    trace_bdrv_co_preadv(child->bs, offset, bytes, flags);
+
     if (!drv) {
         return -ENOMEDIUM;
     }
@@ -1207,8 +1209,6 @@ static int coroutine_fn bdrv_co_do_readv(BdrvChild *child,
 int coroutine_fn bdrv_co_readv(BdrvChild *child, int64_t sector_num,
                                int nb_sectors, QEMUIOVector *qiov)
 {
-    trace_bdrv_co_readv(child->bs, sector_num, nb_sectors);
-
     return bdrv_co_do_readv(child, sector_num, nb_sectors, qiov, 0);
 }
 
@@ -1526,6 +1526,8 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
     bool use_local_qiov = false;
     int ret;
 
+    trace_bdrv_co_pwritev(child->bs, offset, bytes, flags);
+
     if (!bs->drv) {
         return -ENOMEDIUM;
     }
@@ -1660,8 +1662,6 @@ static int coroutine_fn bdrv_co_do_writev(BdrvChild *child,
 int coroutine_fn bdrv_co_writev(BdrvChild *child, int64_t sector_num,
     int nb_sectors, QEMUIOVector *qiov)
 {
-    trace_bdrv_co_writev(child->bs, sector_num, nb_sectors);
-
     return bdrv_co_do_writev(child, sector_num, nb_sectors, qiov, 0);
 }
 
@@ -1714,6 +1714,32 @@ typedef struct BdrvCoGetBlockStatusData {
     bool done;
 } BdrvCoGetBlockStatusData;
 
+int64_t coroutine_fn bdrv_co_get_block_status_from_file(BlockDriverState *bs,
+                                                        int64_t sector_num,
+                                                        int nb_sectors,
+                                                        int *pnum,
+                                                        BlockDriverState **file)
+{
+    assert(bs->file && bs->file->bs);
+    *pnum = nb_sectors;
+    *file = bs->file->bs;
+    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID |
+           (sector_num << BDRV_SECTOR_BITS);
+}
+
+int64_t coroutine_fn bdrv_co_get_block_status_from_backing(BlockDriverState *bs,
+                                                           int64_t sector_num,
+                                                           int nb_sectors,
+                                                           int *pnum,
+                                                           BlockDriverState **file)
+{
+    assert(bs->backing && bs->backing->bs);
+    *pnum = nb_sectors;
+    *file = bs->backing->bs;
+    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID |
+           (sector_num << BDRV_SECTOR_BITS);
+}
+
 /*
  * Returns the allocation status of the specified sectors.
  * Drivers not implementing the functionality are assumed to not support

block/iscsi.c

@@ -34,15 +34,20 @@
 #include "qemu/bitops.h"
 #include "qemu/bitmap.h"
 #include "block/block_int.h"
-#include "block/scsi.h"
+#include "scsi/constants.h"
 #include "qemu/iov.h"
 #include "qemu/uuid.h"
 #include "qmp-commands.h"
 #include "qapi/qmp/qstring.h"
 #include "crypto/secret.h"
+#include "scsi/utils.h"
 
+/* Conflict between scsi/utils.h and libiscsi! :( */
+#define SCSI_XFER_NONE ISCSI_XFER_NONE
 #include <iscsi/iscsi.h>
 #include <iscsi/scsi-lowlevel.h>
+#undef SCSI_XFER_NONE
+QEMU_BUILD_BUG_ON((int)SCSI_XFER_NONE != (int)ISCSI_XFER_NONE);
 
 #ifdef __linux__
 #include <scsi/sg.h>
@@ -209,47 +214,9 @@ static inline unsigned exp_random(double mean)
 
 static int iscsi_translate_sense(struct scsi_sense *sense)
 {
-    int ret;
-
-    switch (sense->key) {
-    case SCSI_SENSE_NOT_READY:
-        return -EBUSY;
-    case SCSI_SENSE_DATA_PROTECTION:
-        return -EACCES;
-    case SCSI_SENSE_COMMAND_ABORTED:
-        return -ECANCELED;
-    case SCSI_SENSE_ILLEGAL_REQUEST:
-        /* Parse ASCQ */
-        break;
-    default:
-        return -EIO;
-    }
-    switch (sense->ascq) {
-    case SCSI_SENSE_ASCQ_PARAMETER_LIST_LENGTH_ERROR:
-    case SCSI_SENSE_ASCQ_INVALID_OPERATION_CODE:
-    case SCSI_SENSE_ASCQ_INVALID_FIELD_IN_CDB:
-    case SCSI_SENSE_ASCQ_INVALID_FIELD_IN_PARAMETER_LIST:
-        ret = -EINVAL;
-        break;
-    case SCSI_SENSE_ASCQ_LBA_OUT_OF_RANGE:
-        ret = -ENOSPC;
-        break;
-    case SCSI_SENSE_ASCQ_LOGICAL_UNIT_NOT_SUPPORTED:
-        ret = -ENOTSUP;
-        break;
-    case SCSI_SENSE_ASCQ_MEDIUM_NOT_PRESENT:
-    case SCSI_SENSE_ASCQ_MEDIUM_NOT_PRESENT_TRAY_CLOSED:
-    case SCSI_SENSE_ASCQ_MEDIUM_NOT_PRESENT_TRAY_OPEN:
-        ret = -ENOMEDIUM;
-        break;
-    case SCSI_SENSE_ASCQ_WRITE_PROTECTED:
-        ret = -EACCES;
-        break;
-    default:
-        ret = -EIO;
-        break;
-    }
-    return ret;
+    return - scsi_sense_to_errno(sense->key,
+                                 (sense->ascq & 0xFF00) >> 8,
+                                 sense->ascq & 0xFF);
 }
 
 /* Called (via iscsi_service) with QemuMutex held.  */
@@ -2087,7 +2054,7 @@ static int iscsi_truncate(BlockDriverState *bs, int64_t offset,
 
     if (prealloc != PREALLOC_MODE_OFF) {
         error_setg(errp, "Unsupported preallocation mode '%s'",
-                   PreallocMode_lookup[prealloc]);
+                   PreallocMode_str(prealloc));
         return -ENOTSUP;
     }
 

block/mirror.c

@@ -1059,16 +1059,6 @@ static int coroutine_fn bdrv_mirror_top_flush(BlockDriverState *bs)
     return bdrv_co_flush(bs->backing->bs);
 }
 
-static int64_t coroutine_fn bdrv_mirror_top_get_block_status(
-    BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum,
-    BlockDriverState **file)
-{
-    *pnum = nb_sectors;
-    *file = bs->backing->bs;
-    return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID |
-           (sector_num << BDRV_SECTOR_BITS);
-}
-
 static int coroutine_fn bdrv_mirror_top_pwrite_zeroes(BlockDriverState *bs,
     int64_t offset, int bytes, BdrvRequestFlags flags)
 {
@@ -1115,7 +1105,7 @@ static BlockDriver bdrv_mirror_top = {
     .bdrv_co_pwrite_zeroes      = bdrv_mirror_top_pwrite_zeroes,
     .bdrv_co_pdiscard           = bdrv_mirror_top_pdiscard,
     .bdrv_co_flush              = bdrv_mirror_top_flush,
-    .bdrv_co_get_block_status   = bdrv_mirror_top_get_block_status,
+    .bdrv_co_get_block_status   = bdrv_co_get_block_status_from_backing,
     .bdrv_refresh_filename      = bdrv_mirror_top_refresh_filename,
     .bdrv_close                 = bdrv_mirror_top_close,
     .bdrv_child_perm            = bdrv_mirror_top_child_perm,
@@ -1134,6 +1124,7 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
                              const BlockJobDriver *driver,
                              bool is_none_mode, BlockDriverState *base,
                              bool auto_complete, const char *filter_node_name,
+                             bool is_mirror,
                              Error **errp)
 {
     MirrorBlockJob *s;
@@ -1168,6 +1159,9 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
     if (mirror_top_bs == NULL) {
         return;
     }
+    if (!filter_node_name) {
+        mirror_top_bs->implicit = true;
+    }
     mirror_top_bs->total_sectors = bs->total_sectors;
     bdrv_set_aio_context(mirror_top_bs, bdrv_get_aio_context(bs));
 
@@ -1219,6 +1213,15 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
     if (ret < 0) {
         goto fail;
     }
+    if (is_mirror) {
+        /* XXX: Mirror target could be a NBD server of target QEMU in the case
+         * of non-shared block migration. To allow migration completion, we
+         * have to allow "inactivate" of the target BB.  When that happens, we
+         * know the job is drained, and the vcpus are stopped, so no write
+         * operation will be performed. Block layer already has assertions to
+         * ensure that. */
+        blk_set_force_allow_inactivate(s->target);
+    }
 
     s->replaces = g_strdup(replaces);
     s->on_source_error = on_source_error;
@@ -1303,7 +1306,7 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
                      speed, granularity, buf_size, backing_mode,
                      on_source_error, on_target_error, unmap, NULL, NULL,
                      &mirror_job_driver, is_none_mode, base, false,
-                     filter_node_name, errp);
+                     filter_node_name, true, errp);
 }
 
 void commit_active_start(const char *job_id, BlockDriverState *bs,
@@ -1326,7 +1329,7 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
                      MIRROR_LEAVE_BACKING_CHAIN,
                      on_error, on_error, true, cb, opaque,
                      &commit_active_job_driver, false, base, auto_complete,
-                     filter_node_name, &local_err);
+                     filter_node_name, false, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         goto error_restore_flags;

block/nbd-client.c

@@ -34,13 +34,15 @@
 #define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
 #define INDEX_TO_HANDLE(bs, index)  ((index)  ^ ((uint64_t)(intptr_t)bs))
 
-static void nbd_recv_coroutines_enter_all(NBDClientSession *s)
+static void nbd_recv_coroutines_wake_all(NBDClientSession *s)
 {
     int i;
 
     for (i = 0; i < MAX_NBD_REQUESTS; i++) {
-        if (s->recv_coroutine[i]) {
-            aio_co_wake(s->recv_coroutine[i]);
+        NBDClientRequest *req = &s->requests[i];
+
+        if (req->coroutine && req->receiving) {
+            aio_co_wake(req->coroutine);
         }
     }
 }
@@ -70,10 +72,10 @@ static coroutine_fn void nbd_read_reply_entry(void *opaque)
 {
     NBDClientSession *s = opaque;
     uint64_t i;
-    int ret;
+    int ret = 0;
     Error *local_err = NULL;
 
-    for (;;) {
+    while (!s->quit) {
         assert(s->reply.handle == 0);
         ret = nbd_receive_reply(s->ioc, &s->reply, &local_err);
         if (ret < 0) {
@@ -88,26 +90,29 @@ static coroutine_fn void nbd_read_reply_entry(void *opaque)
          * one coroutine is called until the reply finishes.
          */
         i = HANDLE_TO_INDEX(s, s->reply.handle);
-        if (i >= MAX_NBD_REQUESTS || !s->recv_coroutine[i]) {
+        if (i >= MAX_NBD_REQUESTS ||
+            !s->requests[i].coroutine ||
+            !s->requests[i].receiving) {
             break;
         }
 
-        /* We're woken up by the recv_coroutine itself.  Note that there
+        /* We're woken up again by the request itself.  Note that there
          * is no race between yielding and reentering read_reply_co.  This
          * is because:
          *
-         * - if recv_coroutine[i] runs on the same AioContext, it is only
+         * - if the request runs on the same AioContext, it is only
          *   entered after we yield
          *
-         * - if recv_coroutine[i] runs on a different AioContext, reentering
+         * - if the request runs on a different AioContext, reentering
          *   read_reply_co happens through a bottom half, which can only
          *   run after we yield.
          */
-        aio_co_wake(s->recv_coroutine[i]);
+        aio_co_wake(s->requests[i].coroutine);
         qemu_coroutine_yield();
     }
 
-    nbd_recv_coroutines_enter_all(s);
+    s->quit = true;
+    nbd_recv_coroutines_wake_all(s);
     s->read_reply_co = NULL;
 }
 
@@ -116,7 +121,7 @@ static int nbd_co_send_request(BlockDriverState *bs,
                                QEMUIOVector *qiov)
 {
     NBDClientSession *s = nbd_get_client_session(bs);
-    int rc, ret, i;
+    int rc, i;
 
     qemu_co_mutex_lock(&s->send_mutex);
     while (s->in_flight == MAX_NBD_REQUESTS) {
@@ -125,28 +130,35 @@ static int nbd_co_send_request(BlockDriverState *bs,
     s->in_flight++;
 
     for (i = 0; i < MAX_NBD_REQUESTS; i++) {
-        if (s->recv_coroutine[i] == NULL) {
-            s->recv_coroutine[i] = qemu_coroutine_self();
+        if (s->requests[i].coroutine == NULL) {
             break;
         }
     }
 
     g_assert(qemu_in_coroutine());
     assert(i < MAX_NBD_REQUESTS);
+
+    s->requests[i].coroutine = qemu_coroutine_self();
+    s->requests[i].receiving = false;
+
     request->handle = INDEX_TO_HANDLE(s, i);
 
+    if (s->quit) {
+        rc = -EIO;
+        goto err;
+    }
     if (!s->ioc) {
-        qemu_co_mutex_unlock(&s->send_mutex);
-        return -EPIPE;
+        rc = -EPIPE;
+        goto err;
     }
 
     if (qiov) {
         qio_channel_set_cork(s->ioc, true);
         rc = nbd_send_request(s->ioc, request);
-        if (rc >= 0) {
-            ret = nbd_rwv(s->ioc, qiov->iov, qiov->niov, request->len, false,
-                          NULL);
-            if (ret != request->len) {
+        if (rc >= 0 && !s->quit) {
+            assert(request->len == iov_size(qiov->iov, qiov->niov));
+            if (qio_channel_writev_all(s->ioc, qiov->iov, qiov->niov,
+                                       NULL) < 0) {
                 rc = -EIO;
             }
         }
@@ -154,6 +166,14 @@ static int nbd_co_send_request(BlockDriverState *bs,
     } else {
         rc = nbd_send_request(s->ioc, request);
     }
+
+err:
+    if (rc < 0) {
+        s->quit = true;
+        s->requests[i].coroutine = NULL;
+        s->in_flight--;
+        qemu_co_queue_next(&s->free_sema);
+    }
     qemu_co_mutex_unlock(&s->send_mutex);
     return rc;
 }
@@ -163,35 +183,30 @@ static void nbd_co_receive_reply(NBDClientSession *s,
                                  NBDReply *reply,
                                  QEMUIOVector *qiov)
 {
-    int ret;
+    int i = HANDLE_TO_INDEX(s, request->handle);
 
     /* Wait until we're woken up by nbd_read_reply_entry.  */
+    s->requests[i].receiving = true;
     qemu_coroutine_yield();
+    s->requests[i].receiving = false;
     *reply = s->reply;
-    if (reply->handle != request->handle ||
-        !s->ioc) {
+    if (reply->handle != request->handle || !s->ioc || s->quit) {
         reply->error = EIO;
     } else {
         if (qiov && reply->error == 0) {
-            ret = nbd_rwv(s->ioc, qiov->iov, qiov->niov, request->len, true,
-                          NULL);
-            if (ret != request->len) {
+            assert(request->len == iov_size(qiov->iov, qiov->niov));
+            if (qio_channel_readv_all(s->ioc, qiov->iov, qiov->niov,
+                                      NULL) < 0) {
                 reply->error = EIO;
+                s->quit = true;
             }
         }
 
         /* Tell the read handler to read another header.  */
         s->reply.handle = 0;
     }
-}
 
-static void nbd_coroutine_end(BlockDriverState *bs,
-                              NBDRequest *request)
-{
-    NBDClientSession *s = nbd_get_client_session(bs);
-    int i = HANDLE_TO_INDEX(s, request->handle);
-
-    s->recv_coroutine[i] = NULL;
+    s->requests[i].coroutine = NULL;
 
     /* Kick the read_reply_co to get the next reply.  */
     if (s->read_reply_co) {
@@ -204,29 +219,40 @@ static void nbd_coroutine_end(BlockDriverState *bs,
     qemu_co_mutex_unlock(&s->send_mutex);
 }
 
+static int nbd_co_request(BlockDriverState *bs,
+                          NBDRequest *request,
+                          QEMUIOVector *qiov)
+{
+    NBDClientSession *client = nbd_get_client_session(bs);
+    NBDReply reply;
+    int ret;
+
+    assert(!qiov || request->type == NBD_CMD_WRITE ||
+           request->type == NBD_CMD_READ);
+    ret = nbd_co_send_request(bs, request,
+                              request->type == NBD_CMD_WRITE ? qiov : NULL);
+    if (ret < 0) {
+        reply.error = -ret;
+    } else {
+        nbd_co_receive_reply(client, request, &reply,
+                             request->type == NBD_CMD_READ ? qiov : NULL);
+    }
+    return -reply.error;
+}
+
 int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset,
                          uint64_t bytes, QEMUIOVector *qiov, int flags)
 {
-    NBDClientSession *client = nbd_get_client_session(bs);
     NBDRequest request = {
         .type = NBD_CMD_READ,
         .from = offset,
         .len = bytes,
     };
-    NBDReply reply;
-    ssize_t ret;
 
     assert(bytes <= NBD_MAX_BUFFER_SIZE);
     assert(!flags);
 
-    ret = nbd_co_send_request(bs, &request, NULL);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, qiov);
-    }
-    nbd_coroutine_end(bs, &request);
-    return -reply.error;
+    return nbd_co_request(bs, &request, qiov);
 }
 
 int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset,
@@ -238,8 +264,6 @@ int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset,
         .from = offset,
         .len = bytes,
     };
-    NBDReply reply;
-    ssize_t ret;
 
     if (flags & BDRV_REQ_FUA) {
         assert(client->info.flags & NBD_FLAG_SEND_FUA);
@@ -248,27 +272,18 @@ int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset,
 
     assert(bytes <= NBD_MAX_BUFFER_SIZE);
 
-    ret = nbd_co_send_request(bs, &request, qiov);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL);
-    }
-    nbd_coroutine_end(bs, &request);
-    return -reply.error;
+    return nbd_co_request(bs, &request, qiov);
 }
 
 int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
                                 int bytes, BdrvRequestFlags flags)
 {
-    ssize_t ret;
     NBDClientSession *client = nbd_get_client_session(bs);
     NBDRequest request = {
         .type = NBD_CMD_WRITE_ZEROES,
         .from = offset,
         .len = bytes,
     };
-    NBDReply reply;
 
     if (!(client->info.flags & NBD_FLAG_SEND_WRITE_ZEROES)) {
         return -ENOTSUP;
@@ -282,22 +297,13 @@ int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
         request.flags |= NBD_CMD_FLAG_NO_HOLE;
     }
 
-    ret = nbd_co_send_request(bs, &request, NULL);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL);
-    }
-    nbd_coroutine_end(bs, &request);
-    return -reply.error;
+    return nbd_co_request(bs, &request, NULL);
 }
 
 int nbd_client_co_flush(BlockDriverState *bs)
 {
     NBDClientSession *client = nbd_get_client_session(bs);
     NBDRequest request = { .type = NBD_CMD_FLUSH };
-    NBDReply reply;
-    ssize_t ret;
 
     if (!(client->info.flags & NBD_FLAG_SEND_FLUSH)) {
         return 0;
@@ -306,14 +312,7 @@ int nbd_client_co_flush(BlockDriverState *bs)
     request.from = 0;
     request.len = 0;
 
-    ret = nbd_co_send_request(bs, &request, NULL);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL);
-    }
-    nbd_coroutine_end(bs, &request);
-    return -reply.error;
+    return nbd_co_request(bs, &request, NULL);
 }
 
 int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes)
@@ -324,22 +323,12 @@ int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes)
         .from = offset,
         .len = bytes,
     };
-    NBDReply reply;
-    ssize_t ret;
 
     if (!(client->info.flags & NBD_FLAG_SEND_TRIM)) {
         return 0;
     }
 
-    ret = nbd_co_send_request(bs, &request, NULL);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(client, &request, &reply, NULL);
-    }
-    nbd_coroutine_end(bs, &request);
-    return -reply.error;
-
+    return nbd_co_request(bs, &request, NULL);
 }
 
 void nbd_client_detach_aio_context(BlockDriverState *bs)

block/nbd-client.h

@@ -17,6 +17,11 @@
 
 #define MAX_NBD_REQUESTS    16
 
+typedef struct {
+    Coroutine *coroutine;
+    bool receiving;         /* waiting for read_reply_co? */
+} NBDClientRequest;
+
 typedef struct NBDClientSession {
     QIOChannelSocket *sioc; /* The master data channel */
     QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */
@@ -27,8 +32,9 @@ typedef struct NBDClientSession {
     Coroutine *read_reply_co;
     int in_flight;
 
-    Coroutine *recv_coroutine[MAX_NBD_REQUESTS];
+    NBDClientRequest requests[MAX_NBD_REQUESTS];
     NBDReply reply;
+    bool quit;
 } NBDClientSession;
 
 NBDClientSession *nbd_get_client_session(BlockDriverState *bs);

block/nfs.c

@@ -433,19 +433,23 @@ static void nfs_client_close(NFSClient *client)
     if (client->context) {
         if (client->fh) {
             nfs_close(client->context, client->fh);
+            client->fh = NULL;
         }
         aio_set_fd_handler(client->aio_context, nfs_get_fd(client->context),
                            false, NULL, NULL, NULL, NULL);
         nfs_destroy_context(client->context);
+        client->context = NULL;
     }
-    memset(client, 0, sizeof(NFSClient));
+    g_free(client->path);
+    qemu_mutex_destroy(&client->mutex);
+    qapi_free_NFSServer(client->server);
+    client->server = NULL;
 }
 
 static void nfs_file_close(BlockDriverState *bs)
 {
     NFSClient *client = bs->opaque;
     nfs_client_close(client);
-    qemu_mutex_destroy(&client->mutex);
 }
 
 static NFSServer *nfs_config(QDict *options, Error **errp)
@@ -498,6 +502,7 @@ static int64_t nfs_client_open(NFSClient *client, QDict *options,
     struct stat st;
     char *file = NULL, *strp = NULL;
 
+    qemu_mutex_init(&client->mutex);
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
@@ -660,7 +665,7 @@ static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
     if (ret < 0) {
         return ret;
     }
-    qemu_mutex_init(&client->mutex);
+
     bs->total_sectors = ret;
     ret = 0;
     return ret;
@@ -767,7 +772,7 @@ static int nfs_file_truncate(BlockDriverState *bs, int64_t offset,
 
     if (prealloc != PREALLOC_MODE_OFF) {
         error_setg(errp, "Unsupported preallocation mode '%s'",
-                   PreallocMode_lookup[prealloc]);
+                   PreallocMode_str(prealloc));
         return -ENOTSUP;
     }
 

block/null.c

@@ -29,11 +29,6 @@ static QemuOptsList runtime_opts = {
     .name = "null",
     .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
     .desc = {
-        {
-            .name = "filename",
-            .type = QEMU_OPT_STRING,
-            .help = "",
-        },
         {
             .name = BLOCK_OPT_SIZE,
             .type = QEMU_OPT_SIZE,
@@ -54,6 +49,30 @@ static QemuOptsList runtime_opts = {
     },
 };
 
+static void null_co_parse_filename(const char *filename, QDict *options,
+                                   Error **errp)
+{
+    /* This functions only exists so that a null-co:// filename is accepted
+     * with the null-co driver. */
+    if (strcmp(filename, "null-co://")) {
+        error_setg(errp, "The only allowed filename for this driver is "
+                         "'null-co://'");
+        return;
+    }
+}
+
+static void null_aio_parse_filename(const char *filename, QDict *options,
+                                    Error **errp)
+{
+    /* This functions only exists so that a null-aio:// filename is accepted
+     * with the null-aio driver. */
+    if (strcmp(filename, "null-aio://")) {
+        error_setg(errp, "The only allowed filename for this driver is "
+                         "'null-aio://'");
+        return;
+    }
+}
+
 static int null_file_open(BlockDriverState *bs, QDict *options, int flags,
                           Error **errp)
 {
@@ -242,6 +261,7 @@ static BlockDriver bdrv_null_co = {
     .instance_size          = sizeof(BDRVNullState),
 
     .bdrv_file_open         = null_file_open,
+    .bdrv_parse_filename    = null_co_parse_filename,
     .bdrv_close             = null_close,
     .bdrv_getlength         = null_getlength,
 
@@ -261,6 +281,7 @@ static BlockDriver bdrv_null_aio = {
     .instance_size          = sizeof(BDRVNullState),
 
     .bdrv_file_open         = null_file_open,
+    .bdrv_parse_filename    = null_aio_parse_filename,
     .bdrv_close             = null_close,
     .bdrv_getlength         = null_getlength,
 

block/parallels.c

@@ -35,7 +35,6 @@
 #include "qemu/module.h"
 #include "qemu/bswap.h"
 #include "qemu/bitmap.h"
-#include "qapi/util.h"
 
 /**************************************************************/
 
@@ -69,13 +68,14 @@ typedef enum ParallelsPreallocMode {
     PRL_PREALLOC_MODE__MAX = 2,
 } ParallelsPreallocMode;
 
-static const char *prealloc_mode_lookup[] = {
-    "falloc",
-    "truncate",
-    NULL,
+static QEnumLookup prealloc_mode_lookup = {
+    .array = (const char *const[]) {
+        "falloc",
+        "truncate",
+    },
+    .size = PRL_PREALLOC_MODE__MAX
 };
 
-
 typedef struct BDRVParallelsState {
     /** Locking is conservative, the lock protects
      *   - image file extending (truncate, fallocate)
@@ -192,7 +192,7 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
                                  int nb_sectors, int *pnum)
 {
     BDRVParallelsState *s = bs->opaque;
-    int64_t pos, space, idx, to_allocate, i;
+    int64_t pos, space, idx, to_allocate, i, len;
 
     pos = block_status(s, sector_num, nb_sectors, pnum);
     if (pos > 0) {
@@ -214,7 +214,11 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
     assert(idx < s->bat_size && idx + to_allocate <= s->bat_size);
 
     space = to_allocate * s->tracks;
-    if (s->data_end + space > bdrv_getlength(bs->file->bs) >> BDRV_SECTOR_BITS) {
+    len = bdrv_getlength(bs->file->bs);
+    if (len < 0) {
+        return len;
+    }
+    if (s->data_end + space > (len >> BDRV_SECTOR_BITS)) {
         int ret;
         space += s->prealloc_size;
         if (s->prealloc_mode == PRL_PREALLOC_MODE_FALLOCATE) {
@@ -692,16 +696,15 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
         qemu_opt_get_size_del(opts, PARALLELS_OPT_PREALLOC_SIZE, 0);
     s->prealloc_size = MAX(s->tracks, s->prealloc_size >> BDRV_SECTOR_BITS);
     buf = qemu_opt_get_del(opts, PARALLELS_OPT_PREALLOC_MODE);
-    s->prealloc_mode = qapi_enum_parse(prealloc_mode_lookup, buf,
-            PRL_PREALLOC_MODE__MAX, PRL_PREALLOC_MODE_FALLOCATE, &local_err);
+    s->prealloc_mode = qapi_enum_parse(&prealloc_mode_lookup, buf,
+                                       PRL_PREALLOC_MODE_FALLOCATE,
+                                       &local_err);
     g_free(buf);
     if (local_err != NULL) {
         goto fail_options;
     }
 
-    if (!(flags & BDRV_O_RESIZE) || !bdrv_has_zero_init(bs->file->bs) ||
-            bdrv_truncate(bs->file, bdrv_getlength(bs->file->bs),
-                          PREALLOC_MODE_OFF, NULL) != 0) {
+    if (!bdrv_has_zero_init(bs->file->bs)) {
         s->prealloc_mode = PRL_PREALLOC_MODE_FALLOCATE;
     }
 

block/qapi.c

@@ -64,13 +64,13 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
         info->backing_file = g_strdup(bs->backing_file);
     }
 
-    info->backing_file_depth = bdrv_get_backing_file_depth(bs);
     info->detect_zeroes = bs->detect_zeroes;
 
-    if (blk && blk_get_public(blk)->throttle_state) {
+    if (blk && blk_get_public(blk)->throttle_group_member.throttle_state) {
         ThrottleConfig cfg;
+        BlockBackendPublic *blkp = blk_get_public(blk);
 
-        throttle_group_get_config(blk, &cfg);
+        throttle_group_get_config(&blkp->throttle_group_member, &cfg);
 
         info->bps     = cfg.buckets[THROTTLE_BPS_TOTAL].avg;
         info->bps_rd  = cfg.buckets[THROTTLE_BPS_READ].avg;
@@ -118,13 +118,15 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
         info->iops_size = cfg.op_size;
 
         info->has_group = true;
-        info->group = g_strdup(throttle_group_get_name(blk));
+        info->group =
+            g_strdup(throttle_group_get_name(&blkp->throttle_group_member));
     }
 
     info->write_threshold = bdrv_write_threshold_get(bs);
 
     bs0 = bs;
     p_image_info = &info->image;
+    info->backing_file_depth = 0;
     while (1) {
         Error *local_err = NULL;
         bdrv_query_image_info(bs0, p_image_info, &local_err);
@@ -133,13 +135,22 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
             qapi_free_BlockDeviceInfo(info);
             return NULL;
         }
+
         if (bs0->drv && bs0->backing) {
+            info->backing_file_depth++;
             bs0 = bs0->backing->bs;
             (*p_image_info)->has_backing_image = true;
             p_image_info = &((*p_image_info)->backing_image);
         } else {
             break;
         }
+
+        /* Skip automatically inserted nodes that the user isn't aware of for
+         * query-block (blk != NULL), but not for query-named-block-nodes */
+        while (blk && bs0->drv && bs0->implicit) {
+            bs0 = backing_bs(bs0);
+            assert(bs0);
+        }
     }
 
     return info;
@@ -324,6 +335,11 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
     BlockDriverState *bs = blk_bs(blk);
     char *qdev;
 
+    /* Skip automatically inserted nodes that the user isn't aware of */
+    while (bs && bs->drv && bs->implicit) {
+        bs = backing_bs(bs);
+    }
+
     info->device = g_strdup(blk_name(blk));
     info->type = g_strdup("unknown");
     info->locked = blk_dev_is_medium_locked(blk);
@@ -434,8 +450,8 @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
     }
 }
 
-static BlockStats *bdrv_query_bds_stats(const BlockDriverState *bs,
-                                 bool query_backing)
+static BlockStats *bdrv_query_bds_stats(BlockDriverState *bs,
+                                        bool blk_level)
 {
     BlockStats *s = NULL;
 
@@ -446,6 +462,14 @@ static BlockStats *bdrv_query_bds_stats(const BlockDriverState *bs,
         return s;
     }
 
+    /* Skip automatically inserted nodes that the user isn't aware of in
+     * a BlockBackend-level command. Stay at the exact node for a node-level
+     * command. */
+    while (blk_level && bs->drv && bs->implicit) {
+        bs = backing_bs(bs);
+        assert(bs);
+    }
+
     if (bdrv_get_node_name(bs)[0]) {
         s->has_node_name = true;
         s->node_name = g_strdup(bdrv_get_node_name(bs));
@@ -455,12 +479,12 @@ static BlockStats *bdrv_query_bds_stats(const BlockDriverState *bs,
 
     if (bs->file) {
         s->has_parent = true;
-        s->parent = bdrv_query_bds_stats(bs->file->bs, query_backing);
+        s->parent = bdrv_query_bds_stats(bs->file->bs, blk_level);
     }
 
-    if (query_backing && bs->backing) {
+    if (blk_level && bs->backing) {
         s->has_backing = true;
-        s->backing = bdrv_query_bds_stats(bs->backing->bs, query_backing);
+        s->backing = bdrv_query_bds_stats(bs->backing->bs, blk_level);
     }
 
     return s;

block/qcow.c

@@ -347,19 +347,22 @@ static int qcow_reopen_prepare(BDRVReopenState *state,
  * 'compressed_size'. 'compressed_size' must be > 0 and <
  * cluster_size
  *
- * return 0 if not allocated.
+ * return 0 if not allocated, 1 if *result is assigned, and negative
+ * errno on failure.
  */
-static uint64_t get_cluster_offset(BlockDriverState *bs,
-                                   uint64_t offset, int allocate,
-                                   int compressed_size,
-                                   int n_start, int n_end)
+static int get_cluster_offset(BlockDriverState *bs,
+                              uint64_t offset, int allocate,
+                              int compressed_size,
+                              int n_start, int n_end, uint64_t *result)
 {
     BDRVQcowState *s = bs->opaque;
-    int min_index, i, j, l1_index, l2_index;
-    uint64_t l2_offset, *l2_table, cluster_offset, tmp;
+    int min_index, i, j, l1_index, l2_index, ret;
+    int64_t l2_offset;
+    uint64_t *l2_table, cluster_offset, tmp;
     uint32_t min_count;
     int new_l2_table;
 
+    *result = 0;
     l1_index = offset >> (s->l2_bits + s->cluster_bits);
     l2_offset = s->l1_table[l1_index];
     new_l2_table = 0;
@@ -368,15 +371,20 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
             return 0;
         /* allocate a new l2 entry */
         l2_offset = bdrv_getlength(bs->file->bs);
+        if (l2_offset < 0) {
+            return l2_offset;
+        }
         /* round to cluster size */
-        l2_offset = (l2_offset + s->cluster_size - 1) & ~(s->cluster_size - 1);
+        l2_offset = QEMU_ALIGN_UP(l2_offset, s->cluster_size);
         /* update the L1 entry */
         s->l1_table[l1_index] = l2_offset;
         tmp = cpu_to_be64(l2_offset);
-        if (bdrv_pwrite_sync(bs->file,
-                s->l1_table_offset + l1_index * sizeof(tmp),
-                &tmp, sizeof(tmp)) < 0)
-            return 0;
+        ret = bdrv_pwrite_sync(bs->file,
+                               s->l1_table_offset + l1_index * sizeof(tmp),
+                               &tmp, sizeof(tmp));
+        if (ret < 0) {
+            return ret;
+        }
         new_l2_table = 1;
     }
     for(i = 0; i < L2_CACHE_SIZE; i++) {
@@ -403,14 +411,17 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
     l2_table = s->l2_cache + (min_index << s->l2_bits);
     if (new_l2_table) {
         memset(l2_table, 0, s->l2_size * sizeof(uint64_t));
-        if (bdrv_pwrite_sync(bs->file, l2_offset, l2_table,
-                s->l2_size * sizeof(uint64_t)) < 0)
-            return 0;
+        ret = bdrv_pwrite_sync(bs->file, l2_offset, l2_table,
+                               s->l2_size * sizeof(uint64_t));
+        if (ret < 0) {
+            return ret;
+        }
     } else {
-        if (bdrv_pread(bs->file, l2_offset, l2_table,
-                       s->l2_size * sizeof(uint64_t)) !=
-            s->l2_size * sizeof(uint64_t))
-            return 0;
+        ret = bdrv_pread(bs->file, l2_offset, l2_table,
+                         s->l2_size * sizeof(uint64_t));
+        if (ret < 0) {
+            return ret;
+        }
     }
     s->l2_cache_offsets[min_index] = l2_offset;
     s->l2_cache_counts[min_index] = 1;
@@ -427,24 +438,36 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
             /* if the cluster is already compressed, we must
                decompress it in the case it is not completely
                overwritten */
-            if (decompress_cluster(bs, cluster_offset) < 0)
-                return 0;
+            if (decompress_cluster(bs, cluster_offset) < 0) {
+                return -EIO;
+            }
             cluster_offset = bdrv_getlength(bs->file->bs);
-            cluster_offset = (cluster_offset + s->cluster_size - 1) &
-                ~(s->cluster_size - 1);
+            if ((int64_t) cluster_offset < 0) {
+                return cluster_offset;
+            }
+            cluster_offset = QEMU_ALIGN_UP(cluster_offset, s->cluster_size);
             /* write the cluster content */
-            if (bdrv_pwrite(bs->file, cluster_offset, s->cluster_cache,
-                            s->cluster_size) !=
-                s->cluster_size)
-                return -1;
+            ret = bdrv_pwrite(bs->file, cluster_offset, s->cluster_cache,
+                              s->cluster_size);
+            if (ret < 0) {
+                return ret;
+            }
         } else {
             cluster_offset = bdrv_getlength(bs->file->bs);
+            if ((int64_t) cluster_offset < 0) {
+                return cluster_offset;
+            }
             if (allocate == 1) {
                 /* round to cluster size */
-                cluster_offset = (cluster_offset + s->cluster_size - 1) &
-                    ~(s->cluster_size - 1);
-                bdrv_truncate(bs->file, cluster_offset + s->cluster_size,
-                              PREALLOC_MODE_OFF, NULL);
+                cluster_offset = QEMU_ALIGN_UP(cluster_offset, s->cluster_size);
+                if (cluster_offset + s->cluster_size > INT64_MAX) {
+                    return -E2BIG;
+                }
+                ret = bdrv_truncate(bs->file, cluster_offset + s->cluster_size,
+                                    PREALLOC_MODE_OFF, NULL);
+                if (ret < 0) {
+                    return ret;
+                }
                 /* if encrypted, we must initialize the cluster
                    content which won't be written */
                 if (bs->encrypted &&
@@ -454,20 +477,19 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
                     start_sect = (offset & ~(s->cluster_size - 1)) >> 9;
                     for(i = 0; i < s->cluster_sectors; i++) {
                         if (i < n_start || i >= n_end) {
-                            Error *err = NULL;
                             memset(s->cluster_data, 0x00, 512);
                             if (qcrypto_block_encrypt(s->crypto, start_sect + i,
                                                       s->cluster_data,
                                                       BDRV_SECTOR_SIZE,
-                                                      &err) < 0) {
-                                error_free(err);
-                                errno = EIO;
-                                return -1;
+                                                      NULL) < 0) {
+                                return -EIO;
+                            }
+                            ret = bdrv_pwrite(bs->file,
+                                              cluster_offset + i * 512,
+                                              s->cluster_data, 512);
+                            if (ret < 0) {
+                                return ret;
                             }
-                            if (bdrv_pwrite(bs->file,
-                                            cluster_offset + i * 512,
-                                            s->cluster_data, 512) != 512)
-                                return -1;
                         }
                     }
                 }
@@ -479,23 +501,29 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
         /* update L2 table */
         tmp = cpu_to_be64(cluster_offset);
         l2_table[l2_index] = tmp;
-        if (bdrv_pwrite_sync(bs->file, l2_offset + l2_index * sizeof(tmp),
-                &tmp, sizeof(tmp)) < 0)
-            return 0;
+        ret = bdrv_pwrite_sync(bs->file, l2_offset + l2_index * sizeof(tmp),
+                               &tmp, sizeof(tmp));
+        if (ret < 0) {
+            return ret;
+        }
     }
-    return cluster_offset;
+    *result = cluster_offset;
+    return 1;
 }
 
 static int64_t coroutine_fn qcow_co_get_block_status(BlockDriverState *bs,
         int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
 {
     BDRVQcowState *s = bs->opaque;
-    int index_in_cluster, n;
+    int index_in_cluster, n, ret;
     uint64_t cluster_offset;
 
     qemu_co_mutex_lock(&s->lock);
-    cluster_offset = get_cluster_offset(bs, sector_num << 9, 0, 0, 0, 0);
+    ret = get_cluster_offset(bs, sector_num << 9, 0, 0, 0, 0, &cluster_offset);
     qemu_co_mutex_unlock(&s->lock);
+    if (ret < 0) {
+        return ret;
+    }
     index_in_cluster = sector_num & (s->cluster_sectors - 1);
     n = s->cluster_sectors - index_in_cluster;
     if (n > nb_sectors)
@@ -572,7 +600,6 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
     QEMUIOVector hd_qiov;
     uint8_t *buf;
     void *orig_buf;
-    Error *err = NULL;
 
     if (qiov->niov > 1) {
         buf = orig_buf = qemu_try_blockalign(bs, qiov->size);
@@ -588,8 +615,11 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
 
     while (nb_sectors != 0) {
         /* prepare next request */
-        cluster_offset = get_cluster_offset(bs, sector_num << 9,
-                                                 0, 0, 0, 0);
+        ret = get_cluster_offset(bs, sector_num << 9,
+                                 0, 0, 0, 0, &cluster_offset);
+        if (ret < 0) {
+            break;
+        }
         index_in_cluster = sector_num & (s->cluster_sectors - 1);
         n = s->cluster_sectors - index_in_cluster;
         if (n > nb_sectors) {
@@ -606,7 +636,7 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
                 ret = bdrv_co_readv(bs->backing, sector_num, n, &hd_qiov);
                 qemu_co_mutex_lock(&s->lock);
                 if (ret < 0) {
-                    goto fail;
+                    break;
                 }
             } else {
                 /* Note: in this case, no need to wait */
@@ -615,13 +645,15 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
         } else if (cluster_offset & QCOW_OFLAG_COMPRESSED) {
             /* add AIO support for compressed blocks ? */
             if (decompress_cluster(bs, cluster_offset) < 0) {
-                goto fail;
+                ret = -EIO;
+                break;
             }
             memcpy(buf,
                    s->cluster_cache + index_in_cluster * 512, 512 * n);
         } else {
             if ((cluster_offset & 511) != 0) {
-                goto fail;
+                ret = -EIO;
+                break;
             }
             hd_iov.iov_base = (void *)buf;
             hd_iov.iov_len = n * 512;
@@ -637,8 +669,9 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
             if (bs->encrypted) {
                 assert(s->crypto);
                 if (qcrypto_block_decrypt(s->crypto, sector_num, buf,
-                                          n * BDRV_SECTOR_SIZE, &err) < 0) {
-                    goto fail;
+                                          n * BDRV_SECTOR_SIZE, NULL) < 0) {
+                    ret = -EIO;
+                    break;
                 }
             }
         }
@@ -649,7 +682,6 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
         buf += n * 512;
     }
 
-done:
     qemu_co_mutex_unlock(&s->lock);
 
     if (qiov->niov > 1) {
@@ -658,11 +690,6 @@ done:
     }
 
     return ret;
-
-fail:
-    error_free(err);
-    ret = -EIO;
-    goto done;
 }
 
 static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
@@ -701,19 +728,20 @@ static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
         if (n > nb_sectors) {
             n = nb_sectors;
         }
-        cluster_offset = get_cluster_offset(bs, sector_num << 9, 1, 0,
-                                            index_in_cluster,
-                                            index_in_cluster + n);
+        ret = get_cluster_offset(bs, sector_num << 9, 1, 0,
+                                 index_in_cluster,
+                                 index_in_cluster + n, &cluster_offset);
+        if (ret < 0) {
+            break;
+        }
         if (!cluster_offset || (cluster_offset & 511) != 0) {
             ret = -EIO;
             break;
         }
         if (bs->encrypted) {
-            Error *err = NULL;
             assert(s->crypto);
             if (qcrypto_block_encrypt(s->crypto, sector_num, buf,
-                                      n * BDRV_SECTOR_SIZE, &err) < 0) {
-                error_free(err);
+                                      n * BDRV_SECTOR_SIZE, NULL) < 0) {
                 ret = -EIO;
                 break;
             }
@@ -768,7 +796,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     Error *local_err = NULL;
     int ret;
     BlockBackend *qcow_blk;
-    const char *encryptfmt = NULL;
+    char *encryptfmt = NULL;
     QDict *options;
     QDict *encryptopts = NULL;
     QCryptoBlockCreateOptions *crypto_opts = NULL;
@@ -793,7 +821,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
             goto cleanup;
         }
     } else if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
-        encryptfmt = "aes";
+        encryptfmt = g_strdup("aes");
     }
 
     ret = bdrv_create_file(filename, opts, &local_err);
@@ -908,6 +936,7 @@ exit:
     blk_unref(qcow_blk);
 cleanup:
     QDECREF(encryptopts);
+    g_free(encryptfmt);
     qcrypto_block_free(crypto);
     qapi_free_QCryptoBlockCreateOptions(crypto_opts);
     g_free(backing_file);
@@ -1000,8 +1029,11 @@ qcow_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
         goto success;
     }
     qemu_co_mutex_lock(&s->lock);
-    cluster_offset = get_cluster_offset(bs, offset, 2, out_len, 0, 0);
+    ret = get_cluster_offset(bs, offset, 2, out_len, 0, 0, &cluster_offset);
     qemu_co_mutex_unlock(&s->lock);
+    if (ret < 0) {
+        goto fail;
+    }
     if (cluster_offset == 0) {
         ret = -EIO;
         goto fail;

block/qcow2-bitmap.c

@@ -487,6 +487,10 @@ static inline void bitmap_directory_to_be(uint8_t *dir, size_t size)
 
 static void bitmap_free(Qcow2Bitmap *bm)
 {
+    if (bm == NULL) {
+        return;
+    }
+
     g_free(bm->name);
     g_free(bm);
 }

block/qcow2-cluster.c

@@ -61,7 +61,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
             new_l1_size = 1;
         }
         while (min_size > new_l1_size) {
-            new_l1_size = (new_l1_size * 3 + 1) / 2;
+            new_l1_size = DIV_ROUND_UP(new_l1_size * 3, 2);
         }
     }
 
@@ -1516,6 +1516,23 @@ int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
         nb_csectors = ((cluster_offset >> s->csize_shift) & s->csize_mask) + 1;
         sector_offset = coffset & 511;
         csize = nb_csectors * 512 - sector_offset;
+
+        /* Allocate buffers on first decompress operation, most images are
+         * uncompressed and the memory overhead can be avoided.  The buffers
+         * are freed in .bdrv_close().
+         */
+        if (!s->cluster_data) {
+            /* one more sector for decompressed data alignment */
+            s->cluster_data = qemu_try_blockalign(bs->file->bs,
+                    QCOW_MAX_CRYPT_CLUSTERS * s->cluster_size + 512);
+            if (!s->cluster_data) {
+                return -ENOMEM;
+            }
+        }
+        if (!s->cluster_cache) {
+            s->cluster_cache = g_malloc(s->cluster_size);
+        }
+
         BLKDBG_EVENT(bs->file, BLKDBG_READ_COMPRESSED);
         ret = bdrv_read(bs->file, coffset >> 9, s->cluster_data,
                         nb_csectors);

block/qcow2-refcount.c

@@ -2189,6 +2189,8 @@ write_refblocks:
              * this will leak that range, but we can easily fix that by running
              * a leak-fixing check after this rebuild operation */
             reftable_offset = -1;
+        } else {
+            assert(on_disk_reftable);
         }
         on_disk_reftable[refblock_index] = refblock_offset;
 
@@ -2258,8 +2260,6 @@ write_refblocks:
         goto write_refblocks;
     }
 
-    assert(on_disk_reftable);
-
     for (refblock_index = 0; refblock_index < reftable_size; refblock_index++) {
         cpu_to_be64s(&on_disk_reftable[refblock_index]);
     }

block/qcow2.c

@@ -30,7 +30,6 @@
 #include "qemu/error-report.h"
 #include "qapi/qmp/qerror.h"
 #include "qapi/qmp/qbool.h"
-#include "qapi/util.h"
 #include "qapi/qmp/types.h"
 #include "qapi-event.h"
 #include "trace.h"
@@ -302,10 +301,11 @@ static int qcow2_read_extensions(BlockDriverState *bs, uint64_t start_offset,
             }
 
             if (!(s->autoclear_features & QCOW2_AUTOCLEAR_BITMAPS)) {
-                error_report("WARNING: a program lacking bitmap support "
-                             "modified this file, so all bitmaps are now "
-                             "considered inconsistent. Some clusters may be "
-                             "leaked, run 'qemu-img check -r' on the image "
+                warn_report("a program lacking bitmap support "
+                            "modified this file, so all bitmaps are now "
+                            "considered inconsistent");
+                error_printf("Some clusters may be leaked, "
+                             "run 'qemu-img check -r' on the image "
                              "file to fix.");
                 if (need_update_header != NULL) {
                     /* Updating is needed to drop invalid bitmap extension. */
@@ -1360,16 +1360,6 @@ static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    s->cluster_cache = g_malloc(s->cluster_size);
-    /* one more sector for decompressed data alignment */
-    s->cluster_data = qemu_try_blockalign(bs->file->bs, QCOW_MAX_CRYPT_CLUSTERS
-                                                    * s->cluster_size + 512);
-    if (s->cluster_data == NULL) {
-        error_setg(errp, "Could not allocate temporary cluster buffer");
-        ret = -ENOMEM;
-        goto fail;
-    }
-
     s->cluster_cache_offset = -1;
     s->flags = flags;
 
@@ -1507,8 +1497,6 @@ static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags,
     if (s->refcount_block_cache) {
         qcow2_cache_destroy(bs, s->refcount_block_cache);
     }
-    g_free(s->cluster_cache);
-    qemu_vfree(s->cluster_data);
     qcrypto_block_free(s->crypto);
     qapi_free_QCryptoBlockOpenOptions(s->crypto_opts);
     return ret;
@@ -1820,15 +1808,13 @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset,
                 assert(s->crypto);
                 assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
                 assert((cur_bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
-                Error *err = NULL;
                 if (qcrypto_block_decrypt(s->crypto,
                                           (s->crypt_physical_offset ?
                                            cluster_offset + offset_in_cluster :
                                            offset) >> BDRV_SECTOR_BITS,
                                           cluster_data,
                                           cur_bytes,
-                                          &err) < 0) {
-                    error_free(err);
+                                          NULL) < 0) {
                     ret = -EIO;
                     goto fail;
                 }
@@ -1942,7 +1928,6 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
         qemu_iovec_concat(&hd_qiov, qiov, bytes_done, cur_bytes);
 
         if (bs->encrypted) {
-            Error *err = NULL;
             assert(s->crypto);
             if (!cluster_data) {
                 cluster_data = qemu_try_blockalign(bs->file->bs,
@@ -1963,8 +1948,7 @@ static coroutine_fn int qcow2_co_pwritev(BlockDriverState *bs, uint64_t offset,
                                        cluster_offset + offset_in_cluster :
                                        offset) >> BDRV_SECTOR_BITS,
                                       cluster_data,
-                                      cur_bytes, &err) < 0) {
-                error_free(err);
+                                      cur_bytes, NULL) < 0) {
                 ret = -EIO;
                 goto fail;
             }
@@ -2053,6 +2037,14 @@ static int qcow2_inactivate(BlockDriverState *bs)
     int ret, result = 0;
     Error *local_err = NULL;
 
+    qcow2_store_persistent_dirty_bitmaps(bs, &local_err);
+    if (local_err != NULL) {
+        result = -EINVAL;
+        error_report_err(local_err);
+        error_report("Persistent bitmaps are lost for node '%s'",
+                     bdrv_get_device_or_node_name(bs));
+    }
+
     ret = qcow2_cache_flush(bs, s->l2_table_cache);
     if (ret) {
         result = ret;
@@ -2067,14 +2059,6 @@ static int qcow2_inactivate(BlockDriverState *bs)
                      strerror(-ret));
     }
 
-    qcow2_store_persistent_dirty_bitmaps(bs, &local_err);
-    if (local_err != NULL) {
-        result = -EINVAL;
-        error_report_err(local_err);
-        error_report("Persistent bitmaps are lost for node '%s'",
-                     bdrv_get_device_or_node_name(bs));
-    }
-
     if (result == 0) {
         qcow2_mark_clean(bs);
     }
@@ -2732,7 +2716,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
         int64_t prealloc_size =
             qcow2_calc_prealloc_size(total_size, cluster_size, refcount_order);
         qemu_opt_set_number(opts, BLOCK_OPT_SIZE, prealloc_size, &error_abort);
-        qemu_opt_set(opts, BLOCK_OPT_PREALLOC, PreallocMode_lookup[prealloc],
+        qemu_opt_set(opts, BLOCK_OPT_PREALLOC, PreallocMode_str(prealloc),
                      &error_abort);
     }
 
@@ -2905,7 +2889,7 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
     int version;
     uint64_t refcount_bits;
     int refcount_order;
-    const char *encryptfmt = NULL;
+    char *encryptfmt = NULL;
     Error *local_err = NULL;
     int ret;
 
@@ -2916,14 +2900,14 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
     backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT);
     encryptfmt = qemu_opt_get_del(opts, BLOCK_OPT_ENCRYPT_FORMAT);
     if (encryptfmt) {
-        if (qemu_opt_get_del(opts, BLOCK_OPT_ENCRYPT)) {
+        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 finish;
         }
     } else if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
-        encryptfmt = "aes";
+        encryptfmt = g_strdup("aes");
     }
     cluster_size = qcow2_opt_get_cluster_size_del(opts, &local_err);
     if (local_err) {
@@ -2932,9 +2916,8 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
         goto finish;
     }
     buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
-    prealloc = qapi_enum_parse(PreallocMode_lookup, buf,
-                               PREALLOC_MODE__MAX, PREALLOC_MODE_OFF,
-                               &local_err);
+    prealloc = qapi_enum_parse(&PreallocMode_lookup, buf,
+                               PREALLOC_MODE_OFF, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
         ret = -EINVAL;
@@ -2983,6 +2966,7 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
 finish:
     g_free(backing_file);
     g_free(backing_fmt);
+    g_free(encryptfmt);
     g_free(buf);
     return ret;
 }
@@ -3097,7 +3081,7 @@ static int qcow2_truncate(BlockDriverState *bs, int64_t offset,
         prealloc != PREALLOC_MODE_FALLOC && prealloc != PREALLOC_MODE_FULL)
     {
         error_setg(errp, "Unsupported preallocation mode '%s'",
-                   PreallocMode_lookup[prealloc]);
+                   PreallocMode_str(prealloc));
         return -ENOTSUP;
     }
 
@@ -3281,12 +3265,15 @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
     z_stream strm;
     int ret, out_len;
     uint8_t *buf, *out_buf;
-    uint64_t cluster_offset;
+    int64_t cluster_offset;
 
     if (bytes == 0) {
         /* align end of file to a sector boundary to ease reading with
            sector based I/Os */
         cluster_offset = bdrv_getlength(bs->file->bs);
+        if (cluster_offset < 0) {
+            return cluster_offset;
+        }
         return bdrv_truncate(bs->file, cluster_offset, PREALLOC_MODE_OFF, NULL);
     }
 
@@ -3619,9 +3606,8 @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs,
     }
 
     optstr = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
-    prealloc = qapi_enum_parse(PreallocMode_lookup, optstr,
-                               PREALLOC_MODE__MAX, PREALLOC_MODE_OFF,
-                               &local_err);
+    prealloc = qapi_enum_parse(&PreallocMode_lookup, optstr,
+                               PREALLOC_MODE_OFF, &local_err);
     g_free(optstr);
     if (local_err) {
         goto err;
@@ -3669,8 +3655,8 @@ static BlockMeasureInfo *qcow2_measure(QemuOpts *opts, BlockDriverState *in_bs,
             for (sector_num = 0;
                  sector_num < ssize / BDRV_SECTOR_SIZE;
                  sector_num += pnum) {
-                int nb_sectors = MAX(ssize / BDRV_SECTOR_SIZE - sector_num,
-                                     INT_MAX);
+                int nb_sectors = MIN(ssize / BDRV_SECTOR_SIZE - sector_num,
+                                     BDRV_REQUEST_MAX_SECTORS);
                 BlockDriverState *file;
                 int64_t ret;
 
@@ -3797,27 +3783,6 @@ static ImageInfoSpecific *qcow2_get_specific_info(BlockDriverState *bs)
     return spec_info;
 }
 
-#if 0
-static void dump_refcounts(BlockDriverState *bs)
-{
-    BDRVQcow2State *s = bs->opaque;
-    int64_t nb_clusters, k, k1, size;
-    int refcount;
-
-    size = bdrv_getlength(bs->file->bs);
-    nb_clusters = size_to_clusters(s, size);
-    for(k = 0; k < nb_clusters;) {
-        k1 = k;
-        refcount = get_refcount(bs, k);
-        k++;
-        while (k < nb_clusters && get_refcount(bs, k) == refcount)
-            k++;
-        printf("%" PRId64 ": refcount=%d nb=%" PRId64 "\n", k, refcount,
-               k - k1);
-    }
-}
-#endif
-
 static int qcow2_save_vmstate(BlockDriverState *bs, QEMUIOVector *qiov,
                               int64_t pos)
 {

block/qed.c

@@ -1399,7 +1399,7 @@ static int bdrv_qed_truncate(BlockDriverState *bs, int64_t offset,
 
     if (prealloc != PREALLOC_MODE_OFF) {
         error_setg(errp, "Unsupported preallocation mode '%s'",
-                   PreallocMode_lookup[prealloc]);
+                   PreallocMode_str(prealloc));
         return -ENOTSUP;
     }
 

block/quorum.c

@@ -785,8 +785,7 @@ static coroutine_fn int quorum_co_flush(BlockDriverState *bs)
     for (i = 0; i < s->num_children; i++) {
         result = bdrv_co_flush(s->children[i]->bs);
         if (result) {
-            quorum_report_bad(QUORUM_OP_TYPE_FLUSH, 0,
-                              bdrv_getlength(s->children[i]->bs),
+            quorum_report_bad(QUORUM_OP_TYPE_FLUSH, 0, 0,
                               s->children[i]->bs->node_name, result);
             result_value.l = result;
             quorum_count_vote(&error_votes, &result_value, i);
@@ -868,30 +867,13 @@ static QemuOptsList quorum_runtime_opts = {
     },
 };
 
-static int parse_read_pattern(const char *opt)
-{
-    int i;
-
-    if (!opt) {
-        /* Set quorum as default */
-        return QUORUM_READ_PATTERN_QUORUM;
-    }
-
-    for (i = 0; i < QUORUM_READ_PATTERN__MAX; i++) {
-        if (!strcmp(opt, QuorumReadPattern_lookup[i])) {
-            return i;
-        }
-    }
-
-    return -EINVAL;
-}
-
 static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
                        Error **errp)
 {
     BDRVQuorumState *s = bs->opaque;
     Error *local_err = NULL;
     QemuOpts *opts = NULL;
+    const char *pattern_str;
     bool *opened;
     int i;
     int ret = 0;
@@ -926,7 +908,13 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
         goto exit;
     }
 
-    ret = parse_read_pattern(qemu_opt_get(opts, QUORUM_OPT_READ_PATTERN));
+    pattern_str = qemu_opt_get(opts, QUORUM_OPT_READ_PATTERN);
+    if (!pattern_str) {
+        ret = QUORUM_READ_PATTERN_QUORUM;
+    } else {
+        ret = qapi_enum_parse(&QuorumReadPattern_lookup, pattern_str,
+                              -EINVAL, NULL);
+    }
     if (ret < 0) {
         error_setg(&local_err, "Please set read-pattern as fifo or quorum");
         goto exit;

block/raw-format.c

@@ -372,11 +372,6 @@ static int raw_truncate(BlockDriverState *bs, int64_t offset,
     return bdrv_truncate(bs->file, offset, prealloc, errp);
 }
 
-static int raw_media_changed(BlockDriverState *bs)
-{
-    return bdrv_media_changed(bs->file->bs);
-}
-
 static void raw_eject(BlockDriverState *bs, bool eject_flag)
 {
     bdrv_eject(bs->file->bs, eject_flag);
@@ -510,7 +505,6 @@ BlockDriver bdrv_raw = {
     .bdrv_refresh_limits  = &raw_refresh_limits,
     .bdrv_probe_blocksizes = &raw_probe_blocksizes,
     .bdrv_probe_geometry  = &raw_probe_geometry,
-    .bdrv_media_changed   = &raw_media_changed,
     .bdrv_eject           = &raw_eject,
     .bdrv_lock_medium     = &raw_lock_medium,
     .bdrv_co_ioctl        = &raw_co_ioctl,

block/rbd.c

@@ -944,7 +944,7 @@ static int qemu_rbd_truncate(BlockDriverState *bs, int64_t offset,
 
     if (prealloc != PREALLOC_MODE_OFF) {
         error_setg(errp, "Unsupported preallocation mode '%s'",
-                   PreallocMode_lookup[prealloc]);
+                   PreallocMode_str(prealloc));
         return -ENOTSUP;
     }
 

block/sheepdog.c

@@ -591,7 +591,7 @@ static int connect_to_sdog(BDRVSheepdogState *s, Error **errp)
 {
     int fd;
 
-    fd = socket_connect(s->addr, NULL, NULL, errp);
+    fd = socket_connect(s->addr, errp);
 
     if (s->addr->type == SOCKET_ADDRESS_TYPE_INET && fd >= 0) {
         int ret = socket_set_nodelay(fd);
@@ -2176,7 +2176,7 @@ static int sd_truncate(BlockDriverState *bs, int64_t offset,
 
     if (prealloc != PREALLOC_MODE_OFF) {
         error_setg(errp, "Unsupported preallocation mode '%s'",
-                   PreallocMode_lookup[prealloc]);
+                   PreallocMode_str(prealloc));
         return -ENOTSUP;
     }
 

block/ssh.c

@@ -678,7 +678,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
     }
 
     /* Open the socket and connect. */
-    s->sock = inet_connect_saddr(s->inet, NULL, NULL, errp);
+    s->sock = inet_connect_saddr(s->inet, errp);
     if (s->sock < 0) {
         ret = -EIO;
         goto err;

block/throttle.c

@@ -0,0 +1,237 @@
+/*
+ * QEMU block throttling filter driver infrastructure
+ *
+ * Copyright (c) 2017 Manos Pitsidianakis
+ *
+ * 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/throttle-groups.h"
+#include "qemu/throttle-options.h"
+#include "qapi/error.h"
+
+static QemuOptsList throttle_opts = {
+    .name = "throttle",
+    .head = QTAILQ_HEAD_INITIALIZER(throttle_opts.head),
+    .desc = {
+        {
+            .name = QEMU_OPT_THROTTLE_GROUP_NAME,
+            .type = QEMU_OPT_STRING,
+            .help = "Name of the throttle group",
+        },
+        { /* end of list */ }
+    },
+};
+
+static int throttle_configure_tgm(BlockDriverState *bs,
+                                  ThrottleGroupMember *tgm,
+                                  QDict *options, Error **errp)
+{
+    int ret;
+    const char *group_name;
+    Error *local_err = NULL;
+    QemuOpts *opts = qemu_opts_create(&throttle_opts, NULL, 0, &error_abort);
+
+    qemu_opts_absorb_qdict(opts, options, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto fin;
+    }
+
+    group_name = qemu_opt_get(opts, QEMU_OPT_THROTTLE_GROUP_NAME);
+    if (!group_name) {
+        error_setg(errp, "Please specify a throttle group");
+        ret = -EINVAL;
+        goto fin;
+    } else if (!throttle_group_exists(group_name)) {
+        error_setg(errp, "Throttle group '%s' does not exist", group_name);
+        ret = -EINVAL;
+        goto fin;
+    }
+
+    /* 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);
+    return ret;
+}
+
+static int throttle_open(BlockDriverState *bs, QDict *options,
+                         int flags, Error **errp)
+{
+    ThrottleGroupMember *tgm = bs->opaque;
+
+    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;
+    bs->supported_zero_flags = bs->file->bs->supported_zero_flags;
+
+    return throttle_configure_tgm(bs, tgm, options, errp);
+}
+
+static void throttle_close(BlockDriverState *bs)
+{
+    ThrottleGroupMember *tgm = bs->opaque;
+    throttle_group_unregister_tgm(tgm);
+}
+
+
+static int64_t throttle_getlength(BlockDriverState *bs)
+{
+    return bdrv_getlength(bs->file->bs);
+}
+
+static int coroutine_fn throttle_co_preadv(BlockDriverState *bs,
+                                           uint64_t offset, uint64_t bytes,
+                                           QEMUIOVector *qiov, int flags)
+{
+
+    ThrottleGroupMember *tgm = bs->opaque;
+    throttle_group_co_io_limits_intercept(tgm, bytes, false);
+
+    return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
+}
+
+static int coroutine_fn throttle_co_pwritev(BlockDriverState *bs,
+                                            uint64_t offset, uint64_t bytes,
+                                            QEMUIOVector *qiov, int flags)
+{
+    ThrottleGroupMember *tgm = bs->opaque;
+    throttle_group_co_io_limits_intercept(tgm, bytes, true);
+
+    return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
+}
+
+static int coroutine_fn throttle_co_pwrite_zeroes(BlockDriverState *bs,
+                                                  int64_t offset, int bytes,
+                                                  BdrvRequestFlags flags)
+{
+    ThrottleGroupMember *tgm = bs->opaque;
+    throttle_group_co_io_limits_intercept(tgm, bytes, true);
+
+    return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
+}
+
+static int coroutine_fn throttle_co_pdiscard(BlockDriverState *bs,
+                                             int64_t offset, int bytes)
+{
+    ThrottleGroupMember *tgm = bs->opaque;
+    throttle_group_co_io_limits_intercept(tgm, bytes, true);
+
+    return bdrv_co_pdiscard(bs->file->bs, offset, bytes);
+}
+
+static int throttle_co_flush(BlockDriverState *bs)
+{
+    return bdrv_co_flush(bs->file->bs);
+}
+
+static void throttle_detach_aio_context(BlockDriverState *bs)
+{
+    ThrottleGroupMember *tgm = bs->opaque;
+    throttle_group_detach_aio_context(tgm);
+}
+
+static void throttle_attach_aio_context(BlockDriverState *bs,
+                                        AioContext *new_context)
+{
+    ThrottleGroupMember *tgm = bs->opaque;
+    throttle_group_attach_aio_context(tgm, new_context);
+}
+
+static int throttle_reopen_prepare(BDRVReopenState *reopen_state,
+                                   BlockReopenQueue *queue, Error **errp)
+{
+    ThrottleGroupMember *tgm;
+
+    assert(reopen_state != NULL);
+    assert(reopen_state->bs != NULL);
+
+    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)
+{
+    ThrottleGroupMember *old_tgm = reopen_state->bs->opaque;
+    ThrottleGroupMember *new_tgm = 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)
+{
+    ThrottleGroupMember *tgm = reopen_state->opaque;
+
+    throttle_group_unregister_tgm(tgm);
+    g_free(tgm);
+    reopen_state->opaque = NULL;
+}
+
+static bool throttle_recurse_is_first_non_filter(BlockDriverState *bs,
+                                                 BlockDriverState *candidate)
+{
+    return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate);
+}
+
+static BlockDriver bdrv_throttle = {
+    .format_name                        =   "throttle",
+    .protocol_name                      =   "throttle",
+    .instance_size                      =   sizeof(ThrottleGroupMember),
+
+    .bdrv_file_open                     =   throttle_open,
+    .bdrv_close                         =   throttle_close,
+    .bdrv_co_flush                      =   throttle_co_flush,
+
+    .bdrv_child_perm                    =   bdrv_filter_default_perms,
+
+    .bdrv_getlength                     =   throttle_getlength,
+
+    .bdrv_co_preadv                     =   throttle_co_preadv,
+    .bdrv_co_pwritev                    =   throttle_co_pwritev,
+
+    .bdrv_co_pwrite_zeroes              =   throttle_co_pwrite_zeroes,
+    .bdrv_co_pdiscard                   =   throttle_co_pdiscard,
+
+    .bdrv_recurse_is_first_non_filter   =   throttle_recurse_is_first_non_filter,
+
+    .bdrv_attach_aio_context            =   throttle_attach_aio_context,
+    .bdrv_detach_aio_context            =   throttle_detach_aio_context,
+
+    .bdrv_reopen_prepare                =   throttle_reopen_prepare,
+    .bdrv_reopen_commit                 =   throttle_reopen_commit,
+    .bdrv_reopen_abort                  =   throttle_reopen_abort,
+    .bdrv_co_get_block_status           =   bdrv_co_get_block_status_from_file,
+
+    .is_filter                          =   true,
+};
+
+static void bdrv_throttle_init(void)
+{
+    bdrv_register(&bdrv_throttle);
+}
+
+block_init(bdrv_throttle_init);

block/trace-events

@@ -1,17 +1,17 @@
-# See docs/tracing.txt for syntax documentation.
+# See docs/devel/tracing.txt for syntax documentation.
 
 # block.c
-bdrv_open_common(void *bs, const char *filename, int flags, const char *format_name) "bs %p filename \"%s\" flags %#x format_name \"%s\""
+bdrv_open_common(void *bs, const char *filename, int flags, const char *format_name) "bs %p filename \"%s\" flags 0x%x format_name \"%s\""
 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 %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 %x"
+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"
 
 # block/io.c
-bdrv_co_readv(void *bs, int64_t sector_num, int nb_sector) "bs %p sector_num %"PRId64" nb_sectors %d"
-bdrv_co_writev(void *bs, int64_t sector_num, int nb_sector) "bs %p sector_num %"PRId64" nb_sectors %d"
-bdrv_co_pwrite_zeroes(void *bs, int64_t offset, int count, int flags) "bs %p offset %"PRId64" count %d flags %#x"
+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, unsigned int cluster_bytes) "bs %p offset %"PRId64" bytes %u cluster_offset %"PRId64" cluster_bytes %u"
 
 # block/stream.c
@@ -54,19 +54,19 @@ paio_submit_co(int64_t offset, int count, int type) "offset %"PRId64" count %d t
 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 %" PRIx64 " bytes %d"
+qcow2_writev_start_req(void *co, int64_t offset, int bytes) "co %p offset 0x%" PRIx64 " bytes %d"
 qcow2_writev_done_req(void *co, int ret) "co %p ret %d"
 qcow2_writev_start_part(void *co) "co %p"
 qcow2_writev_done_part(void *co, int cur_bytes) "co %p cur_bytes %d"
-qcow2_writev_data(void *co, uint64_t offset) "co %p offset %" PRIx64
-qcow2_pwrite_zeroes_start_req(void *co, int64_t offset, int count) "co %p offset %" PRIx64 " count %d"
-qcow2_pwrite_zeroes(void *co, int64_t offset, int count) "co %p offset %" PRIx64 " count %d"
+qcow2_writev_data(void *co, uint64_t offset) "co %p offset 0x%" PRIx64
+qcow2_pwrite_zeroes_start_req(void *co, int64_t offset, int count) "co %p offset 0x%" PRIx64 " count %d"
+qcow2_pwrite_zeroes(void *co, int64_t offset, int count) "co %p offset 0x%" PRIx64 " count %d"
 
 # block/qcow2-cluster.c
-qcow2_alloc_clusters_offset(void *co, uint64_t offset, int bytes) "co %p offset %" PRIx64 " bytes %d"
-qcow2_handle_copied(void *co, uint64_t guest_offset, uint64_t host_offset, uint64_t bytes) "co %p guest_offset %" PRIx64 " host_offset %" PRIx64 " bytes %" PRIx64
-qcow2_handle_alloc(void *co, uint64_t guest_offset, uint64_t host_offset, uint64_t bytes) "co %p guest_offset %" PRIx64 " host_offset %" PRIx64 " bytes %" PRIx64
-qcow2_do_alloc_clusters_offset(void *co, uint64_t guest_offset, uint64_t host_offset, int nb_clusters) "co %p guest_offset %" PRIx64 " host_offset %" PRIx64 " nb_clusters %d"
+qcow2_alloc_clusters_offset(void *co, uint64_t offset, int bytes) "co %p offset 0x%" PRIx64 " bytes %d"
+qcow2_handle_copied(void *co, uint64_t guest_offset, uint64_t host_offset, uint64_t bytes) "co %p guest_offset 0x%" PRIx64 " host_offset 0x%" PRIx64 " bytes 0x%" PRIx64
+qcow2_handle_alloc(void *co, uint64_t guest_offset, uint64_t host_offset, uint64_t bytes) "co %p guest_offset 0x%" PRIx64 " host_offset 0x%" PRIx64 " bytes 0x%" PRIx64
+qcow2_do_alloc_clusters_offset(void *co, uint64_t guest_offset, uint64_t host_offset, int nb_clusters) "co %p guest_offset 0x%" PRIx64 " host_offset 0x%" PRIx64 " nb_clusters %d"
 qcow2_cluster_alloc_phys(void *co) "co %p"
 qcow2_cluster_link_l2(void *co, int nb_clusters) "co %p nb_clusters %d"
 
@@ -77,7 +77,7 @@ qcow2_l2_allocate_write_l1(void *bs, int l1_index) "bs %p l1_index %d"
 qcow2_l2_allocate_done(void *bs, int l1_index, int ret) "bs %p l1_index %d ret %d"
 
 # block/qcow2-cache.c
-qcow2_cache_get(void *co, int c, uint64_t offset, bool read_from_disk) "co %p is_l2_cache %d offset %" PRIx64 " read_from_disk %d"
+qcow2_cache_get(void *co, int c, uint64_t offset, bool read_from_disk) "co %p is_l2_cache %d offset 0x%" PRIx64 " read_from_disk %d"
 qcow2_cache_get_replace_entry(void *co, int c, int i) "co %p is_l2_cache %d index %d"
 qcow2_cache_get_read(void *co, int c, int i) "co %p is_l2_cache %d index %d"
 qcow2_cache_get_done(void *co, int c, int i) "co %p is_l2_cache %d index %d"
@@ -100,7 +100,7 @@ qed_need_check_timer_cb(void *s) "s %p"
 qed_start_need_check_timer(void *s) "s %p"
 qed_cancel_need_check_timer(void *s) "s %p"
 qed_aio_complete(void *s, void *acb, int ret) "s %p acb %p ret %d"
-qed_aio_setup(void *s, void *acb, int64_t sector_num, int nb_sectors, void *opaque, int flags) "s %p acb %p sector_num %"PRId64" nb_sectors %d opaque %p flags %#x"
+qed_aio_setup(void *s, void *acb, int64_t sector_num, int nb_sectors, void *opaque, int flags) "s %p acb %p sector_num %"PRId64" nb_sectors %d opaque %p flags 0x%x"
 qed_aio_next_io(void *s, void *acb, int ret, uint64_t cur_pos) "s %p acb %p ret %d cur_pos %"PRIu64
 qed_aio_read_data(void *s, void *acb, int ret, uint64_t offset, size_t len) "s %p acb %p ret %d offset %"PRIu64" len %zu"
 qed_aio_write_data(void *s, void *acb, int ret, uint64_t offset, size_t len) "s %p acb %p ret %d offset %"PRIu64" len %zu"

block/vhdx-log.c

@@ -491,6 +491,7 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
     uint32_t cnt, sectors_read;
     uint64_t new_file_size;
     void *data = NULL;
+    int64_t file_length;
     VHDXLogDescEntries *desc_entries = NULL;
     VHDXLogEntryHeader hdr_tmp = { 0 };
 
@@ -510,10 +511,15 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
         if (ret < 0) {
             goto exit;
         }
+        file_length = bdrv_getlength(bs->file->bs);
+        if (file_length < 0) {
+            ret = file_length;
+            goto exit;
+        }
         /* if the log shows a FlushedFileOffset larger than our current file
          * size, then that means the file has been truncated / corrupted, and
          * we must refused to open it / use it */
-        if (hdr_tmp.flushed_file_offset > bdrv_getlength(bs->file->bs)) {
+        if (hdr_tmp.flushed_file_offset > file_length) {
             ret = -EINVAL;
             goto exit;
         }
@@ -543,19 +549,30 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
                 goto exit;
             }
         }
-        if (bdrv_getlength(bs->file->bs) < desc_entries->hdr.last_file_offset) {
+        if (file_length < desc_entries->hdr.last_file_offset) {
             new_file_size = desc_entries->hdr.last_file_offset;
             if (new_file_size % (1024*1024)) {
                 /* round up to nearest 1MB boundary */
-                new_file_size = ((new_file_size >> 20) + 1) << 20;
-                bdrv_truncate(bs->file, new_file_size, PREALLOC_MODE_OFF, NULL);
+                new_file_size = QEMU_ALIGN_UP(new_file_size, MiB);
+                if (new_file_size > INT64_MAX) {
+                    ret = -EINVAL;
+                    goto exit;
+                }
+                ret = bdrv_truncate(bs->file, new_file_size, PREALLOC_MODE_OFF,
+                                    NULL);
+                if (ret < 0) {
+                    goto exit;
+                }
             }
         }
         qemu_vfree(desc_entries);
         desc_entries = NULL;
     }
 
-    bdrv_flush(bs);
+    ret = bdrv_flush(bs);
+    if (ret < 0) {
+        goto exit;
+    }
     /* once the log is fully flushed, indicate that we have an empty log
      * now.  This also sets the log guid to 0, to indicate an empty log */
     vhdx_log_reset(bs, s);
@@ -851,6 +868,7 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s,
     uint32_t partial_sectors = 0;
     uint32_t bytes_written = 0;
     uint64_t file_offset;
+    int64_t file_length;
     VHDXHeader *header;
     VHDXLogEntryHeader new_hdr;
     VHDXLogDescriptor *new_desc = NULL;
@@ -884,7 +902,7 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s,
     }
 
     sector_offset = offset % VHDX_LOG_SECTOR_SIZE;
-    file_offset = (offset / VHDX_LOG_SECTOR_SIZE) * VHDX_LOG_SECTOR_SIZE;
+    file_offset = QEMU_ALIGN_DOWN(offset, VHDX_LOG_SECTOR_SIZE);
 
     aligned_length = length;
 
@@ -904,6 +922,12 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s,
 
     sectors += partial_sectors;
 
+    file_length = bdrv_getlength(bs->file->bs);
+    if (file_length < 0) {
+        ret = file_length;
+        goto exit;
+    }
+
     /* sectors is now how many sectors the data itself takes, not
      * including the header and descriptor metadata */
 
@@ -913,11 +937,11 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s,
                 .sequence_number     = s->log.sequence,
                 .descriptor_count    = sectors,
                 .reserved            = 0,
-                .flushed_file_offset = bdrv_getlength(bs->file->bs),
-                .last_file_offset    = bdrv_getlength(bs->file->bs),
+                .flushed_file_offset = file_length,
+                .last_file_offset    = file_length,
+                .log_guid            = header->log_guid,
               };
 
-    new_hdr.log_guid = header->log_guid;
 
     desc_sectors = vhdx_compute_desc_sectors(new_hdr.descriptor_count);
 
@@ -1022,7 +1046,11 @@ int vhdx_log_write_and_flush(BlockDriverState *bs, BDRVVHDXState *s,
 
     /* Make sure data written (new and/or changed blocks) is stable
      * on disk, before creating log entry */
-    bdrv_flush(bs);
+    ret = bdrv_flush(bs);
+    if (ret < 0) {
+        goto exit;
+    }
+
     ret = vhdx_log_write(bs, s, data, length, offset);
     if (ret < 0) {
         goto exit;
@@ -1030,7 +1058,11 @@ int vhdx_log_write_and_flush(BlockDriverState *bs, BDRVVHDXState *s,
     logs.log = s->log;
 
     /* Make sure log is stable on disk */
-    bdrv_flush(bs);
+    ret = bdrv_flush(bs);
+    if (ret < 0) {
+        goto exit;
+    }
+
     ret = vhdx_log_flush(bs, s, &logs);
     if (ret < 0) {
         goto exit;

block/vhdx.c

@@ -1166,10 +1166,20 @@ exit:
 static int vhdx_allocate_block(BlockDriverState *bs, BDRVVHDXState *s,
                                     uint64_t *new_offset)
 {
-    *new_offset = bdrv_getlength(bs->file->bs);
+    int64_t current_len;
+
+    current_len = bdrv_getlength(bs->file->bs);
+    if (current_len < 0) {
+        return current_len;
+    }
+
+    *new_offset = current_len;
 
     /* per the spec, the address for a block is in units of 1MB */
     *new_offset = ROUND_UP(*new_offset, 1024 * 1024);
+    if (*new_offset > INT64_MAX) {
+        return -EINVAL;
+    }
 
     return bdrv_truncate(bs->file, *new_offset + s->block_size,
                          PREALLOC_MODE_OFF, NULL);

block/vmdk.c

@@ -2236,6 +2236,7 @@ static int vmdk_check(BlockDriverState *bs, BdrvCheckResult *result,
             fprintf(stderr,
                     "ERROR: could not find extent for sector %" PRId64 "\n",
                     sector_num);
+            ret = -EINVAL;
             break;
         }
         ret = get_cluster_offset(bs, extent, NULL,
@@ -2247,19 +2248,28 @@ static int vmdk_check(BlockDriverState *bs, BdrvCheckResult *result,
                     PRId64 "\n", sector_num);
             break;
         }
-        if (ret == VMDK_OK &&
-            cluster_offset >= bdrv_getlength(extent->file->bs))
-        {
-            fprintf(stderr,
-                    "ERROR: cluster offset for sector %"
-                    PRId64 " points after EOF\n", sector_num);
-            break;
+        if (ret == VMDK_OK) {
+            int64_t extent_len = bdrv_getlength(extent->file->bs);
+            if (extent_len < 0) {
+                fprintf(stderr,
+                        "ERROR: could not get extent file length for sector %"
+                        PRId64 "\n", sector_num);
+                ret = extent_len;
+                break;
+            }
+            if (cluster_offset >= extent_len) {
+                fprintf(stderr,
+                        "ERROR: cluster offset for sector %"
+                        PRId64 " points after EOF\n", sector_num);
+                ret = -EINVAL;
+                break;
+            }
         }
         sector_num += extent->cluster_sectors;
     }
 
     result->corruptions++;
-    return 0;
+    return ret;
 }
 
 static ImageInfoSpecific *vmdk_get_specific_info(BlockDriverState *bs)

block/vpc.c

@@ -219,6 +219,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     uint64_t pagetable_size;
     int disk_type = VHD_DYNAMIC;
     int ret;
+    int64_t bs_size;
 
     bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
                                false, errp);
@@ -411,7 +412,13 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
             }
         }
 
-        if (s->free_data_block_offset > bdrv_getlength(bs->file->bs)) {
+        bs_size = bdrv_getlength(bs->file->bs);
+        if (bs_size < 0) {
+            error_setg_errno(errp, -bs_size, "Unable to learn image size");
+            ret = bs_size;
+            goto fail;
+        }
+        if (s->free_data_block_offset > bs_size) {
             error_setg(errp, "block-vpc: free_data_block_offset points after "
                              "the end of file. The image has been truncated.");
             ret = -EINVAL;
@@ -649,7 +656,7 @@ vpc_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
     int64_t image_offset;
     int64_t n_bytes;
     int64_t bytes_done = 0;
-    int ret;
+    int ret = 0;
     VHDFooter *footer =  (VHDFooter *) s->footer_buf;
     QEMUIOVector local_qiov;
 
@@ -776,7 +783,7 @@ static int calculate_geometry(int64_t total_sectors, uint16_t* cyls,
     } else {
         *secs_per_cyl = 17;
         cyls_times_heads = total_sectors / *secs_per_cyl;
-        *heads = (cyls_times_heads + 1023) / 1024;
+        *heads = DIV_ROUND_UP(cyls_times_heads, 1024);
 
         if (*heads < 4) {
             *heads = 4;
@@ -829,7 +836,7 @@ static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
     offset = 3 * 512;
 
     memset(buf, 0xFF, 512);
-    for (i = 0; i < (num_bat_entries * 4 + 511) / 512; i++) {
+    for (i = 0; i < DIV_ROUND_UP(num_bat_entries * 4, 512); i++) {
         ret = blk_pwrite(blk, offset, buf, 512, 0);
         if (ret < 0) {
             goto fail;

block/vvfat.c

@@ -32,6 +32,7 @@
 #include "qapi/qmp/qbool.h"
 #include "qapi/qmp/qstring.h"
 #include "qemu/cutils.h"
+#include "qemu/error-report.h"
 
 #ifndef S_IWGRP
 #define S_IWGRP 0
@@ -449,7 +450,7 @@ static direntry_t *create_long_filename(BDRVVVFATState *s, const char *filename)
         return NULL;
     }
 
-    number_of_entries = (length * 2 + 25) / 26;
+    number_of_entries = DIV_ROUND_UP(length * 2, 26);
 
     for(i=0;i<number_of_entries;i++) {
         entry=array_get_next(&(s->directory));
@@ -1226,8 +1227,7 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
 
     switch (s->fat_type) {
     case 32:
-            fprintf(stderr, "Big fat greek warning: FAT32 has not been tested. "
-                "You are welcome to do so!\n");
+        warn_report("FAT32 has not been tested. You are welcome to do so!");
         break;
     case 16:
     case 12:
@@ -2554,7 +2554,7 @@ static int commit_one_file(BDRVVVFATState* s,
                 (size > offset && c >=2 && !fat_eof(s, c)));
 
         ret = vvfat_read(s->bs, cluster2sector(s, c),
-            (uint8_t*)cluster, (rest_size + 0x1ff) / 0x200);
+            (uint8_t*)cluster, DIV_ROUND_UP(rest_size, 0x200));
 
         if (ret < 0) {
             qemu_close(fd);
@@ -3028,7 +3028,8 @@ DLOG(checkpoint());
                         if (memcmp(direntries + k,
                                     array_get(&(s->directory), dir_index + k),
                                     sizeof(direntry_t))) {
-                            fprintf(stderr, "Warning: tried to write to write-protected file\n");
+                            warn_report("tried to write to write-protected "
+                                        "file");
                             return -1;
                         }
                     }

blockdev.c

@@ -44,7 +44,6 @@
 #include "qapi-visit.h"
 #include "qapi/qmp/qerror.h"
 #include "qapi/qobject-output-visitor.h"
-#include "qapi/util.h"
 #include "sysemu/sysemu.h"
 #include "block/block_int.h"
 #include "qmp-commands.h"
@@ -438,9 +437,8 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
 
     if (detect_zeroes) {
         *detect_zeroes =
-            qapi_enum_parse(BlockdevDetectZeroesOptions_lookup,
+            qapi_enum_parse(&BlockdevDetectZeroesOptions_lookup,
                             qemu_opt_get(opts, "detect-zeroes"),
-                            BLOCKDEV_DETECT_ZEROES_OPTIONS__MAX,
                             BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
                             &local_error);
         if (local_error) {
@@ -1468,8 +1466,8 @@ static int action_check_completion_mode(BlkActionState *s, Error **errp)
         error_setg(errp,
                    "Action '%s' does not support Transaction property "
                    "completion-mode = %s",
-                   TransactionActionKind_lookup[s->action->type],
-                   ActionCompletionMode_lookup[s->txn_props->completion_mode]);
+                   TransactionActionKind_str(s->action->type),
+                   ActionCompletionMode_str(s->txn_props->completion_mode));
         return -1;
     }
     return 0;
@@ -2688,7 +2686,7 @@ void qmp_block_set_io_throttle(BlockIOThrottle *arg, Error **errp)
     if (throttle_enabled(&cfg)) {
         /* Enable I/O limits if they're not enabled yet, otherwise
          * just update the throttling group. */
-        if (!blk_get_public(blk)->throttle_state) {
+        if (!blk_get_public(blk)->throttle_group_member.throttle_state) {
             blk_io_limits_enable(blk,
                                  arg->has_group ? arg->group :
                                  arg->has_device ? arg->device :
@@ -2698,7 +2696,7 @@ void qmp_block_set_io_throttle(BlockIOThrottle *arg, Error **errp)
         }
         /* Set the new throttling configuration */
         blk_set_io_limits(blk, &cfg);
-    } else if (blk_get_public(blk)->throttle_state) {
+    } else if (blk_get_public(blk)->throttle_group_member.throttle_state) {
         /* If all throttling settings are set to 0, disable I/O limits */
         blk_io_limits_disable(blk);
     }
@@ -3887,6 +3885,7 @@ 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);
@@ -3900,6 +3899,19 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
 
     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;

blockjob.c

@@ -208,7 +208,7 @@ static char *child_job_get_parent_desc(BdrvChild *c)
 {
     BlockJob *job = c->opaque;
     return g_strdup_printf("%s job '%s'",
-                           BlockJobType_lookup[job->driver->job_type],
+                           BlockJobType_str(job->driver->job_type),
                            job->id);
 }
 
@@ -553,7 +553,7 @@ BlockJobInfo *block_job_query(BlockJob *job, Error **errp)
         return NULL;
     }
     info = g_new0(BlockJobInfo, 1);
-    info->type      = g_strdup(BlockJobType_lookup[job->driver->job_type]);
+    info->type      = g_strdup(BlockJobType_str(job->driver->job_type));
     info->device    = g_strdup(job->id);
     info->len       = job->len;
     info->busy      = job->busy;
@@ -666,7 +666,7 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
     job->refcnt        = 1;
 
     error_setg(&job->blocker, "block device is in use by block job: %s",
-               BlockJobType_lookup[driver->job_type]);
+               BlockJobType_str(driver->job_type));
     block_job_add_bdrv(job, "main node", bs, 0, BLK_PERM_ALL, &error_abort);
     bs->job = job;
 

bsd-user/bsdload.c

@@ -20,22 +20,6 @@ abi_long memcpy_to_target(abi_ulong dest, const void *src,
     return 0;
 }
 
-static int in_group_p(gid_t g)
-{
-    /* return TRUE if we're in the specified group, FALSE otherwise */
-    int         ngroup;
-    int         i;
-    gid_t       grouplist[TARGET_NGROUPS];
-
-    ngroup = getgroups(TARGET_NGROUPS, grouplist);
-    for(i = 0; i < ngroup; i++) {
-        if(grouplist[i] == g) {
-            return 1;
-        }
-    }
-    return 0;
-}
-
 static int count(char ** vec)
 {
     int         i;
@@ -51,7 +35,7 @@ static int prepare_binprm(struct linux_binprm *bprm)
 {
     struct stat         st;
     int mode;
-    int retval, id_change;
+    int retval;
 
     if(fstat(bprm->fd, &st) < 0) {
         return(-errno);
@@ -67,14 +51,10 @@ static int prepare_binprm(struct linux_binprm *bprm)
 
     bprm->e_uid = geteuid();
     bprm->e_gid = getegid();
-    id_change = 0;
 
     /* Set-uid? */
     if(mode & S_ISUID) {
         bprm->e_uid = st.st_uid;
-        if(bprm->e_uid != geteuid()) {
-            id_change = 1;
-        }
     }
 
     /* Set-gid? */
@@ -85,9 +65,6 @@ static int prepare_binprm(struct linux_binprm *bprm)
      */
     if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
         bprm->e_gid = st.st_gid;
-        if (!in_group_p(bprm->e_gid)) {
-                id_change = 1;
-        }
     }
 
     memset(bprm->buf, 0, sizeof(bprm->buf));

bsd-user/elfload.c

@@ -1155,21 +1155,20 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs,
     unsigned int interpreter_type = INTERPRETER_NONE;
     unsigned char ibcs2_interpreter;
     int i;
-    abi_ulong mapped_addr;
     struct elf_phdr * elf_ppnt;
     struct elf_phdr *elf_phdata;
     abi_ulong elf_bss, k, elf_brk;
     int retval;
     char * elf_interpreter;
     abi_ulong elf_entry, interp_load_addr = 0;
-    int status;
     abi_ulong start_code, end_code, start_data, end_data;
     abi_ulong reloc_func_desc = 0;
-    abi_ulong elf_stack;
+#ifdef LOW_ELF_STACK
+    abi_ulong elf_stack = ~((abi_ulong)0UL);
+#endif
     char passed_fileno[6];
 
     ibcs2_interpreter = 0;
-    status = 0;
     load_addr = 0;
     load_bias = 0;
     elf_ex = *((struct elfhdr *) bprm->buf);          /* exec-header */
@@ -1221,7 +1220,6 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs,
     elf_brk = 0;
 
 
-    elf_stack = ~((abi_ulong)0UL);
     elf_interpreter = NULL;
     start_code = ~((abi_ulong)0UL);
     end_code = 0;
@@ -1546,7 +1544,7 @@ int load_elf_binary(struct linux_binprm * bprm, struct target_pt_regs * regs,
                and some applications "depend" upon this behavior.
                Since we do not have the power to recompile these, we
                emulate the SVr4 behavior.  Sigh.  */
-            mapped_addr = target_mmap(0, qemu_host_page_size, PROT_READ | PROT_EXEC,
+            target_mmap(0, qemu_host_page_size, PROT_READ | PROT_EXEC,
                                       MAP_FIXED | MAP_PRIVATE, -1, 0);
     }
 

bsd-user/main.c

@@ -619,9 +619,10 @@ void cpu_loop(CPUSPARCState *env)
             break;
         case EXCP_DEBUG:
             {
-                int sig;
-
-                sig = gdb_handlesig(cs, TARGET_SIGTRAP);
+#if 0
+                int sig =
+#endif
+                gdb_handlesig(cs, TARGET_SIGTRAP);
 #if 0
                 if (sig)
                   {
@@ -685,6 +686,8 @@ static void usage(void)
            "    -E var1=val2 -E var2=val2 -U LD_PRELOAD -U LD_DEBUG\n"
            "Note that if you provide several changes to single variable\n"
            "last change will stay in effect.\n"
+           "\n"
+           QEMU_HELP_BOTTOM "\n"
            ,
            TARGET_NAME,
            interp_prefix,
@@ -899,10 +902,6 @@ int main(int argc, char **argv)
     /* NOTE: we need to init the CPU at this stage to get
        qemu_host_page_size */
     cpu = cpu_init(cpu_model);
-    if (!cpu) {
-        fprintf(stderr, "Unable to find CPU definition\n");
-        exit(1);
-    }
     env = cpu->env_ptr;
 #if defined(TARGET_SPARC) || defined(TARGET_PPC)
     cpu_reset(cpu);

bsd-user/mmap.c

@@ -25,7 +25,7 @@
 //#define DEBUG_MMAP
 
 static pthread_mutex_t mmap_mutex = PTHREAD_MUTEX_INITIALIZER;
-static int __thread mmap_lock_count;
+static __thread int mmap_lock_count;
 
 void mmap_lock(void)
 {

chardev/char-fd.c

@@ -141,7 +141,6 @@ void qemu_chr_open_fd(Chardev *chr,
     qio_channel_set_name(QIO_CHANNEL(s->ioc_out), name);
     g_free(name);
     qemu_set_nonblock(fd_out);
-    s->chr = chr;
 }
 
 static void char_fd_class_init(ObjectClass *oc, void *data)

chardev/char.c

@@ -620,7 +620,7 @@ Chardev *qemu_chr_new_from_opts(QemuOpts *opts, Error **errp)
 
         error_report("Available chardev backend types: %s", str->str);
         g_string_free(str, true);
-        exit(0);
+        return NULL;
     }
 
     if (id == NULL) {
@@ -931,7 +931,7 @@ ChardevReturn *qmp_chardev_add(const char *id, ChardevBackend *backend,
     ChardevReturn *ret;
     Chardev *chr;
 
-    cc = char_get_class(ChardevBackendKind_lookup[backend->type], errp);
+    cc = char_get_class(ChardevBackendKind_str(backend->type), errp);
     if (!cc) {
         return NULL;
     }
@@ -989,7 +989,7 @@ ChardevReturn *qmp_chardev_change(const char *id, ChardevBackend *backend,
         return NULL;
     }
 
-    cc = char_get_class(ChardevBackendKind_lookup[backend->type], errp);
+    cc = char_get_class(ChardevBackendKind_str(backend->type), errp);
     if (!cc) {
         return NULL;
     }

chardev/trace-events

@@ -1,4 +1,4 @@
-# See docs/tracing.txt for syntax documentation.
+# See docs/devel/tracing.txt for syntax documentation.
 
 # chardev/wctablet.c
 wct_init(void) ""

configure

@@ -240,6 +240,11 @@ supported_target() {
     return 1
 }
 
+
+ld_has() {
+    $ld --help 2>/dev/null | grep ".$1" >/dev/null 2>&1
+}
+
 # default parameters
 source_path=$(dirname "$0")
 cpu=""
@@ -282,7 +287,6 @@ curses=""
 docs=""
 fdt=""
 netmap="no"
-pixman=""
 sdl=""
 sdlabi=""
 virtfs=""
@@ -306,6 +310,7 @@ tcg="yes"
 vhost_net="no"
 vhost_scsi="no"
 vhost_vsock="no"
+vhost_user=""
 kvm="no"
 hax="no"
 rdma=""
@@ -344,7 +349,6 @@ cocoa="no"
 softmmu="yes"
 linux_user="no"
 bsd_user="no"
-aix="no"
 blobs="yes"
 pkgversion=""
 pie=""
@@ -358,6 +362,7 @@ libusb=""
 usb_redir=""
 opengl=""
 opengl_dmabuf="no"
+cpuid_h="no"
 avx2_opt="no"
 zlib="yes"
 lzo=""
@@ -537,8 +542,22 @@ elif check_define __sun__ ; then
   targetos='SunOS'
 elif check_define __HAIKU__ ; then
   targetos='Haiku'
+elif check_define __FreeBSD__ ; then
+  targetos='FreeBSD'
+elif check_define __FreeBSD_kernel__ && check_define __GLIBC__; then
+  targetos='GNU/kFreeBSD'
+elif check_define __DragonFly__ ; then
+  targetos='DragonFly'
+elif check_define __NetBSD__; then
+  targetos='NetBSD'
+elif check_define __APPLE__; then
+  targetos='Darwin'
 else
-  targetos=$(uname -s)
+  # This is a fatal error, but don't report it yet, because we
+  # might be going to just print the --help text, or it might
+  # be the result of a missing compiler.
+  targetos='bogus'
+  bogus_os='yes'
 fi
 
 # Some host OSes need non-standard checks for which CPU to use.
@@ -611,9 +630,6 @@ case "$cpu" in
     cpu="$cpu"
     supported_cpu="yes"
   ;;
-  ia64)
-    cpu="$cpu"
-  ;;
   i386|i486|i586|i686|i86pc|BePC)
     cpu="i386"
     supported_cpu="yes"
@@ -731,23 +747,6 @@ SunOS)
   install="${INSTALL-ginstall}"
   ld="gld"
   smbd="${SMBD-/usr/sfw/sbin/smbd}"
-  needs_libsunmath="no"
-  solarisrev=$(uname -r | cut -f2 -d.)
-  if [ "$cpu" = "i386" -o "$cpu" = "x86_64" ] ; then
-    if test "$solarisrev" -le 9 ; then
-      if test -f /opt/SUNWspro/prod/lib/libsunmath.so.1; then
-        needs_libsunmath="yes"
-        QEMU_CFLAGS="-I/opt/SUNWspro/prod/include/cc $QEMU_CFLAGS"
-        LDFLAGS="-L/opt/SUNWspro/prod/lib -R/opt/SUNWspro/prod/lib $LDFLAGS"
-        LIBS="-lsunmath $LIBS"
-      else
-        error_exit "QEMU will not link correctly on Solaris 8/X86 or 9/x86 without" \
-            "libsunmath from the Sun Studio compilers tools, due to a lack of" \
-            "C99 math features in libm.so in Solaris 8/x86 and Solaris 9/x86" \
-            "Studio 11 can be downloaded from www.sun.com."
-      fi
-    fi
-  fi
   if test -f /usr/include/sys/soundcard.h ; then
     audio_drv_list="oss"
   fi
@@ -761,10 +760,6 @@ SunOS)
   LIBS="$solarisnetlibs $LIBS"
   libs_qga="$solarisnetlibs $libs_qga"
 ;;
-AIX)
-  aix="yes"
-  make="${MAKE-gmake}"
-;;
 Haiku)
   haiku="yes"
   QEMU_CFLAGS="-DB_USE_POSITIVE_POSIX_ERRORS $QEMU_CFLAGS"
@@ -782,12 +777,6 @@ Linux)
   QEMU_INCLUDES="-I\$(SRC_PATH)/linux-headers -I$(pwd)/linux-headers $QEMU_INCLUDES"
   supported_os="yes"
 ;;
-*)
-  # This is a fatal error, but don't report it yet, because we
-  # might be going to just print the --help text, or it might
-  # be the result of a missing compiler.
-  bogus_os="yes"
-;;
 esac
 
 if [ "$bsd" = "yes" ] ; then
@@ -933,12 +922,6 @@ for opt do
     # configure to be used by RPM and similar macros that set
     # lots of directory switches by default.
   ;;
-  --with-system-pixman) pixman="system"
-  ;;
-  --without-system-pixman) pixman="internal"
-  ;;
-  --without-pixman) pixman="none"
-  ;;
   --disable-sdl) sdl="no"
   ;;
   --enable-sdl) sdl="yes"
@@ -1288,6 +1271,14 @@ for opt do
   ;;
   --enable-vxhs) vxhs="yes"
   ;;
+  --disable-vhost-user) vhost_user="no"
+  ;;
+  --enable-vhost-user)
+      vhost_user="yes"
+      if test "$mingw32" = "yes"; then
+          error_exit "vhost-user isn't available on win32"
+      fi
+  ;;
   *)
       echo "ERROR: unknown option $opt"
       echo "Try '$0 --help' for more information"
@@ -1296,6 +1287,14 @@ for opt do
   esac
 done
 
+if test "$vhost_user" = ""; then
+    if test "$mingw32" = "yes"; then
+        vhost_user="no"
+    else
+        vhost_user="yes"
+    fi
+fi
+
 case "$cpu" in
     ppc)
            CPU_CFLAGS="-m32"
@@ -1524,6 +1523,7 @@ disabled with --disable-FEATURE, default is enabled if available:
   tools           build qemu-io, qemu-nbd and qemu-image tools
   vxhs            Veritas HyperScale vDisk backend support
   crypto-afalg    Linux AF_ALG crypto backend driver
+  vhost-user      vhost-user support
 
 NOTE: The object files are built at the place where configure is launched
 EOF
@@ -1582,7 +1582,7 @@ if test "$bogus_os" = "yes"; then
     # the compiler works (so the results of the check_defines we used
     # to identify the OS are reliable), if we didn't recognize the
     # host OS we should stop now.
-    error_exit "Unrecognized host OS $targetos"
+    error_exit "Unrecognized host OS (uname -s reports '$(uname -s)')"
 fi
 
 gcc_flags="-Wold-style-declaration -Wold-style-definition -Wtype-limits"
@@ -1938,24 +1938,6 @@ EOF
   fi
 fi
 
-##########################################
-# avx2 optimization requirement check
-
-cat > $TMPC << EOF
-#pragma GCC push_options
-#pragma GCC target("avx2")
-#include <cpuid.h>
-#include <immintrin.h>
-static int bar(void *a) {
-    __m256i x = *(__m256i *)a;
-    return _mm256_testz_si256(x, x);
-}
-int main(int argc, char *argv[]) { return bar(argv[0]); }
-EOF
-if compile_object "" ; then
-  avx2_opt="yes"
-fi
-
 #########################################
 # zlib check
 
@@ -2043,7 +2025,7 @@ if test "$seccomp" != "no" ; then
     arm|aarch64)
         libseccomp_minver="2.2.3"
         ;;
-    ppc|ppc64)
+    ppc|ppc64|s390x)
         libseccomp_minver="2.3.0"
         ;;
     *)
@@ -2053,8 +2035,8 @@ if test "$seccomp" != "no" ; then
 
     if test "$libseccomp_minver" != "" &&
        $pkg_config --atleast-version=$libseccomp_minver libseccomp ; then
-        libs_softmmu="$libs_softmmu $($pkg_config --libs libseccomp)"
-        QEMU_CFLAGS="$QEMU_CFLAGS $($pkg_config --cflags libseccomp)"
+        seccomp_cflags="$($pkg_config --cflags libseccomp)"
+        seccomp_libs="$($pkg_config --libs libseccomp)"
         seccomp="yes"
     else
         if test "$seccomp" = "yes" ; then
@@ -3306,39 +3288,15 @@ fi
 ##########################################
 # pixman support probe
 
-if test "$pixman" = ""; then
-  if test "$want_tools" = "no" -a "$softmmu" = "no"; then
-    pixman="none"
-  elif $pkg_config --atleast-version=0.21.8 pixman-1 > /dev/null 2>&1; then
-    pixman="system"
-  else
-    pixman="internal"
-  fi
-fi
-if test "$pixman" = "none"; then
-  if test "$want_tools" != "no" -o "$softmmu" != "no"; then
-    error_exit "pixman disabled but system emulation or tools build" \
-        "enabled.  You can turn off pixman only if you also" \
-        "disable all system emulation targets and the tools" \
-        "build with '--disable-tools --disable-system'."
-  fi
+if test "$want_tools" = "no" -a "$softmmu" = "no"; then
   pixman_cflags=
   pixman_libs=
-elif test "$pixman" = "system"; then
-  # pixman version has been checked above
+elif $pkg_config --atleast-version=0.21.8 pixman-1 > /dev/null 2>&1; then
   pixman_cflags=$($pkg_config --cflags pixman-1)
   pixman_libs=$($pkg_config --libs pixman-1)
 else
-  if test ! -d ${source_path}/pixman/pixman; then
-    error_exit "pixman >= 0.21.8 not present. Your options:" \
-        "  (1) Preferred: Install the pixman devel package (any recent" \
-        "      distro should have packages as Xorg needs pixman too)." \
-        "  (2) Fetch the pixman submodule, using:" \
-        "      git submodule update --init pixman"
-  fi
-  mkdir -p pixman/pixman
-  pixman_cflags="-I\$(SRC_PATH)/pixman/pixman -I\$(BUILD_DIR)/pixman/pixman"
-  pixman_libs="-L\$(BUILD_DIR)/pixman/pixman/.libs -lpixman-1"
+  error_exit "pixman >= 0.21.8 not present." \
+      "Please install the pixman devel package."
 fi
 
 ##########################################
@@ -4215,7 +4173,7 @@ elif compile_prog "" "$pthread_lib -lrt" ; then
 fi
 
 if test "$darwin" != "yes" -a "$mingw32" != "yes" -a "$solaris" != yes -a \
-        "$aix" != "yes" -a "$haiku" != "yes" ; then
+        "$haiku" != "yes" ; then
     libs_softmmu="-lutil $libs_softmmu"
 fi
 
@@ -4653,7 +4611,6 @@ fi
 ########################################
 # check if cpuid.h is usable.
 
-cpuid_h=no
 cat > $TMPC << EOF
 #include <cpuid.h>
 int main(void) {
@@ -4675,6 +4632,29 @@ if compile_prog "" "" ; then
     cpuid_h=yes
 fi
 
+##########################################
+# avx2 optimization requirement check
+#
+# There is no point enabling this if cpuid.h is not usable,
+# since we won't be able to select the new routines.
+
+if test $cpuid_h = yes; then
+  cat > $TMPC << EOF
+#pragma GCC push_options
+#pragma GCC target("avx2")
+#include <cpuid.h>
+#include <immintrin.h>
+static int bar(void *a) {
+    __m256i x = *(__m256i *)a;
+    return _mm256_testz_si256(x, x);
+}
+int main(int argc, char *argv[]) { return bar(argv[0]); }
+EOF
+  if compile_object "" ; then
+    avx2_opt="yes"
+  fi
+fi
+
 ########################################
 # check if __[u]int128_t is usable.
 
@@ -5027,7 +5007,7 @@ fi
 # Use ASLR, no-SEH and DEP if available
 if test "$mingw32" = "yes" ; then
     for flag in --dynamicbase --no-seh --nxcompat; do
-        if $ld --help 2>/dev/null | grep ".$flag" >/dev/null 2>/dev/null ; then
+        if ld_has $flag ; then
             LDFLAGS="-Wl,$flag $LDFLAGS"
         fi
     done
@@ -5038,11 +5018,18 @@ qemu_moddir=$libdir$confsuffix
 qemu_datadir=$datadir$confsuffix
 qemu_localedir="$datadir/locale"
 
+# We can only support ivshmem if we have eventfd
+if [ "$eventfd" = "yes" ]; then
+  ivshmem=yes
+fi
+
 tools=""
 if test "$want_tools" = "yes" ; then
   tools="qemu-img\$(EXESUF) qemu-io\$(EXESUF) $tools"
   if [ "$linux" = "yes" -o "$bsd" = "yes" -o "$solaris" = "yes" ] ; then
     tools="qemu-nbd\$(EXESUF) $tools"
+  fi
+  if [ "$ivshmem" = "yes" ]; then
     tools="ivshmem-client\$(EXESUF) ivshmem-server\$(EXESUF) $tools"
   fi
 fi
@@ -5282,7 +5269,6 @@ echo "static build      $static"
 if test "$darwin" = "yes" ; then
     echo "Cocoa support     $cocoa"
 fi
-echo "pixman            $pixman"
 echo "SDL support       $sdl $(echo_version $sdl $sdlversion)"
 echo "GTK support       $gtk $(echo_version $gtk $gtk_version)"
 echo "GTK GL support    $gtk_gl"
@@ -5343,6 +5329,7 @@ echo "libcap-ng support $cap_ng"
 echo "vhost-net support $vhost_net"
 echo "vhost-scsi support $vhost_scsi"
 echo "vhost-vsock support $vhost_vsock"
+echo "vhost-user support $vhost_user"
 echo "Trace backends    $trace_backends"
 if have_backend "simple"; then
 echo "Trace output file $trace_file-<pid>"
@@ -5494,16 +5481,8 @@ if test "$darwin" = "yes" ; then
   echo "CONFIG_DARWIN=y" >> $config_host_mak
 fi
 
-if test "$aix" = "yes" ; then
-  echo "CONFIG_AIX=y" >> $config_host_mak
-fi
-
 if test "$solaris" = "yes" ; then
   echo "CONFIG_SOLARIS=y" >> $config_host_mak
-  echo "CONFIG_SOLARIS_VERSION=$solarisrev" >> $config_host_mak
-  if test "$needs_libsunmath" = "yes" ; then
-    echo "CONFIG_NEEDS_LIBSUNMATH=y" >> $config_host_mak
-  fi
 fi
 if test "$haiku" = "yes" ; then
   echo "CONFIG_HAIKU=y" >> $config_host_mak
@@ -5756,12 +5735,15 @@ fi
 if test "$vhost_scsi" = "yes" ; then
   echo "CONFIG_VHOST_SCSI=y" >> $config_host_mak
 fi
-if test "$vhost_net" = "yes" ; then
+if test "$vhost_net" = "yes" -a "$vhost_user" = "yes"; then
   echo "CONFIG_VHOST_NET_USED=y" >> $config_host_mak
 fi
 if test "$vhost_vsock" = "yes" ; then
   echo "CONFIG_VHOST_VSOCK=y" >> $config_host_mak
 fi
+if test "$vhost_user" = "yes" ; then
+  echo "CONFIG_VHOST_USER=y" >> $config_host_mak
+fi
 if test "$blobs" = "yes" ; then
   echo "INSTALL_BLOBS=yes" >> $config_host_mak
 fi
@@ -5847,6 +5829,8 @@ fi
 
 if test "$seccomp" = "yes"; then
   echo "CONFIG_SECCOMP=y" >> $config_host_mak
+  echo "SECCOMP_CFLAGS=$seccomp_cflags" >> $config_host_mak
+  echo "SECCOMP_LIBS=$seccomp_libs" >> $config_host_mak
 fi
 
 # XXX: suppress that
@@ -5953,13 +5937,6 @@ if test "$live_block_migration" = "yes" ; then
   echo "CONFIG_LIVE_BLOCK_MIGRATION=y" >> $config_host_mak
 fi
 
-# USB host support
-if test "$libusb" = "yes"; then
-  echo "HOST_USB=libusb legacy" >> $config_host_mak
-else
-  echo "HOST_USB=stub" >> $config_host_mak
-fi
-
 # TPM passthrough support?
 if test "$tpm" = "yes"; then
   echo 'CONFIG_TPM=$(CONFIG_SOFTMMU)' >> $config_host_mak
@@ -6033,6 +6010,10 @@ if test "$have_utmpx" = "yes" ; then
   echo "HAVE_UTMPX=y" >> $config_host_mak
 fi
 
+if test "$ivshmem" = "yes" ; then
+  echo "CONFIG_IVSHMEM=y" >> $config_host_mak
+fi
+
 # Hold two types of flag:
 #   CONFIG_THREAD_SETNAME_BYTHREAD  - we've got a way of setting the name on
 #                                     a thread we have a handle to
@@ -6353,7 +6334,9 @@ if supported_kvm_target $target; then
     echo "CONFIG_KVM=y" >> $config_target_mak
     if test "$vhost_net" = "yes" ; then
         echo "CONFIG_VHOST_NET=y" >> $config_target_mak
-        echo "CONFIG_VHOST_NET_TEST_$target_name=y" >> $config_host_mak
+        if test "$vhost_user" = "yes" ; then
+            echo "CONFIG_VHOST_USER_NET_TEST_$target_name=y" >> $config_host_mak
+        fi
     fi
 fi
 if supported_hax_target $target; then
@@ -6425,9 +6408,6 @@ for i in $ARCH $TARGET_BASE_ARCH ; do
   i386|x86_64|x32)
     disas_config "I386"
   ;;
-  ia64*)
-    disas_config "IA64"
-  ;;
   lm32)
     disas_config "LM32"
   ;;
@@ -6493,15 +6473,25 @@ if test "$target_linux_user" = "yes" -o "$target_bsd_user" = "yes" ; then
   ldflags="$ldflags $textseg_ldflags"
 fi
 
+# Newer kernels on s390 check for an S390_PGSTE program header and
+# enable the pgste page table extensions in that case. This makes
+# the vm.allocate_pgste sysctl unnecessary. We enable this program
+# header if
+#  - we build on s390x
+#  - we build the system emulation for s390x (qemu-system-s390x)
+#  - KVM is enabled
+#  - the linker supports --s390-pgste
+if test "$TARGET_ARCH" = "s390x" -a "$target_softmmu" = "yes"  -a "$ARCH" = "s390x" -a "$kvm" = "yes"; then
+    if ld_has --s390-pgste ; then
+        ldflags="-Wl,--s390-pgste $ldflags"
+    fi
+fi
+
 echo "LDFLAGS+=$ldflags" >> $config_target_mak
 echo "QEMU_CFLAGS+=$cflags" >> $config_target_mak
 
 done # for target in $targets
 
-if [ "$pixman" = "internal" ]; then
-  echo "config-host.h: subdir-pixman" >> $config_host_mak
-fi
-
 if [ "$dtc_internal" = "yes" ]; then
   echo "config-host.h: subdir-dtc" >> $config_host_mak
 fi

contrib/libvhost-user/libvhost-user.c

@@ -161,7 +161,7 @@ vu_message_read(VuDev *dev, int conn_fd, VhostUserMsg *vmsg)
         rc = recvmsg(conn_fd, &msg, 0);
     } while (rc < 0 && (errno == EINTR || errno == EAGAIN));
 
-    if (rc <= 0) {
+    if (rc < 0) {
         vu_panic(dev, "Error while recvmsg: %s", strerror(errno));
         return false;
     }
@@ -521,6 +521,19 @@ vu_set_vring_addr_exec(VuDev *dev, VhostUserMsg *vmsg)
 
     vq->used_idx = vq->vring.used->idx;
 
+    if (vq->last_avail_idx != vq->used_idx) {
+        bool resume = dev->iface->queue_is_processed_in_order &&
+            dev->iface->queue_is_processed_in_order(dev, index);
+
+        DPRINT("Last avail index != used index: %u != %u%s\n",
+               vq->last_avail_idx, vq->used_idx,
+               resume ? ", resuming" : "");
+
+        if (resume) {
+            vq->shadow_avail_idx = vq->last_avail_idx = vq->used_idx;
+        }
+    }
+
     return false;
 }
 
@@ -806,6 +819,8 @@ vu_process_message(VuDev *dev, VhostUserMsg *vmsg)
         return vu_get_queue_num_exec(dev, vmsg);
     case VHOST_USER_SET_VRING_ENABLE:
         return vu_set_vring_enable_exec(dev, vmsg);
+    case VHOST_USER_NONE:
+        break;
     default:
         vmsg_close_fds(vmsg);
         vu_panic(dev, "Unhandled request: %d", vmsg->request);

contrib/libvhost-user/libvhost-user.h

@@ -132,6 +132,7 @@ typedef void (*vu_set_features_cb) (VuDev *dev, uint64_t features);
 typedef int (*vu_process_msg_cb) (VuDev *dev, VhostUserMsg *vmsg,
                                   int *do_reply);
 typedef void (*vu_queue_set_started_cb) (VuDev *dev, int qidx, bool started);
+typedef bool (*vu_queue_is_processed_in_order_cb) (VuDev *dev, int qidx);
 
 typedef struct VuDevIface {
     /* called by VHOST_USER_GET_FEATURES to get the features bitmask */
@@ -148,6 +149,12 @@ typedef struct VuDevIface {
     vu_process_msg_cb process_msg;
     /* tells when queues can be processed */
     vu_queue_set_started_cb queue_set_started;
+    /*
+     * If the queue is processed in order, in which case it will be
+     * resumed to vring.used->idx. This can help to support resuming
+     * on unmanaged exit/crash.
+     */
+    vu_queue_is_processed_in_order_cb queue_is_processed_in_order;
 } VuDevIface;
 
 typedef void (*vu_queue_handler_cb) (VuDev *dev, int qidx);

crypto/block-luks.c

@@ -257,47 +257,41 @@ qcrypto_block_luks_cipher_alg_lookup(QCryptoCipherAlgorithm alg,
     }
 
     error_setg(errp, "Algorithm '%s' not supported",
-               QCryptoCipherAlgorithm_lookup[alg]);
+               QCryptoCipherAlgorithm_str(alg));
     return NULL;
 }
 
 /* XXX replace with qapi_enum_parse() in future, when we can
  * make that function emit a more friendly error message */
 static int qcrypto_block_luks_name_lookup(const char *name,
-                                          const char *const *map,
-                                          size_t maplen,
+                                          const QEnumLookup *map,
                                           const char *type,
                                           Error **errp)
 {
-    size_t i;
-    for (i = 0; i < maplen; i++) {
-        if (g_str_equal(map[i], name)) {
-            return i;
-        }
-    }
+    int ret = qapi_enum_parse(map, name, -1, NULL);
 
-    error_setg(errp, "%s %s not supported", type, name);
-    return 0;
+    if (ret < 0) {
+        error_setg(errp, "%s %s not supported", type, name);
+        return 0;
+    }
+    return ret;
 }
 
 #define qcrypto_block_luks_cipher_mode_lookup(name, errp)               \
     qcrypto_block_luks_name_lookup(name,                                \
-                                   QCryptoCipherMode_lookup,            \
-                                   QCRYPTO_CIPHER_MODE__MAX,            \
+                                   &QCryptoCipherMode_lookup,           \
                                    "Cipher mode",                       \
                                    errp)
 
 #define qcrypto_block_luks_hash_name_lookup(name, errp)                 \
     qcrypto_block_luks_name_lookup(name,                                \
-                                   QCryptoHashAlgorithm_lookup,         \
-                                   QCRYPTO_HASH_ALG__MAX,               \
+                                   &QCryptoHashAlgorithm_lookup,        \
                                    "Hash algorithm",                    \
                                    errp)
 
 #define qcrypto_block_luks_ivgen_name_lookup(name, errp)                \
     qcrypto_block_luks_name_lookup(name,                                \
-                                   QCryptoIVGenAlgorithm_lookup,        \
-                                   QCRYPTO_IVGEN_ALG__MAX,              \
+                                   &QCryptoIVGenAlgorithm_lookup,       \
                                    "IV generator",                      \
                                    errp)
 
@@ -398,7 +392,7 @@ qcrypto_block_luks_essiv_cipher(QCryptoCipherAlgorithm cipher,
         break;
     default:
         error_setg(errp, "Cipher %s not supported with essiv",
-                   QCryptoCipherAlgorithm_lookup[cipher]);
+                   QCryptoCipherAlgorithm_str(cipher));
         return 0;
     }
 }
@@ -968,16 +962,16 @@ qcrypto_block_luks_create(QCryptoBlock *block,
         goto error;
     }
 
-    cipher_mode = QCryptoCipherMode_lookup[luks_opts.cipher_mode];
-    ivgen_alg = QCryptoIVGenAlgorithm_lookup[luks_opts.ivgen_alg];
+    cipher_mode = QCryptoCipherMode_str(luks_opts.cipher_mode);
+    ivgen_alg = QCryptoIVGenAlgorithm_str(luks_opts.ivgen_alg);
     if (luks_opts.has_ivgen_hash_alg) {
-        ivgen_hash_alg = QCryptoHashAlgorithm_lookup[luks_opts.ivgen_hash_alg];
+        ivgen_hash_alg = QCryptoHashAlgorithm_str(luks_opts.ivgen_hash_alg);
         cipher_mode_spec = g_strdup_printf("%s-%s:%s", cipher_mode, ivgen_alg,
                                            ivgen_hash_alg);
     } else {
         cipher_mode_spec = g_strdup_printf("%s-%s", cipher_mode, ivgen_alg);
     }
-    hash_alg = QCryptoHashAlgorithm_lookup[luks_opts.hash_alg];
+    hash_alg = QCryptoHashAlgorithm_str(luks_opts.hash_alg);
 
 
     if (strlen(cipher_alg) >= QCRYPTO_BLOCK_LUKS_CIPHER_NAME_LEN) {

crypto/block.c

@@ -61,7 +61,7 @@ QCryptoBlock *qcrypto_block_open(QCryptoBlockOpenOptions *options,
     if (options->format >= G_N_ELEMENTS(qcrypto_block_drivers) ||
         !qcrypto_block_drivers[options->format]) {
         error_setg(errp, "Unsupported block driver %s",
-                   QCryptoBlockFormat_lookup[options->format]);
+                   QCryptoBlockFormat_str(options->format));
         g_free(block);
         return NULL;
     }
@@ -92,7 +92,7 @@ QCryptoBlock *qcrypto_block_create(QCryptoBlockCreateOptions *options,
     if (options->format >= G_N_ELEMENTS(qcrypto_block_drivers) ||
         !qcrypto_block_drivers[options->format]) {
         error_setg(errp, "Unsupported block driver %s",
-                   QCryptoBlockFormat_lookup[options->format]);
+                   QCryptoBlockFormat_str(options->format));
         g_free(block);
         return NULL;
     }

crypto/cipher-afalg.c

@@ -52,7 +52,7 @@ qcrypto_afalg_cipher_format_name(QCryptoCipherAlgorithm alg,
         return NULL;
     }
 
-    mode_name = QCryptoCipherMode_lookup[mode];
+    mode_name = QCryptoCipherMode_str(mode);
     name = g_strdup_printf("%s(%s)", mode_name, alg_name);
 
     return name;

crypto/cipher-builtin.c

@@ -247,7 +247,7 @@ qcrypto_cipher_init_aes(QCryptoCipherMode mode,
         mode != QCRYPTO_CIPHER_MODE_ECB &&
         mode != QCRYPTO_CIPHER_MODE_XTS) {
         error_setg(errp, "Unsupported cipher mode %s",
-                   QCryptoCipherMode_lookup[mode]);
+                   QCryptoCipherMode_str(mode));
         return NULL;
     }
 
@@ -379,7 +379,7 @@ qcrypto_cipher_init_des_rfb(QCryptoCipherMode mode,
 
     if (mode != QCRYPTO_CIPHER_MODE_ECB) {
         error_setg(errp, "Unsupported cipher mode %s",
-                   QCryptoCipherMode_lookup[mode]);
+                   QCryptoCipherMode_str(mode));
         return NULL;
     }
 
@@ -440,7 +440,7 @@ static QCryptoCipherBuiltin *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg,
         break;
     default:
         error_setg(errp, "Unsupported cipher mode %s",
-                   QCryptoCipherMode_lookup[mode]);
+                   QCryptoCipherMode_str(mode));
         return NULL;
     }
 
@@ -460,7 +460,7 @@ static QCryptoCipherBuiltin *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg,
     default:
         error_setg(errp,
                    "Unsupported cipher algorithm %s",
-                   QCryptoCipherAlgorithm_lookup[alg]);
+                   QCryptoCipherAlgorithm_str(alg));
         return NULL;
     }
 

crypto/cipher-gcrypt.c

@@ -105,7 +105,7 @@ static QCryptoCipherGcrypt *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg,
         break;
     default:
         error_setg(errp, "Unsupported cipher mode %s",
-                   QCryptoCipherMode_lookup[mode]);
+                   QCryptoCipherMode_str(mode));
         return NULL;
     }
 
@@ -160,7 +160,7 @@ static QCryptoCipherGcrypt *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg,
 
     default:
         error_setg(errp, "Unsupported cipher algorithm %s",
-                   QCryptoCipherAlgorithm_lookup[alg]);
+                   QCryptoCipherAlgorithm_str(alg));
         return NULL;
     }
 

crypto/cipher-nettle.c

@@ -281,7 +281,7 @@ static QCryptoCipherNettle *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg,
         break;
     default:
         error_setg(errp, "Unsupported cipher mode %s",
-                   QCryptoCipherMode_lookup[mode]);
+                   QCryptoCipherMode_str(mode));
         return NULL;
     }
 
@@ -420,7 +420,7 @@ static QCryptoCipherNettle *qcrypto_cipher_ctx_new(QCryptoCipherAlgorithm alg,
 
     default:
         error_setg(errp, "Unsupported cipher algorithm %s",
-                   QCryptoCipherAlgorithm_lookup[alg]);
+                   QCryptoCipherAlgorithm_str(alg));
         goto error;
     }
 
@@ -491,7 +491,7 @@ qcrypto_nettle_cipher_encrypt(QCryptoCipher *cipher,
 
     default:
         error_setg(errp, "Unsupported cipher mode %s",
-                   QCryptoCipherMode_lookup[cipher->mode]);
+                   QCryptoCipherMode_str(cipher->mode));
         return -1;
     }
     return 0;
@@ -537,7 +537,7 @@ qcrypto_nettle_cipher_decrypt(QCryptoCipher *cipher,
 
     default:
         error_setg(errp, "Unsupported cipher mode %s",
-                   QCryptoCipherMode_lookup[cipher->mode]);
+                   QCryptoCipherMode_str(cipher->mode));
         return -1;
     }
     return 0;

crypto/hmac-gcrypt.c

@@ -52,7 +52,7 @@ void *qcrypto_hmac_ctx_new(QCryptoHashAlgorithm alg,
 
     if (!qcrypto_hmac_supports(alg)) {
         error_setg(errp, "Unsupported hmac algorithm %s",
-                   QCryptoHashAlgorithm_lookup[alg]);
+                   QCryptoHashAlgorithm_str(alg));
         return NULL;
     }
 

crypto/hmac-glib.c

@@ -58,7 +58,7 @@ void *qcrypto_hmac_ctx_new(QCryptoHashAlgorithm alg,
 
     if (!qcrypto_hmac_supports(alg)) {
         error_setg(errp, "Unsupported hmac algorithm %s",
-                   QCryptoHashAlgorithm_lookup[alg]);
+                   QCryptoHashAlgorithm_str(alg));
         return NULL;
     }
 

crypto/hmac-nettle.c

@@ -106,7 +106,7 @@ void *qcrypto_hmac_ctx_new(QCryptoHashAlgorithm alg,
 
     if (!qcrypto_hmac_supports(alg)) {
         error_setg(errp, "Unsupported hmac algorithm %s",
-                   QCryptoHashAlgorithm_lookup[alg]);
+                   QCryptoHashAlgorithm_str(alg));
         return NULL;
     }
 

crypto/pbkdf-gcrypt.c

@@ -68,7 +68,7 @@ int qcrypto_pbkdf2(QCryptoHashAlgorithm hash,
         hash_map[hash] == GCRY_MD_NONE) {
         error_setg_errno(errp, ENOSYS,
                          "PBKDF does not support hash algorithm %s",
-                         QCryptoHashAlgorithm_lookup[hash]);
+                         QCryptoHashAlgorithm_str(hash));
         return -1;
     }
 

crypto/pbkdf-nettle.c

@@ -110,7 +110,7 @@ int qcrypto_pbkdf2(QCryptoHashAlgorithm hash,
     default:
         error_setg_errno(errp, ENOSYS,
                          "PBKDF does not support hash algorithm %s",
-                         QCryptoHashAlgorithm_lookup[hash]);
+                         QCryptoHashAlgorithm_str(hash));
         return -1;
     }
     return 0;

crypto/secret.c

@@ -378,7 +378,7 @@ qcrypto_secret_class_init(ObjectClass *oc, void *data)
                                    NULL);
     object_class_property_add_enum(oc, "format",
                                    "QCryptoSecretFormat",
-                                   QCryptoSecretFormat_lookup,
+                                   &QCryptoSecretFormat_lookup,
                                    qcrypto_secret_prop_get_format,
                                    qcrypto_secret_prop_set_format,
                                    NULL);

crypto/tlscreds.c

@@ -233,7 +233,7 @@ qcrypto_tls_creds_class_init(ObjectClass *oc, void *data)
                                   NULL);
     object_class_property_add_enum(oc, "endpoint",
                                    "QCryptoTLSCredsEndpoint",
-                                   QCryptoTLSCredsEndpoint_lookup,
+                                   &QCryptoTLSCredsEndpoint_lookup,
                                    qcrypto_tls_creds_prop_get_endpoint,
                                    qcrypto_tls_creds_prop_set_endpoint,
                                    NULL);

crypto/trace-events

@@ -1,4 +1,4 @@
-# See docs/tracing.txt for syntax documentation.
+# See docs/devel/tracing.txt for syntax documentation.
 
 # crypto/tlscreds.c
 qcrypto_tls_creds_load_dh(void *creds, const char *filename) "TLS creds load DH creds=%p filename=%s"

default-configs/pci.mak

@@ -41,6 +41,6 @@ CONFIG_SDHCI=y
 CONFIG_EDU=y
 CONFIG_VGA=y
 CONFIG_VGA_PCI=y
-CONFIG_IVSHMEM=$(CONFIG_EVENTFD)
+CONFIG_IVSHMEM_DEVICE=$(CONFIG_IVSHMEM)
 CONFIG_ROCKER=y
-CONFIG_VHOST_USER_SCSI=$(CONFIG_LINUX)
+CONFIG_VHOST_USER_SCSI=$(call land,$(CONFIG_VHOST_USER),$(CONFIG_LINUX))

default-configs/ppc-softmmu.mak

@@ -3,6 +3,7 @@
 include pci.mak
 include sound.mak
 include usb.mak
+CONFIG_PPC4XX=y
 CONFIG_ESCC=y
 CONFIG_M48T59=y
 CONFIG_SERIAL=y
@@ -17,6 +18,7 @@ CONFIG_PREP_PCI=y
 CONFIG_I82378=y
 CONFIG_PC87312=y
 CONFIG_MACIO=y
+CONFIG_SUNGEM=y
 CONFIG_PCSPK=y
 CONFIG_CS4231A=y
 CONFIG_CUDA=y
@@ -41,7 +43,7 @@ CONFIG_XILINX_ETHLITE=y
 CONFIG_PREP=y
 CONFIG_MAC=y
 CONFIG_E500=y
-CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
+CONFIG_OPENPIC_KVM=$(call land,$(CONFIG_E500),$(CONFIG_KVM))
 CONFIG_PLATFORM_BUS=y
 CONFIG_ETSEC=y
 CONFIG_LIBDECNUMBER=y

default-configs/ppc64-softmmu.mak

@@ -3,6 +3,7 @@
 include pci.mak
 include sound.mak
 include usb.mak
+CONFIG_PPC4XX=y
 CONFIG_VIRTIO_VGA=y
 CONFIG_ESCC=y
 CONFIG_M48T59=y
@@ -47,7 +48,7 @@ CONFIG_POWERNV=y
 CONFIG_PREP=y
 CONFIG_MAC=y
 CONFIG_E500=y
-CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
+CONFIG_OPENPIC_KVM=$(call land,$(CONFIG_E500),$(CONFIG_KVM))
 CONFIG_PLATFORM_BUS=y
 CONFIG_ETSEC=y
 CONFIG_LIBDECNUMBER=y
@@ -55,7 +56,7 @@ CONFIG_SM501=y
 # For pSeries
 CONFIG_XICS=$(CONFIG_PSERIES)
 CONFIG_XICS_SPAPR=$(CONFIG_PSERIES)
-CONFIG_XICS_KVM=$(and $(CONFIG_PSERIES),$(CONFIG_KVM))
+CONFIG_XICS_KVM=$(call land,$(CONFIG_PSERIES),$(CONFIG_KVM))
 # For PReP
 CONFIG_SERIAL_ISA=y
 CONFIG_MC146818RTC=y