Update version for 2.6.2 release

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

.travis.yml

@@ -42,83 +42,49 @@ notifications:
 env:
   global:
     - TEST_CMD="make check"
-    - EXTRA_CONFIG=""
   matrix:
-    # Group major targets together with their linux-user counterparts
-    - TARGETS=alpha-softmmu,alpha-linux-user,cris-softmmu,cris-linux-user,m68k-softmmu,m68k-linux-user,microblaze-softmmu,microblazeel-softmmu,microblaze-linux-user,microblazeel-linux-user
-    - TARGETS=arm-softmmu,arm-linux-user,armeb-linux-user,aarch64-softmmu,aarch64-linux-user
-    - TARGETS=i386-softmmu,i386-linux-user,x86_64-softmmu,x86_64-linux-user
-    - TARGETS=mips-softmmu,mips64-softmmu,mips64el-softmmu,mipsel-softmmu,mips-linux-user,mips64-linux-user,mips64el-linux-user,mipsel-linux-user,mipsn32-linux-user,mipsn32el-linux-user
-    - TARGETS=or32-softmmu,or32-linux-user,ppc-softmmu,ppc64-softmmu,ppcemb-softmmu,ppc-linux-user,ppc64-linux-user,ppc64abi32-linux-user,ppc64le-linux-user
-    - TARGETS=s390x-softmmu,s390x-linux-user,sh4-softmmu,sh4eb-softmmu,sh4-linux-user,sh4eb-linux-user,sparc-softmmu,sparc64-softmmu,sparc-linux-user,sparc32plus-linux-user,sparc64-linux-user,unicore32-softmmu,unicore32-linux-user
-    # Group remaining softmmu only targets into one build
-    - TARGETS=lm32-softmmu,moxie-softmmu,tricore-softmmu,xtensa-softmmu,xtensaeb-softmmu
+    - CONFIG=""
+    - CONFIG="--enable-debug --enable-debug-tcg --enable-trace-backends=log"
+    - CONFIG="--disable-linux-aio --disable-cap-ng --disable-attr --disable-brlapi --disable-uuid --disable-libusb"
+    - CONFIG="--enable-modules"
+    - CONFIG="--with-coroutine=ucontext"
+    - CONFIG="--with-coroutine=sigaltstack"
 git:
   # we want to do this ourselves
   submodules: false
 before_install:
+  - if [ "$TRAVIS_OS_NAME" == "osx" ]; then brew update ; fi
+  - if [ "$TRAVIS_OS_NAME" == "osx" ]; then brew install libffi gettext glib pixman ; fi
   - wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
   - git submodule update --init --recursive
 before_script:
-  - ./configure --target-list=${TARGETS} --enable-debug-tcg ${EXTRA_CONFIG}
+  - ./configure ${CONFIG}
 script:
-  - make -j2 && ${TEST_CMD}
+  - make -j3 && ${TEST_CMD}
 matrix:
-  # We manually include a number of additional build for non-standard bits
   include:
-    # Debug related options
-    - env: TARGETS=x86_64-softmmu
-           EXTRA_CONFIG="--enable-debug"
+    # Sparse is GCC only
+    - env: CONFIG="--enable-sparse"
       compiler: gcc
-    # We currently disable "make check"
-    - env: TARGETS=alpha-softmmu
-           EXTRA_CONFIG="--enable-debug --enable-tcg-interpreter"
+    # gprof/gcov are GCC features
+    - env: CONFIG="--enable-gprof --enable-gcov --disable-pie"
+      compiler: gcc
+    # We manually include builds which we disable "make check" for
+    - env: CONFIG="--enable-debug --enable-tcg-interpreter"
            TEST_CMD=""
       compiler: gcc
-    # Disable a few of the optional features
-    - env: TARGETS=x86_64-softmmu
-           EXTRA_CONFIG="--disable-linux-aio --disable-cap-ng --disable-attr --disable-brlapi --disable-uuid --disable-libusb"
-      compiler: gcc
-    # Currently configure doesn't force --disable-pie
-    - env: TARGETS=x86_64-softmmu
-           EXTRA_CONFIG="--enable-gprof --enable-gcov --disable-pie"
-      compiler: gcc
-    # Sparse
-    - env: TARGETS=x86_64-softmmu
-           EXTRA_CONFIG="--enable-sparse"
-      compiler: gcc
-    # Modules
-    - env: TARGETS=arm-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-modules"
-      compiler: gcc
-    # All the trace backends (apart from dtrace)
-    - env: TARGETS=i386-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=log"
-      compiler: gcc
-    # We currently disable "make check" (until 41fc57e44ed regression fixed)
-    - env: TARGETS=x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=simple"
+    - env: CONFIG="--enable-trace-backends=simple"
            TEST_CMD=""
       compiler: gcc
-    # We currently disable "make check"
-    - env: TARGETS=x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=ftrace"
+    - env: CONFIG="--enable-trace-backends=ftrace"
            TEST_CMD=""
       compiler: gcc
-    # We currently disable "make check"
-    - env: TARGETS=x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backends=ust"
+    - env: CONFIG="--enable-trace-backends=ust"
            TEST_CMD=""
       compiler: gcc
-    # All the co-routine backends (apart from windows)
-    # We currently disable "make check"
-    - env: TARGETS=x86_64-softmmu
-           EXTRA_CONFIG="--with-coroutine=gthread"
+    - env: CONFIG="--with-coroutine=gthread"
            TEST_CMD=""
       compiler: gcc
-    - env: TARGETS=x86_64-softmmu
-           EXTRA_CONFIG="--with-coroutine=ucontext"
-      compiler: gcc
-    - env: TARGETS=x86_64-softmmu
-           EXTRA_CONFIG="--with-coroutine=sigaltstack"
-      compiler: gcc
+    - env: CONFIG=""
+      os: osx
+      compiler: clang

MAINTAINERS

@@ -278,7 +278,8 @@ Guest CPU Cores (Xen):
 ----------------------
 
 X86
-M: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
+M: Stefano Stabellini <sstabellini@kernel.org>
+M: Anthony Perard <anthony.perard@citrix.com>
 L: xen-devel@lists.xensource.com
 S: Supported
 F: xen-*
@@ -357,10 +358,7 @@ F: include/hw/timer/a9gtimer.h
 F: include/hw/timer/arm_mptimer.h
 
 Exynos
-M: Evgeny Voevodin <e.voevodin@samsung.com>
-M: Maksim Kozlov <m.kozlov@samsung.com>
 M: Igor Mitsyanko <i.mitsyanko@gmail.com>
-M: Dmitry Solodkiy <d.solodkiy@samsung.com>
 L: qemu-arm@nongnu.org
 S: Maintained
 F: hw/*/exynos*
@@ -987,6 +985,7 @@ F: tests/intel-hda-test.c
 
 Block layer core
 M: Kevin Wolf <kwolf@redhat.com>
+M: Max Reitz <mreitz@redhat.com>
 L: qemu-block@nongnu.org
 S: Supported
 F: block*
@@ -1000,6 +999,7 @@ T: git git://repo.or.cz/qemu/kevin.git block
 
 Block I/O path
 M: Stefan Hajnoczi <stefanha@redhat.com>
+M: Fam Zheng <famz@redhat.com>
 L: qemu-block@nongnu.org
 S: Supported
 F: async.c
@@ -1050,7 +1050,6 @@ M: Andreas Färber <afaerber@suse.de>
 S: Supported
 F: qom/cpu.c
 F: include/qom/cpu.h
-F: target-i386/cpu.c
 
 ICC Bus
 M: Igor Mammedov <imammedo@redhat.com>
@@ -1156,8 +1155,6 @@ M: Eduardo Habkost <ehabkost@redhat.com>
 S: Maintained
 F: numa.c
 F: include/sysemu/numa.h
-K: numa|NUMA
-K: srat|SRAT
 T: git git://github.com/ehabkost/qemu.git numa
 
 QAPI
@@ -1570,6 +1567,7 @@ F: block/win32-aio.c
 
 qcow2
 M: Kevin Wolf <kwolf@redhat.com>
+M: Max Reitz <mreitz@redhat.com>
 L: qemu-block@nongnu.org
 S: Supported
 F: block/qcow2*
@@ -1582,6 +1580,7 @@ F: block/qcow.c
 
 blkdebug
 M: Kevin Wolf <kwolf@redhat.com>
+M: Max Reitz <mreitz@redhat.com>
 L: qemu-block@nongnu.org
 S: Supported
 F: block/blkdebug.c

VERSION

@@ -1 +1 @@
-2.5.50
+2.6.2

aio-posix.c

@@ -282,10 +282,12 @@ bool aio_pending(AioContext *ctx)
         int revents;
 
         revents = node->pfd.revents & node->pfd.events;
-        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
+        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read &&
+            aio_node_check(ctx, node->is_external)) {
             return true;
         }
-        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
+        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write &&
+            aio_node_check(ctx, node->is_external)) {
             return true;
         }
     }
@@ -323,6 +325,7 @@ bool aio_dispatch(AioContext *ctx)
 
         if (!node->deleted &&
             (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) &&
+            aio_node_check(ctx, node->is_external) &&
             node->io_read) {
             node->io_read(node->opaque);
 
@@ -333,6 +336,7 @@ bool aio_dispatch(AioContext *ctx)
         }
         if (!node->deleted &&
             (revents & (G_IO_OUT | G_IO_ERR)) &&
+            aio_node_check(ctx, node->is_external) &&
             node->io_write) {
             node->io_write(node->opaque);
             progress = true;

arch_init.c

@@ -31,6 +31,7 @@
 #include "qemu/error-report.h"
 #include "qmp-commands.h"
 #include "hw/acpi/acpi.h"
+#include "qemu/help_option.h"
 
 #ifdef TARGET_SPARC
 int graphic_width = 1024;

async.c

@@ -23,6 +23,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/aio.h"
 #include "block/thread-pool.h"

audio/audio.c

@@ -27,6 +27,7 @@
 #include "monitor/monitor.h"
 #include "qemu/timer.h"
 #include "sysemu/sysemu.h"
+#include "qemu/cutils.h"
 
 #define AUDIO_CAP "audio"
 #include "audio_int.h"
@@ -1869,8 +1870,7 @@ static void audio_init (void)
         }
         conf.period.ticks = 1;
     } else {
-        conf.period.ticks =
-            muldiv64 (1, get_ticks_per_sec (), conf.period.hertz);
+        conf.period.ticks = NANOSECONDS_PER_SECOND / conf.period.hertz;
     }
 
     e = qemu_add_vm_change_state_handler (audio_vm_change_state_handler, s);

audio/mixeng.c

@@ -270,7 +270,7 @@ f_sample *mixeng_clip[2][2][2][3] = {
  * August 21, 1998
  * Copyright 1998 Fabrice Bellard.
  *
- * [Rewrote completly the code of Lance Norskog And Sundry
+ * [Rewrote completely the code of Lance Norskog And Sundry
  * Contributors with a more efficient algorithm.]
  *
  * This source code is freely redistributable and may be used for

audio/noaudio.c

@@ -49,8 +49,8 @@ static int no_run_out (HWVoiceOut *hw, int live)
 
     now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
     ticks = now - no->old_ticks;
-    bytes = muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());
-    bytes = audio_MIN (bytes, INT_MAX);
+    bytes = muldiv64(ticks, hw->info.bytes_per_second, NANOSECONDS_PER_SECOND);
+    bytes = audio_MIN(bytes, INT_MAX);
     samples = bytes >> hw->info.shift;
 
     no->old_ticks = now;
@@ -61,7 +61,7 @@ static int no_run_out (HWVoiceOut *hw, int live)
 
 static int no_write (SWVoiceOut *sw, void *buf, int len)
 {
-    return audio_pcm_sw_write (sw, buf, len);
+    return audio_pcm_sw_write(sw, buf, len);
 }
 
 static int no_init_out(HWVoiceOut *hw, struct audsettings *as, void *drv_opaque)
@@ -106,7 +106,7 @@ static int no_run_in (HWVoiceIn *hw)
         int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
         int64_t ticks = now - no->old_ticks;
         int64_t bytes =
-            muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());
+            muldiv64(ticks, hw->info.bytes_per_second, NANOSECONDS_PER_SECOND);
 
         no->old_ticks = now;
         bytes = audio_MIN (bytes, INT_MAX);

audio/ossaudio.c

@@ -898,7 +898,7 @@ static struct audio_option oss_options[] = {
         .name  = "EXCLUSIVE",
         .tag   = AUD_OPT_BOOL,
         .valp  = &glob_conf.exclusive,
-        .descr = "Open device in exclusive mode (vmix wont work)"
+        .descr = "Open device in exclusive mode (vmix won't work)"
     },
 #ifdef USE_DSP_POLICY
     {

audio/spiceaudio.c

@@ -104,11 +104,11 @@ static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)
 
     now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
     ticks = now - rate->start_ticks;
-    bytes = muldiv64 (ticks, info->bytes_per_second, get_ticks_per_sec ());
+    bytes = muldiv64(ticks, info->bytes_per_second, NANOSECONDS_PER_SECOND);
     samples = (bytes - rate->bytes_sent) >> info->shift;
     if (samples < 0 || samples > 65536) {
         error_report("Resetting rate control (%" PRId64 " samples)", samples);
-        rate_start (rate);
+        rate_start(rate);
         samples = 0;
     }
     rate->bytes_sent += samples << info->shift;

audio/wavaudio.c

@@ -51,7 +51,7 @@ static int wav_run_out (HWVoiceOut *hw, int live)
     int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
     int64_t ticks = now - wav->old_ticks;
     int64_t bytes =
-        muldiv64 (ticks, hw->info.bytes_per_second, get_ticks_per_sec ());
+        muldiv64(ticks, hw->info.bytes_per_second, NANOSECONDS_PER_SECOND);
 
     if (bytes > INT_MAX) {
         samples = INT_MAX >> hw->info.shift;

backends/baum.c

@@ -22,6 +22,7 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "sysemu/char.h"
 #include "qemu/timer.h"
@@ -336,7 +337,7 @@ static int baum_eat_packet(BaumDriverState *baum, const uint8_t *buf, int len)
 
         /* Allow 100ms to complete the DisplayData packet */
         timer_mod(baum->cellCount_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
-                       get_ticks_per_sec() / 10);
+                       NANOSECONDS_PER_SECOND / 10);
         for (i = 0; i < baum->x * baum->y ; i++) {
             EAT(c);
             cells[i] = c;

backends/hostmem-file.c

@@ -10,6 +10,7 @@
  * See the COPYING file in the top-level directory.
  */
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "sysemu/hostmem.h"
 #include "sysemu/sysemu.h"
@@ -51,11 +52,14 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
     error_setg(errp, "-mem-path not supported on this host");
 #else
     if (!memory_region_size(&backend->mr)) {
+        gchar *path;
         backend->force_prealloc = mem_prealloc;
+        path = object_get_canonical_path(OBJECT(backend));
         memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
-                                 object_get_canonical_path(OBJECT(backend)),
+                                 path,
                                  backend->size, fb->share,
                                  fb->mem_path, errp);
+        g_free(path);
     }
 #endif
 }
@@ -117,11 +121,19 @@ file_backend_instance_init(Object *o)
                             set_mem_path, NULL);
 }
 
+static void file_backend_instance_finalize(Object *o)
+{
+    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
+
+    g_free(fb->mem_path);
+}
+
 static const TypeInfo file_backend_info = {
     .name = TYPE_MEMORY_BACKEND_FILE,
     .parent = TYPE_MEMORY_BACKEND,
     .class_init = file_backend_class_init,
     .instance_init = file_backend_instance_init,
+    .instance_finalize = file_backend_instance_finalize,
     .instance_size = sizeof(HostMemoryBackendFile),
 };
 

backends/hostmem-ram.c

@@ -11,6 +11,7 @@
  */
 #include "qemu/osdep.h"
 #include "sysemu/hostmem.h"
+#include "qapi/error.h"
 #include "qom/object_interfaces.h"
 
 #define TYPE_MEMORY_BACKEND_RAM "memory-backend-ram"

backends/hostmem.c

@@ -12,6 +12,7 @@
 #include "qemu/osdep.h"
 #include "sysemu/hostmem.h"
 #include "hw/boards.h"
+#include "qapi/error.h"
 #include "qapi/visitor.h"
 #include "qapi-types.h"
 #include "qapi-visit.h"

backends/rng-egd.c

@@ -13,6 +13,7 @@
 #include "qemu/osdep.h"
 #include "sysemu/rng.h"
 #include "sysemu/char.h"
+#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "hw/qdev.h" /* just for DEFINE_PROP_CHR */
 

backends/rng-random.c

@@ -13,6 +13,7 @@
 #include "qemu/osdep.h"
 #include "sysemu/rng-random.h"
 #include "sysemu/rng.h"
+#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/main-loop.h"
 

backends/rng.c

@@ -12,6 +12,7 @@
 
 #include "qemu/osdep.h"
 #include "sysemu/rng.h"
+#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qom/object_interfaces.h"
 

backends/tpm.c

@@ -14,6 +14,7 @@
 
 #include "qemu/osdep.h"
 #include "sysemu/tpm_backend.h"
+#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "sysemu/tpm.h"
 #include "qemu/thread.h"

block.c

@@ -22,7 +22,6 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
-#include "qemu-common.h"
 #include "trace.h"
 #include "block/block_int.h"
 #include "block/blockjob.h"
@@ -40,6 +39,8 @@
 #include "qemu/timer.h"
 #include "qapi-event.h"
 #include "block/throttle-groups.h"
+#include "qemu/cutils.h"
+#include "qemu/id.h"
 
 #ifdef CONFIG_BSD
 #include <sys/ioctl.h>
@@ -288,6 +289,11 @@ static int bdrv_is_whitelisted(BlockDriver *drv, bool read_only)
     return 0;
 }
 
+bool bdrv_uses_whitelist(void)
+{
+    return use_bdrv_whitelist;
+}
+
 typedef struct CreateCo {
     BlockDriver *drv;
     char *filename;
@@ -639,21 +645,23 @@ int bdrv_parse_discard_flags(const char *mode, int *flags)
  *
  * Return 0 on success, -1 if the cache mode was invalid.
  */
-int bdrv_parse_cache_flags(const char *mode, int *flags)
+int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough)
 {
     *flags &= ~BDRV_O_CACHE_MASK;
 
     if (!strcmp(mode, "off") || !strcmp(mode, "none")) {
-        *flags |= BDRV_O_NOCACHE | BDRV_O_CACHE_WB;
+        *writethrough = false;
+        *flags |= BDRV_O_NOCACHE;
     } else if (!strcmp(mode, "directsync")) {
+        *writethrough = true;
         *flags |= BDRV_O_NOCACHE;
     } else if (!strcmp(mode, "writeback")) {
-        *flags |= BDRV_O_CACHE_WB;
+        *writethrough = false;
     } else if (!strcmp(mode, "unsafe")) {
-        *flags |= BDRV_O_CACHE_WB;
+        *writethrough = false;
         *flags |= BDRV_O_NO_FLUSH;
     } else if (!strcmp(mode, "writethrough")) {
-        /* this is the default */
+        *writethrough = true;
     } else {
         return -1;
     }
@@ -672,7 +680,6 @@ static void bdrv_temp_snapshot_options(int *child_flags, QDict *child_options,
     *child_flags = (parent_flags & ~BDRV_O_SNAPSHOT) | BDRV_O_TEMPORARY;
 
     /* For temporary files, unconditional cache=unsafe is fine */
-    qdict_set_default_str(child_options, BDRV_OPT_CACHE_WB, "on");
     qdict_set_default_str(child_options, BDRV_OPT_CACHE_DIRECT, "off");
     qdict_set_default_str(child_options, BDRV_OPT_CACHE_NO_FLUSH, "on");
 }
@@ -697,11 +704,11 @@ static void bdrv_inherited_options(int *child_flags, QDict *child_options,
     /* Our block drivers take care to send flushes and respect unmap policy,
      * so we can default to enable both on lower layers regardless of the
      * corresponding parent options. */
-    qdict_set_default_str(child_options, BDRV_OPT_CACHE_WB, "on");
     flags |= BDRV_O_UNMAP;
 
     /* Clear flags that only apply to the top layer */
-    flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING | BDRV_O_COPY_ON_READ);
+    flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING | BDRV_O_COPY_ON_READ |
+               BDRV_O_NO_IO);
 
     *child_flags = flags;
 }
@@ -721,7 +728,7 @@ static void bdrv_inherited_fmt_options(int *child_flags, QDict *child_options,
     child_file.inherit_options(child_flags, child_options,
                                parent_flags, parent_options);
 
-    *child_flags &= ~BDRV_O_PROTOCOL;
+    *child_flags &= ~(BDRV_O_PROTOCOL | BDRV_O_NO_IO);
 }
 
 const BdrvChildRole child_format = {
@@ -737,8 +744,8 @@ static void bdrv_backing_options(int *child_flags, QDict *child_options,
 {
     int flags = parent_flags;
 
-    /* The cache mode is inherited unmodified for backing files */
-    qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_WB);
+    /* The cache mode is inherited unmodified for backing files; except WCE,
+     * which is only applied on the top level (BlockBackend) */
     qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_DIRECT);
     qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_NO_FLUSH);
 
@@ -757,7 +764,7 @@ static const BdrvChildRole child_backing = {
 
 static int bdrv_open_flags(BlockDriverState *bs, int flags)
 {
-    int open_flags = flags | BDRV_O_CACHE_WB;
+    int open_flags = flags;
 
     /*
      * Clear flags that are internal to the block layer before opening the
@@ -779,11 +786,6 @@ static void update_flags_from_options(int *flags, QemuOpts *opts)
 {
     *flags &= ~BDRV_O_CACHE_MASK;
 
-    assert(qemu_opt_find(opts, BDRV_OPT_CACHE_WB));
-    if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_WB, false)) {
-        *flags |= BDRV_O_CACHE_WB;
-    }
-
     assert(qemu_opt_find(opts, BDRV_OPT_CACHE_NO_FLUSH));
     if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_NO_FLUSH, false)) {
         *flags |= BDRV_O_NO_FLUSH;
@@ -797,10 +799,6 @@ static void update_flags_from_options(int *flags, QemuOpts *opts)
 
 static void update_options_from_flags(QDict *options, int flags)
 {
-    if (!qdict_haskey(options, BDRV_OPT_CACHE_WB)) {
-        qdict_put(options, BDRV_OPT_CACHE_WB,
-                  qbool_from_bool(flags & BDRV_O_CACHE_WB));
-    }
     if (!qdict_haskey(options, BDRV_OPT_CACHE_DIRECT)) {
         qdict_put(options, BDRV_OPT_CACHE_DIRECT,
                   qbool_from_bool(flags & BDRV_O_NOCACHE));
@@ -862,11 +860,6 @@ static QemuOptsList bdrv_runtime_opts = {
             .type = QEMU_OPT_STRING,
             .help = "Block driver to use for the node",
         },
-        {
-            .name = BDRV_OPT_CACHE_WB,
-            .type = QEMU_OPT_BOOL,
-            .help = "Enable writeback mode",
-        },
         {
             .name = BDRV_OPT_CACHE_DIRECT,
             .type = QEMU_OPT_BOOL,
@@ -973,7 +966,6 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file,
 
     /* Apply cache mode options */
     update_flags_from_options(&bs->open_flags, opts);
-    bdrv_set_enable_write_cache(bs, bs->open_flags & BDRV_O_CACHE_WB);
 
     /* Open the image, either directly or using a protocol */
     open_flags = bdrv_open_flags(bs, bs->open_flags);
@@ -1003,13 +995,6 @@ static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file,
         goto free_and_fail;
     }
 
-    if (bs->encrypted) {
-        error_report("Encrypted images are deprecated");
-        error_printf("Support for them will be removed in a future release.\n"
-                     "You can use 'qemu-img convert' to convert your image"
-                     " to an unencrypted one.\n");
-    }
-
     ret = refresh_total_sectors(bs, bs->total_sectors);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not refresh total sector count");
@@ -1541,6 +1526,13 @@ static int bdrv_open_inherit(BlockDriverState **pbs, const char *filename,
         if (!bs) {
             return -ENODEV;
         }
+
+        if (bs->throttle_state) {
+            error_setg(errp, "Cannot reference an existing block device for "
+                       "which I/O throttling is enabled");
+            return -EINVAL;
+        }
+
         bdrv_ref(bs);
         *pbs = bs;
         return 0;
@@ -2003,17 +1995,6 @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
 
     update_flags_from_options(&reopen_state->flags, opts);
 
-    /* If a guest device is attached, it owns WCE */
-    if (reopen_state->bs->blk && blk_get_attached_dev(reopen_state->bs->blk)) {
-        bool old_wce = bdrv_enable_write_cache(reopen_state->bs);
-        bool new_wce = (reopen_state->flags & BDRV_O_CACHE_WB);
-        if (old_wce != new_wce) {
-            error_setg(errp, "Cannot change cache.writeback: Device attached");
-            ret = -EINVAL;
-            goto error;
-        }
-    }
-
     /* node-name and driver must be unchanged. Put them back into the QDict, so
      * that they are checked at the end of this function. */
     value = qemu_opt_get(opts, "node-name");
@@ -2113,8 +2094,6 @@ void bdrv_reopen_commit(BDRVReopenState *reopen_state)
 
     reopen_state->bs->explicit_options   = reopen_state->explicit_options;
     reopen_state->bs->open_flags         = reopen_state->flags;
-    reopen_state->bs->enable_write_cache = !!(reopen_state->flags &
-                                              BDRV_O_CACHE_WB);
     reopen_state->bs->read_only = !(reopen_state->flags & BDRV_O_RDWR);
 
     bdrv_refresh_limits(reopen_state->bs, NULL);
@@ -2241,29 +2220,11 @@ void bdrv_close_all(void)
     }
 }
 
-/* make a BlockDriverState anonymous by removing from graph_bdrv_state list.
- * Also, NULL terminate the device_name to prevent double remove */
-void bdrv_make_anon(BlockDriverState *bs)
-{
-    if (bs->node_name[0] != '\0') {
-        QTAILQ_REMOVE(&graph_bdrv_states, bs, node_list);
-    }
-    bs->node_name[0] = '\0';
-}
-
 /* Fields that need to stay with the top-level BDS */
 static void bdrv_move_feature_fields(BlockDriverState *bs_dest,
                                      BlockDriverState *bs_src)
 {
     /* move some fields that need to stay attached to the device */
-
-    /* dev info */
-    bs_dest->copy_on_read       = bs_src->copy_on_read;
-
-    bs_dest->enable_write_cache = bs_src->enable_write_cache;
-
-    /* dirty bitmap */
-    bs_dest->dirty_bitmaps      = bs_src->dirty_bitmaps;
 }
 
 static void change_parent_backing_link(BlockDriverState *from,
@@ -2380,8 +2341,9 @@ static void bdrv_delete(BlockDriverState *bs)
     bdrv_close(bs);
 
     /* remove from list, if necessary */
-    bdrv_make_anon(bs);
-
+    if (bs->node_name[0] != '\0') {
+        QTAILQ_REMOVE(&graph_bdrv_states, bs, node_list);
+    }
     QTAILQ_REMOVE(&all_bdrv_states, bs, bs_list);
 
     g_free(bs);
@@ -2740,23 +2702,6 @@ int bdrv_is_sg(BlockDriverState *bs)
     return bs->sg;
 }
 
-int bdrv_enable_write_cache(BlockDriverState *bs)
-{
-    return bs->enable_write_cache;
-}
-
-void bdrv_set_enable_write_cache(BlockDriverState *bs, bool wce)
-{
-    bs->enable_write_cache = wce;
-
-    /* so a reopen() will preserve wce */
-    if (wce) {
-        bs->open_flags |= BDRV_O_CACHE_WB;
-    } else {
-        bs->open_flags &= ~BDRV_O_CACHE_WB;
-    }
-}
-
 int bdrv_is_encrypted(BlockDriverState *bs)
 {
     if (bs->backing && bs->backing->bs->encrypted) {
@@ -2898,7 +2843,7 @@ BlockDeviceInfoList *bdrv_named_nodes_list(Error **errp)
 
     list = NULL;
     QTAILQ_FOREACH(bs, &graph_bdrv_states, node_list) {
-        BlockDeviceInfo *info = bdrv_block_device_info(bs, errp);
+        BlockDeviceInfo *info = bdrv_block_device_info(NULL, bs, errp);
         if (!info) {
             qapi_free_BlockDeviceInfoList(list);
             return NULL;
@@ -3607,8 +3552,8 @@ void bdrv_img_create(const char *filename, const char *fmt,
             }
 
             /* backing files always opened read-only */
-            back_flags =
-                flags & ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
+            back_flags = flags;
+            back_flags &= ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
 
             if (backing_fmt) {
                 backing_options = qdict_new();

block/Makefile.objs

@@ -4,7 +4,7 @@ block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-obj-y += qed-check.o
 block-obj-$(CONFIG_VHDX) += vhdx.o vhdx-endian.o vhdx-log.o
 block-obj-y += quorum.o
-block-obj-y += parallels.o blkdebug.o blkverify.o
+block-obj-y += parallels.o blkdebug.o blkverify.o blkreplay.o
 block-obj-y += block-backend.o snapshot.o qapi.o
 block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
 block-obj-$(CONFIG_POSIX) += raw-posix.o
@@ -23,6 +23,8 @@ block-obj-$(CONFIG_LIBSSH2) += ssh.o
 block-obj-y += accounting.o dirty-bitmap.o
 block-obj-y += write-threshold.o
 
+block-obj-y += crypto.o
+
 common-obj-y += stream.o
 common-obj-y += commit.o
 common-obj-y += backup.o

block/archipelago.c

@@ -51,7 +51,7 @@
  */
 
 #include "qemu/osdep.h"
-#include "qemu-common.h"
+#include "qemu/cutils.h"
 #include "block/block_int.h"
 #include "qemu/error-report.h"
 #include "qemu/thread.h"

block/backup.c

@@ -17,8 +17,10 @@
 #include "block/block.h"
 #include "block/block_int.h"
 #include "block/blockjob.h"
+#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
+#include "qemu/cutils.h"
 #include "sysemu/block-backend.h"
 #include "qemu/bitmap.h"
 
@@ -402,7 +404,6 @@ static void coroutine_fn backup_run(void *opaque)
 
     job->done_bitmap = bitmap_new(end);
 
-    bdrv_set_enable_write_cache(target, true);
     if (target->blk) {
         blk_set_on_error(target->blk, on_target_error, on_target_error);
         blk_iostatus_enable(target->blk);
@@ -503,6 +504,7 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target,
 {
     int64_t len;
     BlockDriverInfo bdi;
+    BackupBlockJob *job = NULL;
     int ret;
 
     assert(bs);
@@ -567,8 +569,7 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target,
         goto error;
     }
 
-    BackupBlockJob *job = block_job_create(&backup_job_driver, bs, speed,
-                                           cb, opaque, errp);
+    job = block_job_create(&backup_job_driver, bs, speed, cb, opaque, errp);
     if (!job) {
         goto error;
     }
@@ -609,4 +610,7 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target,
     if (sync_bitmap) {
         bdrv_reclaim_dirty_bitmap(bs, sync_bitmap, NULL);
     }
+    if (job) {
+        block_job_unref(&job->common);
+    }
 }

block/blkdebug.c

@@ -23,7 +23,8 @@
  */
 
 #include "qemu/osdep.h"
-#include "qemu-common.h"
+#include "qapi/error.h"
+#include "qemu/cutils.h"
 #include "qemu/config-file.h"
 #include "block/block_int.h"
 #include "qemu/module.h"

block/blkreplay.c

@@ -0,0 +1,160 @@
+/*
+ * Block protocol for record/replay
+ *
+ * Copyright (c) 2010-2016 Institute for System Programming
+ *                         of the Russian Academy of Sciences.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu-common.h"
+#include "block/block_int.h"
+#include "sysemu/replay.h"
+#include "qapi/error.h"
+
+typedef struct Request {
+    Coroutine *co;
+    QEMUBH *bh;
+} Request;
+
+/* Next request id.
+   This counter is global, because requests from different
+   block devices should not get overlapping ids. */
+static uint64_t request_id;
+
+static int blkreplay_open(BlockDriverState *bs, QDict *options, int flags,
+                          Error **errp)
+{
+    Error *local_err = NULL;
+    int ret;
+
+    /* Open the image file */
+    bs->file = bdrv_open_child(NULL, options, "image",
+                               bs, &child_file, false, &local_err);
+    if (local_err) {
+        ret = -EINVAL;
+        error_propagate(errp, local_err);
+        goto fail;
+    }
+
+    ret = 0;
+fail:
+    if (ret < 0) {
+        bdrv_unref_child(bs, bs->file);
+    }
+    return ret;
+}
+
+static void blkreplay_close(BlockDriverState *bs)
+{
+}
+
+static int64_t blkreplay_getlength(BlockDriverState *bs)
+{
+    return bdrv_getlength(bs->file->bs);
+}
+
+/* This bh is used for synchronization of return from coroutines.
+   It continues yielded coroutine which then finishes its execution.
+   BH is called adjusted to some replay checkpoint, therefore
+   record and replay will always finish coroutines deterministically.
+*/
+static void blkreplay_bh_cb(void *opaque)
+{
+    Request *req = opaque;
+    qemu_coroutine_enter(req->co, NULL);
+    qemu_bh_delete(req->bh);
+    g_free(req);
+}
+
+static void block_request_create(uint64_t reqid, BlockDriverState *bs,
+                                 Coroutine *co)
+{
+    Request *req = g_new(Request, 1);
+    *req = (Request) {
+        .co = co,
+        .bh = aio_bh_new(bdrv_get_aio_context(bs), blkreplay_bh_cb, req),
+    };
+    replay_block_event(req->bh, reqid);
+}
+
+static int coroutine_fn blkreplay_co_readv(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+{
+    uint64_t reqid = request_id++;
+    int ret = bdrv_co_readv(bs->file->bs, sector_num, nb_sectors, qiov);
+    block_request_create(reqid, bs, qemu_coroutine_self());
+    qemu_coroutine_yield();
+
+    return ret;
+}
+
+static int coroutine_fn blkreplay_co_writev(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
+{
+    uint64_t reqid = request_id++;
+    int ret = bdrv_co_writev(bs->file->bs, sector_num, nb_sectors, qiov);
+    block_request_create(reqid, bs, qemu_coroutine_self());
+    qemu_coroutine_yield();
+
+    return ret;
+}
+
+static int coroutine_fn blkreplay_co_write_zeroes(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors, BdrvRequestFlags flags)
+{
+    uint64_t reqid = request_id++;
+    int ret = bdrv_co_write_zeroes(bs->file->bs, sector_num, nb_sectors, flags);
+    block_request_create(reqid, bs, qemu_coroutine_self());
+    qemu_coroutine_yield();
+
+    return ret;
+}
+
+static int coroutine_fn blkreplay_co_discard(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors)
+{
+    uint64_t reqid = request_id++;
+    int ret = bdrv_co_discard(bs->file->bs, sector_num, nb_sectors);
+    block_request_create(reqid, bs, qemu_coroutine_self());
+    qemu_coroutine_yield();
+
+    return ret;
+}
+
+static int coroutine_fn blkreplay_co_flush(BlockDriverState *bs)
+{
+    uint64_t reqid = request_id++;
+    int ret = bdrv_co_flush(bs->file->bs);
+    block_request_create(reqid, bs, qemu_coroutine_self());
+    qemu_coroutine_yield();
+
+    return ret;
+}
+
+static BlockDriver bdrv_blkreplay = {
+    .format_name            = "blkreplay",
+    .protocol_name          = "blkreplay",
+    .instance_size          = 0,
+
+    .bdrv_file_open         = blkreplay_open,
+    .bdrv_close             = blkreplay_close,
+    .bdrv_getlength         = blkreplay_getlength,
+
+    .bdrv_co_readv          = blkreplay_co_readv,
+    .bdrv_co_writev         = blkreplay_co_writev,
+
+    .bdrv_co_write_zeroes   = blkreplay_co_write_zeroes,
+    .bdrv_co_discard        = blkreplay_co_discard,
+    .bdrv_co_flush          = blkreplay_co_flush,
+};
+
+static void bdrv_blkreplay_init(void)
+{
+    bdrv_register(&bdrv_blkreplay);
+}
+
+block_init(bdrv_blkreplay_init);

block/blkverify.c

@@ -8,10 +8,12 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu/sockets.h" /* for EINPROGRESS on Windows */
 #include "block/block_int.h"
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qstring.h"
+#include "qemu/cutils.h"
 
 typedef struct {
     BdrvChild *test_file;

block/block-backend.c

@@ -18,6 +18,7 @@
 #include "sysemu/blockdev.h"
 #include "sysemu/sysemu.h"
 #include "qapi-event.h"
+#include "qemu/id.h"
 
 /* Number of coroutines to reserve per attached device model */
 #define COROUTINE_POOL_RESERVATION 64
@@ -46,6 +47,8 @@ struct BlockBackend {
      * can be used to restore those options in the new BDS on insert) */
     BlockBackendRootState root_state;
 
+    bool enable_write_cache;
+
     /* I/O stats (display with "info blockstats"). */
     BlockAcctStats stats;
 
@@ -159,6 +162,8 @@ BlockBackend *blk_new_open(const char *filename, const char *reference,
         return NULL;
     }
 
+    blk_set_enable_write_cache(blk, true);
+
     return blk;
 }
 
@@ -370,23 +375,6 @@ BlockDriverState *blk_bs(BlockBackend *blk)
     return blk->root ? blk->root->bs : NULL;
 }
 
-/*
- * Changes the BlockDriverState attached to @blk
- */
-void blk_set_bs(BlockBackend *blk, BlockDriverState *bs)
-{
-    bdrv_ref(bs);
-
-    if (blk->root) {
-        blk->root->bs->blk = NULL;
-        bdrv_root_unref_child(blk->root);
-    }
-    assert(bs->blk == NULL);
-
-    blk->root = bdrv_root_attach_child(bs, "root", &child_root);
-    bs->blk = blk;
-}
-
 /*
  * Return @blk's DriveInfo if any, else null.
  */
@@ -711,11 +699,17 @@ static int coroutine_fn blk_co_pwritev(BlockBackend *blk, int64_t offset,
                                       unsigned int bytes, QEMUIOVector *qiov,
                                       BdrvRequestFlags flags)
 {
-    int ret = blk_check_byte_request(blk, offset, bytes);
+    int ret;
+
+    ret = blk_check_byte_request(blk, offset, bytes);
     if (ret < 0) {
         return ret;
     }
 
+    if (!blk->enable_write_cache) {
+        flags |= BDRV_REQ_FUA;
+    }
+
     return bdrv_co_do_pwritev(blk_bs(blk), offset, bytes, qiov, flags);
 }
 
@@ -826,7 +820,7 @@ int blk_write_zeroes(BlockBackend *blk, int64_t sector_num,
                      int nb_sectors, BdrvRequestFlags flags)
 {
     return blk_rw(blk, sector_num, NULL, nb_sectors, blk_write_entry,
-                  BDRV_REQ_ZERO_WRITE);
+                  flags | BDRV_REQ_ZERO_WRITE);
 }
 
 static void error_callback_bh(void *opaque)
@@ -858,6 +852,7 @@ BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
 typedef struct BlkAioEmAIOCB {
     BlockAIOCB common;
     BlkRwCo rwco;
+    int bytes;
     bool has_returned;
     QEMUBH* bh;
 } BlkAioEmAIOCB;
@@ -883,7 +878,7 @@ static void blk_aio_complete_bh(void *opaque)
     blk_aio_complete(opaque);
 }
 
-static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset,
+static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset, int bytes,
                                 QEMUIOVector *qiov, CoroutineEntry co_entry,
                                 BdrvRequestFlags flags,
                                 BlockCompletionFunc *cb, void *opaque)
@@ -899,6 +894,7 @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset,
         .flags  = flags,
         .ret    = NOT_DONE,
     };
+    acb->bytes = bytes;
     acb->bh = NULL;
     acb->has_returned = false;
 
@@ -919,7 +915,8 @@ static void blk_aio_read_entry(void *opaque)
     BlkAioEmAIOCB *acb = opaque;
     BlkRwCo *rwco = &acb->rwco;
 
-    rwco->ret = blk_co_preadv(rwco->blk, rwco->offset, rwco->qiov->size,
+    assert(rwco->qiov->size == acb->bytes);
+    rwco->ret = blk_co_preadv(rwco->blk, rwco->offset, acb->bytes,
                               rwco->qiov, rwco->flags);
     blk_aio_complete(acb);
 }
@@ -929,8 +926,8 @@ static void blk_aio_write_entry(void *opaque)
     BlkAioEmAIOCB *acb = opaque;
     BlkRwCo *rwco = &acb->rwco;
 
-    rwco->ret = blk_co_pwritev(rwco->blk, rwco->offset,
-                               rwco->qiov ? rwco->qiov->size : 0,
+    assert(!rwco->qiov || rwco->qiov->size == acb->bytes);
+    rwco->ret = blk_co_pwritev(rwco->blk, rwco->offset, acb->bytes,
                                rwco->qiov, rwco->flags);
     blk_aio_complete(acb);
 }
@@ -943,8 +940,10 @@ BlockAIOCB *blk_aio_write_zeroes(BlockBackend *blk, int64_t sector_num,
         return blk_abort_aio_request(blk, cb, opaque, -EINVAL);
     }
 
-    return blk_aio_prwv(blk, sector_num << BDRV_SECTOR_BITS, NULL,
-                        blk_aio_write_entry, BDRV_REQ_ZERO_WRITE, cb, opaque);
+    return blk_aio_prwv(blk, sector_num << BDRV_SECTOR_BITS,
+                        nb_sectors << BDRV_SECTOR_BITS, NULL,
+                        blk_aio_write_entry, flags | BDRV_REQ_ZERO_WRITE,
+                        cb, opaque);
 }
 
 int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int count)
@@ -1000,7 +999,8 @@ BlockAIOCB *blk_aio_readv(BlockBackend *blk, int64_t sector_num,
         return blk_abort_aio_request(blk, cb, opaque, -EINVAL);
     }
 
-    return blk_aio_prwv(blk, sector_num << BDRV_SECTOR_BITS, iov,
+    assert(nb_sectors << BDRV_SECTOR_BITS == iov->size);
+    return blk_aio_prwv(blk, sector_num << BDRV_SECTOR_BITS, iov->size, iov,
                         blk_aio_read_entry, 0, cb, opaque);
 }
 
@@ -1012,7 +1012,8 @@ BlockAIOCB *blk_aio_writev(BlockBackend *blk, int64_t sector_num,
         return blk_abort_aio_request(blk, cb, opaque, -EINVAL);
     }
 
-    return blk_aio_prwv(blk, sector_num << BDRV_SECTOR_BITS, iov,
+    assert(nb_sectors << BDRV_SECTOR_BITS == iov->size);
+    return blk_aio_prwv(blk, sector_num << BDRV_SECTOR_BITS, iov->size, iov,
                         blk_aio_write_entry, 0, cb, opaque);
 }
 
@@ -1222,28 +1223,12 @@ int blk_is_sg(BlockBackend *blk)
 
 int blk_enable_write_cache(BlockBackend *blk)
 {
-    BlockDriverState *bs = blk_bs(blk);
-
-    if (bs) {
-        return bdrv_enable_write_cache(bs);
-    } else {
-        return !!(blk->root_state.open_flags & BDRV_O_CACHE_WB);
-    }
+    return blk->enable_write_cache;
 }
 
 void blk_set_enable_write_cache(BlockBackend *blk, bool wce)
 {
-    BlockDriverState *bs = blk_bs(blk);
-
-    if (bs) {
-        bdrv_set_enable_write_cache(bs, wce);
-    } else {
-        if (wce) {
-            blk->root_state.open_flags |= BDRV_O_CACHE_WB;
-        } else {
-            blk->root_state.open_flags &= ~BDRV_O_CACHE_WB;
-        }
-    }
+    blk->enable_write_cache = wce;
 }
 
 void blk_invalidate_cache(BlockBackend *blk, Error **errp)
@@ -1468,7 +1453,7 @@ int coroutine_fn blk_co_write_zeroes(BlockBackend *blk, int64_t sector_num,
 
     return blk_co_pwritev(blk, sector_num << BDRV_SECTOR_BITS,
                           nb_sectors << BDRV_SECTOR_BITS, NULL,
-                          BDRV_REQ_ZERO_WRITE);
+                          flags | BDRV_REQ_ZERO_WRITE);
 }
 
 int blk_write_compressed(BlockBackend *blk, int64_t sector_num,
@@ -1504,11 +1489,22 @@ int blk_discard(BlockBackend *blk, int64_t sector_num, int nb_sectors)
 int blk_save_vmstate(BlockBackend *blk, const uint8_t *buf,
                      int64_t pos, int size)
 {
+    int ret;
+
     if (!blk_is_available(blk)) {
         return -ENOMEDIUM;
     }
 
-    return bdrv_save_vmstate(blk_bs(blk), buf, pos, size);
+    ret = bdrv_save_vmstate(blk_bs(blk), buf, pos, size);
+    if (ret < 0) {
+        return ret;
+    }
+
+    if (ret == size && !blk->enable_write_cache) {
+        ret = bdrv_flush(blk_bs(blk));
+    }
+
+    return ret < 0 ? ret : size;
 }
 
 int blk_load_vmstate(BlockBackend *blk, uint8_t *buf, int64_t pos, int size)

block/bochs.c

@@ -23,6 +23,7 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "qemu/module.h"

block/cloop.c

@@ -22,6 +22,7 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "qemu/module.h"

block/commit.c

@@ -16,6 +16,7 @@
 #include "trace.h"
 #include "block/block_int.h"
 #include "block/blockjob.h"
+#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
 #include "sysemu/block-backend.h"

block/crypto.c

@@ -0,0 +1,586 @@
+/*
+ * QEMU block full disk encryption
+ *
+ * Copyright (c) 2015-2016 Red Hat, Inc.
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#include "qemu/osdep.h"
+
+#include "block/block_int.h"
+#include "sysemu/block-backend.h"
+#include "crypto/block.h"
+#include "qapi/opts-visitor.h"
+#include "qapi-visit.h"
+#include "qapi/error.h"
+
+#define BLOCK_CRYPTO_OPT_LUKS_KEY_SECRET "key-secret"
+#define BLOCK_CRYPTO_OPT_LUKS_CIPHER_ALG "cipher-alg"
+#define BLOCK_CRYPTO_OPT_LUKS_CIPHER_MODE "cipher-mode"
+#define BLOCK_CRYPTO_OPT_LUKS_IVGEN_ALG "ivgen-alg"
+#define BLOCK_CRYPTO_OPT_LUKS_IVGEN_HASH_ALG "ivgen-hash-alg"
+#define BLOCK_CRYPTO_OPT_LUKS_HASH_ALG "hash-alg"
+
+typedef struct BlockCrypto BlockCrypto;
+
+struct BlockCrypto {
+    QCryptoBlock *block;
+};
+
+
+static int block_crypto_probe_generic(QCryptoBlockFormat format,
+                                      const uint8_t *buf,
+                                      int buf_size,
+                                      const char *filename)
+{
+    if (qcrypto_block_has_format(format, buf, buf_size)) {
+        return 100;
+    } else {
+        return 0;
+    }
+}
+
+
+static ssize_t block_crypto_read_func(QCryptoBlock *block,
+                                      size_t offset,
+                                      uint8_t *buf,
+                                      size_t buflen,
+                                      Error **errp,
+                                      void *opaque)
+{
+    BlockDriverState *bs = opaque;
+    ssize_t ret;
+
+    ret = bdrv_pread(bs->file->bs, offset, buf, buflen);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Could not read encryption header");
+        return ret;
+    }
+    return ret;
+}
+
+
+struct BlockCryptoCreateData {
+    const char *filename;
+    QemuOpts *opts;
+    BlockBackend *blk;
+    uint64_t size;
+};
+
+
+static ssize_t block_crypto_write_func(QCryptoBlock *block,
+                                       size_t offset,
+                                       const uint8_t *buf,
+                                       size_t buflen,
+                                       Error **errp,
+                                       void *opaque)
+{
+    struct BlockCryptoCreateData *data = opaque;
+    ssize_t ret;
+
+    ret = blk_pwrite(data->blk, offset, buf, buflen);
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Could not write encryption header");
+        return ret;
+    }
+    return ret;
+}
+
+
+static ssize_t block_crypto_init_func(QCryptoBlock *block,
+                                      size_t headerlen,
+                                      Error **errp,
+                                      void *opaque)
+{
+    struct BlockCryptoCreateData *data = opaque;
+    int ret;
+
+    /* User provided size should reflect amount of space made
+     * available to the guest, so we must take account of that
+     * which will be used by the crypto header
+     */
+    data->size += headerlen;
+
+    qemu_opt_set_number(data->opts, BLOCK_OPT_SIZE, data->size, &error_abort);
+    ret = bdrv_create_file(data->filename, data->opts, errp);
+    if (ret < 0) {
+        return -1;
+    }
+
+    data->blk = blk_new_open(data->filename, NULL, NULL,
+                             BDRV_O_RDWR | BDRV_O_PROTOCOL, errp);
+    if (!data->blk) {
+        return -1;
+    }
+
+    return 0;
+}
+
+
+static QemuOptsList block_crypto_runtime_opts_luks = {
+    .name = "crypto",
+    .head = QTAILQ_HEAD_INITIALIZER(block_crypto_runtime_opts_luks.head),
+    .desc = {
+        {
+            .name = BLOCK_CRYPTO_OPT_LUKS_KEY_SECRET,
+            .type = QEMU_OPT_STRING,
+            .help = "ID of the secret that provides the encryption key",
+        },
+        { /* end of list */ }
+    },
+};
+
+
+static QemuOptsList block_crypto_create_opts_luks = {
+    .name = "crypto",
+    .head = QTAILQ_HEAD_INITIALIZER(block_crypto_create_opts_luks.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        {
+            .name = BLOCK_CRYPTO_OPT_LUKS_KEY_SECRET,
+            .type = QEMU_OPT_STRING,
+            .help = "ID of the secret that provides the encryption key",
+        },
+        {
+            .name = BLOCK_CRYPTO_OPT_LUKS_CIPHER_ALG,
+            .type = QEMU_OPT_STRING,
+            .help = "Name of encryption cipher algorithm",
+        },
+        {
+            .name = BLOCK_CRYPTO_OPT_LUKS_CIPHER_MODE,
+            .type = QEMU_OPT_STRING,
+            .help = "Name of encryption cipher mode",
+        },
+        {
+            .name = BLOCK_CRYPTO_OPT_LUKS_IVGEN_ALG,
+            .type = QEMU_OPT_STRING,
+            .help = "Name of IV generator algorithm",
+        },
+        {
+            .name = BLOCK_CRYPTO_OPT_LUKS_IVGEN_HASH_ALG,
+            .type = QEMU_OPT_STRING,
+            .help = "Name of IV generator hash algorithm",
+        },
+        {
+            .name = BLOCK_CRYPTO_OPT_LUKS_HASH_ALG,
+            .type = QEMU_OPT_STRING,
+            .help = "Name of encryption hash algorithm",
+        },
+        { /* end of list */ }
+    },
+};
+
+
+static QCryptoBlockOpenOptions *
+block_crypto_open_opts_init(QCryptoBlockFormat format,
+                            QemuOpts *opts,
+                            Error **errp)
+{
+    OptsVisitor *ov;
+    QCryptoBlockOpenOptions *ret = NULL;
+    Error *local_err = NULL;
+    Error *end_err = NULL;
+
+    ret = g_new0(QCryptoBlockOpenOptions, 1);
+    ret->format = format;
+
+    ov = opts_visitor_new(opts);
+
+    visit_start_struct(opts_get_visitor(ov),
+                       NULL, NULL, 0, &local_err);
+    if (local_err) {
+        goto out;
+    }
+
+    switch (format) {
+    case Q_CRYPTO_BLOCK_FORMAT_LUKS:
+        visit_type_QCryptoBlockOptionsLUKS_members(
+            opts_get_visitor(ov), &ret->u.luks, &local_err);
+        break;
+
+    default:
+        error_setg(&local_err, "Unsupported block format %d", format);
+        break;
+    }
+
+    visit_end_struct(opts_get_visitor(ov), &end_err);
+    error_propagate(&local_err, end_err);
+
+ out:
+    if (local_err) {
+        error_propagate(errp, local_err);
+        qapi_free_QCryptoBlockOpenOptions(ret);
+        ret = NULL;
+    }
+    opts_visitor_cleanup(ov);
+    return ret;
+}
+
+
+static QCryptoBlockCreateOptions *
+block_crypto_create_opts_init(QCryptoBlockFormat format,
+                              QemuOpts *opts,
+                              Error **errp)
+{
+    OptsVisitor *ov;
+    QCryptoBlockCreateOptions *ret = NULL;
+    Error *local_err = NULL;
+    Error *end_err = NULL;
+
+    ret = g_new0(QCryptoBlockCreateOptions, 1);
+    ret->format = format;
+
+    ov = opts_visitor_new(opts);
+
+    visit_start_struct(opts_get_visitor(ov),
+                       NULL, NULL, 0, &local_err);
+    if (local_err) {
+        goto out;
+    }
+
+    switch (format) {
+    case Q_CRYPTO_BLOCK_FORMAT_LUKS:
+        visit_type_QCryptoBlockCreateOptionsLUKS_members(
+            opts_get_visitor(ov), &ret->u.luks, &local_err);
+        break;
+
+    default:
+        error_setg(&local_err, "Unsupported block format %d", format);
+        break;
+    }
+
+    visit_end_struct(opts_get_visitor(ov), &end_err);
+    error_propagate(&local_err, end_err);
+
+ out:
+    if (local_err) {
+        error_propagate(errp, local_err);
+        qapi_free_QCryptoBlockCreateOptions(ret);
+        ret = NULL;
+    }
+    opts_visitor_cleanup(ov);
+    return ret;
+}
+
+
+static int block_crypto_open_generic(QCryptoBlockFormat format,
+                                     QemuOptsList *opts_spec,
+                                     BlockDriverState *bs,
+                                     QDict *options,
+                                     int flags,
+                                     Error **errp)
+{
+    BlockCrypto *crypto = bs->opaque;
+    QemuOpts *opts = NULL;
+    Error *local_err = NULL;
+    int ret = -EINVAL;
+    QCryptoBlockOpenOptions *open_opts = NULL;
+    unsigned int cflags = 0;
+
+    opts = qemu_opts_create(opts_spec, NULL, 0, &error_abort);
+    qemu_opts_absorb_qdict(opts, options, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        goto cleanup;
+    }
+
+    open_opts = block_crypto_open_opts_init(format, opts, errp);
+    if (!open_opts) {
+        goto cleanup;
+    }
+
+    if (flags & BDRV_O_NO_IO) {
+        cflags |= QCRYPTO_BLOCK_OPEN_NO_IO;
+    }
+    crypto->block = qcrypto_block_open(open_opts,
+                                       block_crypto_read_func,
+                                       bs,
+                                       cflags,
+                                       errp);
+
+    if (!crypto->block) {
+        ret = -EIO;
+        goto cleanup;
+    }
+
+    bs->encrypted = 1;
+    bs->valid_key = 1;
+
+    ret = 0;
+ cleanup:
+    qapi_free_QCryptoBlockOpenOptions(open_opts);
+    return ret;
+}
+
+
+static int block_crypto_create_generic(QCryptoBlockFormat format,
+                                       const char *filename,
+                                       QemuOpts *opts,
+                                       Error **errp)
+{
+    int ret = -EINVAL;
+    QCryptoBlockCreateOptions *create_opts = NULL;
+    QCryptoBlock *crypto = NULL;
+    struct BlockCryptoCreateData data = {
+        .size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
+                         BDRV_SECTOR_SIZE),
+        .opts = opts,
+        .filename = filename,
+    };
+
+    create_opts = block_crypto_create_opts_init(format, opts, errp);
+    if (!create_opts) {
+        return -1;
+    }
+
+    crypto = qcrypto_block_create(create_opts,
+                                  block_crypto_init_func,
+                                  block_crypto_write_func,
+                                  &data,
+                                  errp);
+
+    if (!crypto) {
+        ret = -EIO;
+        goto cleanup;
+    }
+
+    ret = 0;
+ cleanup:
+    qcrypto_block_free(crypto);
+    blk_unref(data.blk);
+    qapi_free_QCryptoBlockCreateOptions(create_opts);
+    return ret;
+}
+
+static int block_crypto_truncate(BlockDriverState *bs, int64_t offset)
+{
+    BlockCrypto *crypto = bs->opaque;
+    size_t payload_offset =
+        qcrypto_block_get_payload_offset(crypto->block);
+
+    offset += payload_offset;
+
+    return bdrv_truncate(bs->file->bs, offset);
+}
+
+static void block_crypto_close(BlockDriverState *bs)
+{
+    BlockCrypto *crypto = bs->opaque;
+    qcrypto_block_free(crypto->block);
+}
+
+
+#define BLOCK_CRYPTO_MAX_SECTORS 32
+
+static coroutine_fn int
+block_crypto_co_readv(BlockDriverState *bs, int64_t sector_num,
+                      int remaining_sectors, QEMUIOVector *qiov)
+{
+    BlockCrypto *crypto = bs->opaque;
+    int cur_nr_sectors; /* number of sectors in current iteration */
+    uint64_t bytes_done = 0;
+    uint8_t *cipher_data = NULL;
+    QEMUIOVector hd_qiov;
+    int ret = 0;
+    size_t payload_offset =
+        qcrypto_block_get_payload_offset(crypto->block) / 512;
+
+    qemu_iovec_init(&hd_qiov, qiov->niov);
+
+    /* Bounce buffer so we have a linear mem region for
+     * entire sector. XXX optimize so we avoid bounce
+     * buffer in case that qiov->niov == 1
+     */
+    cipher_data =
+        qemu_try_blockalign(bs->file->bs, MIN(BLOCK_CRYPTO_MAX_SECTORS * 512,
+                                              qiov->size));
+    if (cipher_data == NULL) {
+        ret = -ENOMEM;
+        goto cleanup;
+    }
+
+    while (remaining_sectors) {
+        cur_nr_sectors = remaining_sectors;
+
+        if (cur_nr_sectors > BLOCK_CRYPTO_MAX_SECTORS) {
+            cur_nr_sectors = BLOCK_CRYPTO_MAX_SECTORS;
+        }
+
+        qemu_iovec_reset(&hd_qiov);
+        qemu_iovec_add(&hd_qiov, cipher_data, cur_nr_sectors * 512);
+
+        ret = bdrv_co_readv(bs->file->bs,
+                            payload_offset + sector_num,
+                            cur_nr_sectors, &hd_qiov);
+        if (ret < 0) {
+            goto cleanup;
+        }
+
+        if (qcrypto_block_decrypt(crypto->block,
+                                  sector_num,
+                                  cipher_data, cur_nr_sectors * 512,
+                                  NULL) < 0) {
+            ret = -EIO;
+            goto cleanup;
+        }
+
+        qemu_iovec_from_buf(qiov, bytes_done,
+                            cipher_data, cur_nr_sectors * 512);
+
+        remaining_sectors -= cur_nr_sectors;
+        sector_num += cur_nr_sectors;
+        bytes_done += cur_nr_sectors * 512;
+    }
+
+ cleanup:
+    qemu_iovec_destroy(&hd_qiov);
+    qemu_vfree(cipher_data);
+
+    return ret;
+}
+
+
+static coroutine_fn int
+block_crypto_co_writev(BlockDriverState *bs, int64_t sector_num,
+                       int remaining_sectors, QEMUIOVector *qiov)
+{
+    BlockCrypto *crypto = bs->opaque;
+    int cur_nr_sectors; /* number of sectors in current iteration */
+    uint64_t bytes_done = 0;
+    uint8_t *cipher_data = NULL;
+    QEMUIOVector hd_qiov;
+    int ret = 0;
+    size_t payload_offset =
+        qcrypto_block_get_payload_offset(crypto->block) / 512;
+
+    qemu_iovec_init(&hd_qiov, qiov->niov);
+
+    /* Bounce buffer so we have a linear mem region for
+     * entire sector. XXX optimize so we avoid bounce
+     * buffer in case that qiov->niov == 1
+     */
+    cipher_data =
+        qemu_try_blockalign(bs->file->bs, MIN(BLOCK_CRYPTO_MAX_SECTORS * 512,
+                                              qiov->size));
+    if (cipher_data == NULL) {
+        ret = -ENOMEM;
+        goto cleanup;
+    }
+
+    while (remaining_sectors) {
+        cur_nr_sectors = remaining_sectors;
+
+        if (cur_nr_sectors > BLOCK_CRYPTO_MAX_SECTORS) {
+            cur_nr_sectors = BLOCK_CRYPTO_MAX_SECTORS;
+        }
+
+        qemu_iovec_to_buf(qiov, bytes_done,
+                          cipher_data, cur_nr_sectors * 512);
+
+        if (qcrypto_block_encrypt(crypto->block,
+                                  sector_num,
+                                  cipher_data, cur_nr_sectors * 512,
+                                  NULL) < 0) {
+            ret = -EIO;
+            goto cleanup;
+        }
+
+        qemu_iovec_reset(&hd_qiov);
+        qemu_iovec_add(&hd_qiov, cipher_data, cur_nr_sectors * 512);
+
+        ret = bdrv_co_writev(bs->file->bs,
+                             payload_offset + sector_num,
+                             cur_nr_sectors, &hd_qiov);
+        if (ret < 0) {
+            goto cleanup;
+        }
+
+        remaining_sectors -= cur_nr_sectors;
+        sector_num += cur_nr_sectors;
+        bytes_done += cur_nr_sectors * 512;
+    }
+
+ cleanup:
+    qemu_iovec_destroy(&hd_qiov);
+    qemu_vfree(cipher_data);
+
+    return ret;
+}
+
+
+static int64_t block_crypto_getlength(BlockDriverState *bs)
+{
+    BlockCrypto *crypto = bs->opaque;
+    int64_t len = bdrv_getlength(bs->file->bs);
+
+    ssize_t offset = qcrypto_block_get_payload_offset(crypto->block);
+
+    len -= offset;
+
+    return len;
+}
+
+
+static int block_crypto_probe_luks(const uint8_t *buf,
+                                   int buf_size,
+                                   const char *filename) {
+    return block_crypto_probe_generic(Q_CRYPTO_BLOCK_FORMAT_LUKS,
+                                      buf, buf_size, filename);
+}
+
+static int block_crypto_open_luks(BlockDriverState *bs,
+                                  QDict *options,
+                                  int flags,
+                                  Error **errp)
+{
+    return block_crypto_open_generic(Q_CRYPTO_BLOCK_FORMAT_LUKS,
+                                     &block_crypto_runtime_opts_luks,
+                                     bs, options, flags, errp);
+}
+
+static int block_crypto_create_luks(const char *filename,
+                                    QemuOpts *opts,
+                                    Error **errp)
+{
+    return block_crypto_create_generic(Q_CRYPTO_BLOCK_FORMAT_LUKS,
+                                       filename, opts, errp);
+}
+
+BlockDriver bdrv_crypto_luks = {
+    .format_name        = "luks",
+    .instance_size      = sizeof(BlockCrypto),
+    .bdrv_probe         = block_crypto_probe_luks,
+    .bdrv_open          = block_crypto_open_luks,
+    .bdrv_close         = block_crypto_close,
+    .bdrv_create        = block_crypto_create_luks,
+    .bdrv_truncate      = block_crypto_truncate,
+    .create_opts        = &block_crypto_create_opts_luks,
+
+    .bdrv_co_readv      = block_crypto_co_readv,
+    .bdrv_co_writev     = block_crypto_co_writev,
+    .bdrv_getlength     = block_crypto_getlength,
+};
+
+static void block_crypto_init(void)
+{
+    bdrv_register(&bdrv_crypto_luks);
+}
+
+block_init(block_crypto_init);

block/curl.c

@@ -22,6 +22,7 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "qemu/error-report.h"
 #include "block/block_int.h"
@@ -29,6 +30,7 @@
 #include "qapi/qmp/qstring.h"
 #include "crypto/secret.h"
 #include <curl/curl.h>
+#include "qemu/cutils.h"
 
 // #define DEBUG_CURL
 // #define DEBUG_VERBOSE

block/dirty-bitmap.c

@@ -22,7 +22,7 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
-#include "config-host.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "trace.h"
 #include "block/block_int.h"

block/dmg.c

@@ -22,6 +22,7 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "qemu/bswap.h"

block/gluster.c

@@ -10,6 +10,7 @@
 #include "qemu/osdep.h"
 #include <glusterfs/api/glfs.h>
 #include "block/block_int.h"
+#include "qapi/error.h"
 #include "qemu/uri.h"
 
 typedef struct GlusterAIOCB {
@@ -246,7 +247,7 @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
     if (!ret || ret == acb->size) {
         acb->ret = 0; /* Success */
     } else if (ret < 0) {
-        acb->ret = ret; /* Read/Write failed */
+        acb->ret = -errno; /* Read/Write failed */
     } else {
         acb->ret = -EIO; /* Partial read/write - fail it */
     }
@@ -313,6 +314,23 @@ static int qemu_gluster_open(BlockDriverState *bs,  QDict *options,
         goto out;
     }
 
+#ifdef CONFIG_GLUSTERFS_XLATOR_OPT
+    /* Without this, if fsync fails for a recoverable reason (for instance,
+     * ENOSPC), gluster will dump its cache, preventing retries.  This means
+     * almost certain data loss.  Not all gluster versions support the
+     * 'resync-failed-syncs-after-fsync' key value, but there is no way to
+     * discover during runtime if it is supported (this api returns success for
+     * unknown key/value pairs) */
+    ret = glfs_set_xlator_option(s->glfs, "*-write-behind",
+                                          "resync-failed-syncs-after-fsync",
+                                          "on");
+    if (ret < 0) {
+        error_setg_errno(errp, errno, "Unable to set xlator key/value pair");
+        ret = -errno;
+        goto out;
+    }
+#endif
+
     qemu_gluster_parse_flags(bdrv_flags, &open_flags);
 
     s->fd = glfs_open(s->glfs, gconf->image, open_flags);
@@ -365,6 +383,16 @@ static int qemu_gluster_reopen_prepare(BDRVReopenState *state,
         goto exit;
     }
 
+#ifdef CONFIG_GLUSTERFS_XLATOR_OPT
+    ret = glfs_set_xlator_option(reop_s->glfs, "*-write-behind",
+                                 "resync-failed-syncs-after-fsync", "on");
+    if (ret < 0) {
+        error_setg_errno(errp, errno, "Unable to set xlator key/value pair");
+        ret = -errno;
+        goto exit;
+    }
+#endif
+
     reop_s->fd = glfs_open(reop_s->glfs, gconf->image, open_flags);
     if (reop_s->fd == NULL) {
         /* reops->glfs will be cleaned up in _abort */
@@ -588,6 +616,17 @@ static coroutine_fn int qemu_gluster_co_writev(BlockDriverState *bs,
     return qemu_gluster_co_rw(bs, sector_num, nb_sectors, qiov, 1);
 }
 
+static void qemu_gluster_close(BlockDriverState *bs)
+{
+    BDRVGlusterState *s = bs->opaque;
+
+    if (s->fd) {
+        glfs_close(s->fd);
+        s->fd = NULL;
+    }
+    glfs_fini(s->glfs);
+}
+
 static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
 {
     int ret;
@@ -601,11 +640,35 @@ static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
 
     ret = glfs_fsync_async(s->fd, gluster_finish_aiocb, &acb);
     if (ret < 0) {
-        return -errno;
+        ret = -errno;
+        goto error;
     }
 
     qemu_coroutine_yield();
+    if (acb.ret < 0) {
+        ret = acb.ret;
+        goto error;
+    }
+
     return acb.ret;
+
+error:
+    /* Some versions of Gluster (3.5.6 -> 3.5.8?) will not retain its cache
+     * after a fsync failure, so we have no way of allowing the guest to safely
+     * continue.  Gluster versions prior to 3.5.6 don't retain the cache
+     * either, but will invalidate the fd on error, so this is again our only
+     * option.
+     *
+     * The 'resync-failed-syncs-after-fsync' xlator option for the
+     * write-behind cache will cause later gluster versions to retain its
+     * cache after error, so long as the fd remains open.  However, we
+     * currently have no way of knowing if this option is supported.
+     *
+     * TODO: Once gluster provides a way for us to determine if the option
+     * is supported, bypass the closure and setting drv to NULL.  */
+    qemu_gluster_close(bs);
+    bs->drv = NULL;
+    return ret;
 }
 
 #ifdef CONFIG_GLUSTERFS_DISCARD
@@ -660,17 +723,6 @@ static int64_t qemu_gluster_allocated_file_size(BlockDriverState *bs)
     }
 }
 
-static void qemu_gluster_close(BlockDriverState *bs)
-{
-    BDRVGlusterState *s = bs->opaque;
-
-    if (s->fd) {
-        glfs_close(s->fd);
-        s->fd = NULL;
-    }
-    glfs_fini(s->glfs);
-}
-
 static int qemu_gluster_has_zero_init(BlockDriverState *bs)
 {
     /* GlusterFS volume could be backed by a block device */

block/io.c

@@ -28,6 +28,8 @@
 #include "block/blockjob.h"
 #include "block/block_int.h"
 #include "block/throttle-groups.h"
+#include "qemu/cutils.h"
+#include "qapi/error.h"
 #include "qemu/error-report.h"
 
 #define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
@@ -251,6 +253,47 @@ static void bdrv_drain_recurse(BlockDriverState *bs)
     }
 }
 
+typedef struct {
+    Coroutine *co;
+    BlockDriverState *bs;
+    QEMUBH *bh;
+    bool done;
+} BdrvCoDrainData;
+
+static void bdrv_co_drain_bh_cb(void *opaque)
+{
+    BdrvCoDrainData *data = opaque;
+    Coroutine *co = data->co;
+
+    qemu_bh_delete(data->bh);
+    bdrv_drain(data->bs);
+    data->done = true;
+    qemu_coroutine_enter(co, NULL);
+}
+
+void coroutine_fn bdrv_co_drain(BlockDriverState *bs)
+{
+    BdrvCoDrainData data;
+
+    /* Calling bdrv_drain() from a BH ensures the current coroutine yields and
+     * other coroutines run if they were queued from
+     * qemu_co_queue_run_restart(). */
+
+    assert(qemu_in_coroutine());
+    data = (BdrvCoDrainData) {
+        .co = qemu_coroutine_self(),
+        .bs = bs,
+        .done = false,
+        .bh = aio_bh_new(bdrv_get_aio_context(bs), bdrv_co_drain_bh_cb, &data),
+    };
+    qemu_bh_schedule(data.bh);
+
+    qemu_coroutine_yield();
+    /* If we are resumed from some other event (such as an aio completion or a
+     * timer callback), it is a bug in the caller that should be fixed. */
+    assert(data.done);
+}
+
 /*
  * Wait for pending requests to complete on a single BlockDriverState subtree,
  * and suspend block driver's internal I/O until next request arrives.
@@ -267,6 +310,10 @@ void bdrv_drain(BlockDriverState *bs)
     bool busy = true;
 
     bdrv_drain_recurse(bs);
+    if (qemu_in_coroutine()) {
+        bdrv_co_drain(bs);
+        return;
+    }
     while (busy) {
         /* Keep iterating */
          bdrv_flush_io_queue(bs);
@@ -745,9 +792,9 @@ int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
         return ret;
     }
 
-    /* No flush needed for cache modes that already do it */
-    if (bs->enable_write_cache) {
-        bdrv_flush(bs);
+    ret = bdrv_flush(bs);
+    if (ret < 0) {
+        return ret;
     }
 
     return 0;
@@ -842,6 +889,7 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
     assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
     assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
     assert(!qiov || bytes == qiov->size);
+    assert((bs->open_flags & BDRV_O_NO_IO) == 0);
 
     /* Handle Copy on Read and associated serialisation */
     if (flags & BDRV_REQ_COPY_ON_READ) {
@@ -1128,6 +1176,7 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
     assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
     assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
     assert(!qiov || bytes == qiov->size);
+    assert((bs->open_flags & BDRV_O_NO_IO) == 0);
 
     waited = wait_serialising_requests(req);
     assert(!waited || !req->serialising);
@@ -1150,13 +1199,20 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
     } else if (flags & BDRV_REQ_ZERO_WRITE) {
         bdrv_debug_event(bs, BLKDBG_PWRITEV_ZERO);
         ret = bdrv_co_do_write_zeroes(bs, sector_num, nb_sectors, flags);
+    } else if (drv->bdrv_co_writev_flags) {
+        bdrv_debug_event(bs, BLKDBG_PWRITEV);
+        ret = drv->bdrv_co_writev_flags(bs, sector_num, nb_sectors, qiov,
+                                        flags);
     } else {
+        assert(drv->supported_write_flags == 0);
         bdrv_debug_event(bs, BLKDBG_PWRITEV);
         ret = drv->bdrv_co_writev(bs, sector_num, nb_sectors, qiov);
     }
     bdrv_debug_event(bs, BLKDBG_PWRITEV_DONE);
 
-    if (ret == 0 && !bs->enable_write_cache) {
+    if (ret == 0 && (flags & BDRV_REQ_FUA) &&
+        !(drv->supported_write_flags & BDRV_REQ_FUA))
+    {
         ret = bdrv_co_flush(bs);
     }
 
@@ -2329,6 +2385,13 @@ int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
     }
 
     tracked_request_begin(&req, bs, 0, 0, BDRV_TRACKED_FLUSH);
+
+    /* Write back all layers by calling one driver function */
+    if (bs->drv->bdrv_co_flush) {
+        ret = bs->drv->bdrv_co_flush(bs);
+        goto out;
+    }
+
     /* Write back cached data to the OS even with cache=unsafe */
     BLKDBG_EVENT(bs->file, BLKDBG_FLUSH_TO_OS);
     if (bs->drv->bdrv_co_flush_to_os) {
@@ -2532,19 +2595,6 @@ int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors)
     return rwco.ret;
 }
 
-typedef struct {
-    CoroutineIOCompletion *co;
-    QEMUBH *bh;
-} BdrvIoctlCompletionData;
-
-static void bdrv_ioctl_bh_cb(void *opaque)
-{
-    BdrvIoctlCompletionData *data = opaque;
-
-    bdrv_co_io_em_complete(data->co, -ENOTSUP);
-    qemu_bh_delete(data->bh);
-}
-
 static int bdrv_co_do_ioctl(BlockDriverState *bs, int req, void *buf)
 {
     BlockDriver *drv = bs->drv;
@@ -2562,11 +2612,8 @@ static int bdrv_co_do_ioctl(BlockDriverState *bs, int req, void *buf)
 
     acb = drv->bdrv_aio_ioctl(bs, req, buf, bdrv_co_io_em_complete, &co);
     if (!acb) {
-        BdrvIoctlCompletionData *data = g_new(BdrvIoctlCompletionData, 1);
-        data->bh = aio_bh_new(bdrv_get_aio_context(bs),
-                                bdrv_ioctl_bh_cb, data);
-        data->co = &co;
-        qemu_bh_schedule(data->bh);
+        co.ret = -ENOTSUP;
+        goto out;
     }
     qemu_coroutine_yield();
 out:

block/iscsi.c

@@ -70,7 +70,6 @@ typedef struct IscsiLun {
     bool lbprz;
     bool dpofua;
     bool has_write_same;
-    bool force_next_flush;
     bool request_timed_out;
 } IscsiLun;
 
@@ -84,7 +83,6 @@ typedef struct IscsiTask {
     QEMUBH *bh;
     IscsiLun *iscsilun;
     QEMUTimer retry_timer;
-    bool force_next_flush;
     int err_code;
 } IscsiTask;
 
@@ -282,8 +280,6 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
         }
         iTask->err_code = iscsi_translate_sense(&task->sense);
         error_report("iSCSI Failure: %s", iscsi_get_error(iscsi));
-    } else {
-        iTask->iscsilun->force_next_flush |= iTask->force_next_flush;
     }
 
 out:
@@ -429,12 +425,14 @@ static unsigned long *iscsi_allocationmap_init(IscsiLun *iscsilun)
 static void iscsi_allocationmap_set(IscsiLun *iscsilun, int64_t sector_num,
                                     int nb_sectors)
 {
+    int64_t cluster_num, nb_clusters;
     if (iscsilun->allocationmap == NULL) {
         return;
     }
-    bitmap_set(iscsilun->allocationmap,
-               sector_num / iscsilun->cluster_sectors,
-               DIV_ROUND_UP(nb_sectors, iscsilun->cluster_sectors));
+    cluster_num = sector_num / iscsilun->cluster_sectors;
+    nb_clusters = DIV_ROUND_UP(sector_num + nb_sectors,
+                               iscsilun->cluster_sectors) - cluster_num;
+    bitmap_set(iscsilun->allocationmap, cluster_num, nb_clusters);
 }
 
 static void iscsi_allocationmap_clear(IscsiLun *iscsilun, int64_t sector_num,
@@ -452,15 +450,15 @@ static void iscsi_allocationmap_clear(IscsiLun *iscsilun, int64_t sector_num,
     }
 }
 
-static int coroutine_fn iscsi_co_writev(BlockDriverState *bs,
-                                        int64_t sector_num, int nb_sectors,
-                                        QEMUIOVector *iov)
+static int coroutine_fn
+iscsi_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
+                      QEMUIOVector *iov, int flags)
 {
     IscsiLun *iscsilun = bs->opaque;
     struct IscsiTask iTask;
     uint64_t lba;
     uint32_t num_sectors;
-    int fua;
+    bool fua;
 
     if (!is_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
         return -EINVAL;
@@ -476,8 +474,7 @@ static int coroutine_fn iscsi_co_writev(BlockDriverState *bs,
     num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
     iscsi_co_init_iscsitask(iscsilun, &iTask);
 retry:
-    fua = iscsilun->dpofua && !bs->enable_write_cache;
-    iTask.force_next_flush = !fua;
+    fua = iscsilun->dpofua && (flags & BDRV_REQ_FUA);
     if (iscsilun->use_16_for_rw) {
         iTask.task = iscsi_write16_task(iscsilun->iscsi, iscsilun->lun, lba,
                                         NULL, num_sectors * iscsilun->block_size,
@@ -518,6 +515,13 @@ retry:
     return 0;
 }
 
+static int coroutine_fn
+iscsi_co_writev(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
+                QEMUIOVector *iov)
+{
+    return iscsi_co_writev_flags(bs, sector_num, nb_sectors, iov, 0);
+}
+
 
 static bool iscsi_allocationmap_is_allocated(IscsiLun *iscsilun,
                                              int64_t sector_num, int nb_sectors)
@@ -715,11 +719,6 @@ static int coroutine_fn iscsi_co_flush(BlockDriverState *bs)
     IscsiLun *iscsilun = bs->opaque;
     struct IscsiTask iTask;
 
-    if (!iscsilun->force_next_flush) {
-        return 0;
-    }
-    iscsilun->force_next_flush = false;
-
     iscsi_co_init_iscsitask(iscsilun, &iTask);
 retry:
     if (iscsi_synchronizecache10_task(iscsilun->iscsi, iscsilun->lun, 0, 0, 0,
@@ -769,6 +768,7 @@ iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
     acb->ioh->driver_status = 0;
     acb->ioh->host_status   = 0;
     acb->ioh->resid         = 0;
+    acb->ioh->status        = status;
 
 #define SG_ERR_DRIVER_SENSE    0x08
 
@@ -840,6 +840,13 @@ static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
         return &acb->common;
     }
 
+    if (acb->ioh->cmd_len > SCSI_CDB_MAX_SIZE) {
+        error_report("iSCSI: ioctl error CDB exceeds max size (%d > %d)",
+                     acb->ioh->cmd_len, SCSI_CDB_MAX_SIZE);
+        qemu_aio_unref(acb);
+        return NULL;
+    }
+
     acb->task = malloc(sizeof(struct scsi_task));
     if (acb->task == NULL) {
         error_report("iSCSI: Failed to allocate task for scsi command. %s",
@@ -1019,7 +1026,6 @@ coroutine_fn iscsi_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
     }
 
     iscsi_co_init_iscsitask(iscsilun, &iTask);
-    iTask.force_next_flush = true;
 retry:
     if (use_16_for_ws) {
         iTask.task = iscsi_writesame16_task(iscsilun->iscsi, iscsilun->lun, lba,
@@ -1852,6 +1858,8 @@ static BlockDriver bdrv_iscsi = {
     .bdrv_co_write_zeroes = iscsi_co_write_zeroes,
     .bdrv_co_readv         = iscsi_co_readv,
     .bdrv_co_writev        = iscsi_co_writev,
+    .bdrv_co_writev_flags  = iscsi_co_writev_flags,
+    .supported_write_flags = BDRV_REQ_FUA,
     .bdrv_co_flush_to_disk = iscsi_co_flush,
 
 #ifdef __linux__

block/mirror.c

@@ -16,6 +16,7 @@
 #include "block/blockjob.h"
 #include "block/block_int.h"
 #include "sysemu/block-backend.h"
+#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
 #include "qemu/bitmap.h"
@@ -107,7 +108,7 @@ static void mirror_iteration_done(MirrorOp *op, int ret)
 
     sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
     chunk_num = op->sector_num / sectors_per_chunk;
-    nb_chunks = op->nb_sectors / sectors_per_chunk;
+    nb_chunks = DIV_ROUND_UP(op->nb_sectors, sectors_per_chunk);
     bitmap_clear(s->in_flight_bitmap, chunk_num, nb_chunks);
     if (ret >= 0) {
         if (s->cow_bitmap) {
@@ -160,6 +161,14 @@ static void mirror_read_complete(void *opaque, int ret)
                     mirror_write_complete, op);
 }
 
+static inline void mirror_clip_sectors(MirrorBlockJob *s,
+                                       int64_t sector_num,
+                                       int *nb_sectors)
+{
+    *nb_sectors = MIN(*nb_sectors,
+                      s->bdev_length / BDRV_SECTOR_SIZE - sector_num);
+}
+
 /* Round sector_num and/or nb_sectors to target cluster if COW is needed, and
  * return the offset of the adjusted tail sector against original. */
 static int mirror_cow_align(MirrorBlockJob *s,
@@ -188,6 +197,9 @@ static int mirror_cow_align(MirrorBlockJob *s,
                                                s->target_cluster_sectors);
         }
     }
+    /* Clipping may result in align_nb_sectors unaligned to chunk boundary, but
+     * that doesn't matter because it's already the end of source image. */
+    mirror_clip_sectors(s, align_sector_num, &align_nb_sectors);
 
     ret = align_sector_num + align_nb_sectors - (*sector_num + *nb_sectors);
     *sector_num = align_sector_num;
@@ -230,9 +242,8 @@ static int mirror_do_read(MirrorBlockJob *s, int64_t sector_num,
     /* The sector range must meet granularity because:
      * 1) Caller passes in aligned values;
      * 2) mirror_cow_align is used only when target cluster is larger. */
-    assert(!(nb_sectors % sectors_per_chunk));
     assert(!(sector_num % sectors_per_chunk));
-    nb_chunks = nb_sectors / sectors_per_chunk;
+    nb_chunks = DIV_ROUND_UP(nb_sectors, sectors_per_chunk);
 
     while (s->buf_free_count < nb_chunks) {
         trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
@@ -297,7 +308,7 @@ static void mirror_do_zero_or_discard(MirrorBlockJob *s,
 static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
 {
     BlockDriverState *source = s->common.bs;
-    int64_t sector_num;
+    int64_t sector_num, first_chunk;
     uint64_t delay_ns = 0;
     /* At least the first dirty chunk is mirrored in one iteration. */
     int nb_chunks = 1;
@@ -312,6 +323,12 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
         assert(sector_num >= 0);
     }
 
+    first_chunk = sector_num / sectors_per_chunk;
+    while (test_bit(first_chunk, s->in_flight_bitmap)) {
+        trace_mirror_yield_in_flight(s, first_chunk, s->in_flight);
+        mirror_wait_for_io(s);
+    }
+
     /* Find the number of consective dirty chunks following the first dirty
      * one, and wait for in flight requests in them. */
     while (nb_chunks * sectors_per_chunk < (s->buf_size >> BDRV_SECTOR_BITS)) {
@@ -323,17 +340,17 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
             break;
         }
         if (test_bit(next_chunk, s->in_flight_bitmap)) {
-            if (nb_chunks > 0) {
-                break;
-            }
-            trace_mirror_yield_in_flight(s, next_sector, s->in_flight);
-            mirror_wait_for_io(s);
-            /* Now retry.  */
-        } else {
-            hbitmap_next = hbitmap_iter_next(&s->hbi);
-            assert(hbitmap_next == next_sector);
-            nb_chunks++;
+            break;
         }
+
+        hbitmap_next = hbitmap_iter_next(&s->hbi);
+        if (hbitmap_next > next_sector || hbitmap_next < 0) {
+            /* The bitmap iterator's cache is stale, refresh it */
+            bdrv_set_dirty_iter(&s->hbi, next_sector);
+            hbitmap_next = hbitmap_iter_next(&s->hbi);
+        }
+        assert(hbitmap_next == next_sector);
+        nb_chunks++;
     }
 
     /* Clear dirty bits before querying the block status, because
@@ -377,6 +394,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
             }
         }
 
+        mirror_clip_sectors(s, sector_num, &io_sectors);
         switch (mirror_method) {
         case MIRROR_METHOD_COPY:
             io_sectors = mirror_do_read(s, sector_num, io_sectors);
@@ -392,7 +410,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
         }
         assert(io_sectors);
         sector_num += io_sectors;
-        nb_chunks -= io_sectors / sectors_per_chunk;
+        nb_chunks -= DIV_ROUND_UP(io_sectors, sectors_per_chunk);
         delay_ns += ratelimit_calculate_delay(&s->limit, io_sectors);
     }
     return delay_ns;
@@ -477,6 +495,9 @@ out:
     block_job_completed(&s->common, data->ret);
     g_free(data);
     bdrv_drained_end(src);
+    if (qemu_get_aio_context() == bdrv_get_aio_context(src)) {
+        aio_enable_external(iohandler_get_aio_context());
+    }
     bdrv_unref(src);
 }
 
@@ -649,7 +670,7 @@ static void coroutine_fn mirror_run(void *opaque)
              * mirror_populate runs.
              */
             trace_mirror_before_drain(s, cnt);
-            bdrv_drain(bs);
+            bdrv_co_drain(bs);
             cnt = bdrv_get_dirty_count(s->dirty_bitmap);
         }
 
@@ -698,6 +719,12 @@ immediate_exit:
     /* Before we switch to target in mirror_exit, make sure data doesn't
      * change. */
     bdrv_drained_begin(s->common.bs);
+    if (qemu_get_aio_context() == bdrv_get_aio_context(bs)) {
+        /* FIXME: virtio host notifiers run on iohandler_ctx, therefore the
+         * above bdrv_drained_end isn't enough to quiesce it. This is ugly, we
+         * need a block layer API change to achieve this. */
+        aio_disable_external(iohandler_get_aio_context());
+    }
     block_job_defer_to_main_loop(&s->common, mirror_exit, data);
 }
 
@@ -855,7 +882,6 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
 
     bdrv_op_block_all(s->target, s->common.blocker);
 
-    bdrv_set_enable_write_cache(s->target, true);
     if (s->target->blk) {
         blk_set_on_error(s->target->blk, on_target_error, on_target_error);
         blk_iostatus_enable(s->target->blk);

block/nbd-client.c

@@ -243,15 +243,15 @@ static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
 
 static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
                            int nb_sectors, QEMUIOVector *qiov,
-                           int offset)
+                           int offset, int *flags)
 {
     NbdClientSession *client = nbd_get_client_session(bs);
     struct nbd_request request = { .type = NBD_CMD_WRITE };
     struct nbd_reply reply;
     ssize_t ret;
 
-    if (!bdrv_enable_write_cache(bs) &&
-        (client->nbdflags & NBD_FLAG_SEND_FUA)) {
+    if ((*flags & BDRV_REQ_FUA) && (client->nbdflags & NBD_FLAG_SEND_FUA)) {
+        *flags &= ~BDRV_REQ_FUA;
         request.type |= NBD_CMD_FLAG_FUA;
     }
 
@@ -269,10 +269,6 @@ static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
     return -reply.error;
 }
 
-/* qemu-nbd has a limit of slightly less than 1M per request.  Try to
- * remain aligned to 4K. */
-#define NBD_MAX_SECTORS 2040
-
 int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
                         int nb_sectors, QEMUIOVector *qiov)
 {
@@ -291,12 +287,13 @@ int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
 }
 
 int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
-                         int nb_sectors, QEMUIOVector *qiov)
+                         int nb_sectors, QEMUIOVector *qiov, int *flags)
 {
     int offset = 0;
     int ret;
     while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_writev_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
+        ret = nbd_co_writev_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset,
+                              flags);
         if (ret < 0) {
             return ret;
         }
@@ -304,7 +301,7 @@ int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
         sector_num += NBD_MAX_SECTORS;
         nb_sectors -= NBD_MAX_SECTORS;
     }
-    return nbd_co_writev_1(bs, sector_num, nb_sectors, qiov, offset);
+    return nbd_co_writev_1(bs, sector_num, nb_sectors, qiov, offset, flags);
 }
 
 int nbd_client_co_flush(BlockDriverState *bs)
@@ -318,10 +315,6 @@ int nbd_client_co_flush(BlockDriverState *bs)
         return 0;
     }
 
-    if (client->nbdflags & NBD_FLAG_SEND_FUA) {
-        request.type |= NBD_CMD_FLAG_FUA;
-    }
-
     request.from = 0;
     request.len = 0;
 

block/nbd-client.h

@@ -20,7 +20,7 @@
 typedef struct NbdClientSession {
     QIOChannelSocket *sioc; /* The master data channel */
     QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */
-    uint32_t nbdflags;
+    uint16_t nbdflags;
     off_t size;
 
     CoMutex send_mutex;
@@ -48,7 +48,7 @@ int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
                           int nb_sectors);
 int nbd_client_co_flush(BlockDriverState *bs);
 int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
-                         int nb_sectors, QEMUIOVector *qiov);
+                         int nb_sectors, QEMUIOVector *qiov, int *flags);
 int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
                         int nb_sectors, QEMUIOVector *qiov);
 

block/nbd.c

@@ -28,6 +28,7 @@
 
 #include "qemu/osdep.h"
 #include "block/nbd-client.h"
+#include "qapi/error.h"
 #include "qemu/uri.h"
 #include "block/block_int.h"
 #include "qemu/module.h"
@@ -35,7 +36,7 @@
 #include "qapi/qmp/qjson.h"
 #include "qapi/qmp/qint.h"
 #include "qapi/qmp/qstring.h"
-
+#include "qemu/cutils.h"
 
 #define EN_OPTSTR ":exportname="
 
@@ -354,10 +355,29 @@ static int nbd_co_readv(BlockDriverState *bs, int64_t sector_num,
     return nbd_client_co_readv(bs, sector_num, nb_sectors, qiov);
 }
 
+static int nbd_co_writev_flags(BlockDriverState *bs, int64_t sector_num,
+                               int nb_sectors, QEMUIOVector *qiov, int flags)
+{
+    int ret;
+
+    ret = nbd_client_co_writev(bs, sector_num, nb_sectors, qiov, &flags);
+    if (ret < 0) {
+        return ret;
+    }
+
+    /* The flag wasn't sent to the server, so we need to emulate it with an
+     * explicit flush */
+    if (flags & BDRV_REQ_FUA) {
+        ret = nbd_client_co_flush(bs);
+    }
+
+    return ret;
+}
+
 static int nbd_co_writev(BlockDriverState *bs, int64_t sector_num,
                          int nb_sectors, QEMUIOVector *qiov)
 {
-    return nbd_client_co_writev(bs, sector_num, nb_sectors, qiov);
+    return nbd_co_writev_flags(bs, sector_num, nb_sectors, qiov, 0);
 }
 
 static int nbd_co_flush(BlockDriverState *bs)
@@ -457,6 +477,8 @@ static BlockDriver bdrv_nbd = {
     .bdrv_file_open             = nbd_open,
     .bdrv_co_readv              = nbd_co_readv,
     .bdrv_co_writev             = nbd_co_writev,
+    .bdrv_co_writev_flags       = nbd_co_writev_flags,
+    .supported_write_flags      = BDRV_REQ_FUA,
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
     .bdrv_co_discard            = nbd_co_discard,
@@ -475,6 +497,8 @@ static BlockDriver bdrv_nbd_tcp = {
     .bdrv_file_open             = nbd_open,
     .bdrv_co_readv              = nbd_co_readv,
     .bdrv_co_writev             = nbd_co_writev,
+    .bdrv_co_writev_flags       = nbd_co_writev_flags,
+    .supported_write_flags      = BDRV_REQ_FUA,
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
     .bdrv_co_discard            = nbd_co_discard,
@@ -493,6 +517,8 @@ static BlockDriver bdrv_nbd_unix = {
     .bdrv_file_open             = nbd_open,
     .bdrv_co_readv              = nbd_co_readv,
     .bdrv_co_writev             = nbd_co_writev,
+    .bdrv_co_writev_flags       = nbd_co_writev_flags,
+    .supported_write_flags      = BDRV_REQ_FUA,
     .bdrv_close                 = nbd_close,
     .bdrv_co_flush_to_os        = nbd_co_flush,
     .bdrv_co_discard            = nbd_co_discard,

block/nfs.c

@@ -1,7 +1,7 @@
 /*
  * QEMU Block driver for native access to files on NFS shares
  *
- * Copyright (c) 2014 Peter Lieven <pl@kamp.de>
+ * Copyright (c) 2014-2016 Peter Lieven <pl@kamp.de>
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this software and associated documentation files (the "Software"), to deal
@@ -28,10 +28,12 @@
 #include "qemu-common.h"
 #include "qemu/config-file.h"
 #include "qemu/error-report.h"
+#include "qapi/error.h"
 #include "block/block_int.h"
 #include "trace.h"
 #include "qemu/iov.h"
 #include "qemu/uri.h"
+#include "qemu/cutils.h"
 #include "sysemu/sysemu.h"
 #include <nfsc/libnfs.h>
 
@@ -45,6 +47,7 @@ typedef struct NFSClient {
     bool has_zero_init;
     AioContext *aio_context;
     blkcnt_t st_blocks;
+    bool cache_used;
 } NFSClient;
 
 typedef struct NFSRPC {
@@ -276,7 +279,7 @@ static void nfs_file_close(BlockDriverState *bs)
 }
 
 static int64_t nfs_client_open(NFSClient *client, const char *filename,
-                               int flags, Error **errp)
+                               int flags, Error **errp, int open_flags)
 {
     int ret = -EINVAL, i;
     struct stat st;
@@ -328,12 +331,18 @@ static int64_t nfs_client_open(NFSClient *client, const char *filename,
             nfs_set_tcp_syncnt(client->context, val);
 #ifdef LIBNFS_FEATURE_READAHEAD
         } else if (!strcmp(qp->p[i].name, "readahead")) {
+            if (open_flags & BDRV_O_NOCACHE) {
+                error_setg(errp, "Cannot enable NFS readahead "
+                                 "if cache.direct = on");
+                goto fail;
+            }
             if (val > QEMU_NFS_MAX_READAHEAD_SIZE) {
                 error_report("NFS Warning: Truncating NFS readahead"
                              " size to %d", QEMU_NFS_MAX_READAHEAD_SIZE);
                 val = QEMU_NFS_MAX_READAHEAD_SIZE;
             }
             nfs_set_readahead(client->context, val);
+            client->cache_used = true;
 #endif
 #ifdef LIBNFS_FEATURE_DEBUG
         } else if (!strcmp(qp->p[i].name, "debug")) {
@@ -416,7 +425,7 @@ static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
     }
     ret = nfs_client_open(client, qemu_opt_get(opts, "filename"),
                           (flags & BDRV_O_RDWR) ? O_RDWR : O_RDONLY,
-                          errp);
+                          errp, bs->open_flags);
     if (ret < 0) {
         goto out;
     }
@@ -452,7 +461,7 @@ static int nfs_file_create(const char *url, QemuOpts *opts, Error **errp)
     total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
                           BDRV_SECTOR_SIZE);
 
-    ret = nfs_client_open(client, url, O_CREAT, errp);
+    ret = nfs_client_open(client, url, O_CREAT, errp, 0);
     if (ret < 0) {
         goto out;
     }
@@ -514,6 +523,11 @@ static int nfs_reopen_prepare(BDRVReopenState *state,
         return -EACCES;
     }
 
+    if ((state->flags & BDRV_O_NOCACHE) && client->cache_used) {
+        error_setg(errp, "Cannot disable cache if libnfs readahead is enabled");
+        return -EINVAL;
+    }
+
     /* Update cache for read-only reopens */
     if (!(state->flags & BDRV_O_RDWR)) {
         ret = nfs_fstat(client->context, client->fh, &st);

block/null.c

@@ -11,13 +11,16 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "block/block_int.h"
 
 #define NULL_OPT_LATENCY "latency-ns"
+#define NULL_OPT_ZEROES  "read-zeroes"
 
 typedef struct {
     int64_t length;
     int64_t latency_ns;
+    bool read_zeroes;
 } BDRVNullState;
 
 static QemuOptsList runtime_opts = {
@@ -40,6 +43,11 @@ static QemuOptsList runtime_opts = {
             .help = "nanoseconds (approximated) to wait "
                     "before completing request",
         },
+        {
+            .name = NULL_OPT_ZEROES,
+            .type = QEMU_OPT_BOOL,
+            .help = "return zeroes when read",
+        },
         { /* end of list */ }
     },
 };
@@ -61,6 +69,7 @@ static int null_file_open(BlockDriverState *bs, QDict *options, int flags,
         error_setg(errp, "latency-ns is invalid");
         ret = -EINVAL;
     }
+    s->read_zeroes = qemu_opt_get_bool(opts, NULL_OPT_ZEROES, false);
     qemu_opts_del(opts);
     return ret;
 }
@@ -90,6 +99,12 @@ static coroutine_fn int null_co_readv(BlockDriverState *bs,
                                       int64_t sector_num, int nb_sectors,
                                       QEMUIOVector *qiov)
 {
+    BDRVNullState *s = bs->opaque;
+
+    if (s->read_zeroes) {
+        qemu_iovec_memset(qiov, 0, 0, nb_sectors * BDRV_SECTOR_SIZE);
+    }
+
     return null_co_common(bs);
 }
 
@@ -159,6 +174,12 @@ static BlockAIOCB *null_aio_readv(BlockDriverState *bs,
                                   BlockCompletionFunc *cb,
                                   void *opaque)
 {
+    BDRVNullState *s = bs->opaque;
+
+    if (s->read_zeroes) {
+        qemu_iovec_memset(qiov, 0, 0, nb_sectors * BDRV_SECTOR_SIZE);
+    }
+
     return null_aio_common(bs, cb, opaque);
 }
 
@@ -184,6 +205,24 @@ static int null_reopen_prepare(BDRVReopenState *reopen_state,
     return 0;
 }
 
+static int64_t coroutine_fn null_co_get_block_status(BlockDriverState *bs,
+                                                     int64_t sector_num,
+                                                     int nb_sectors, int *pnum,
+                                                     BlockDriverState **file)
+{
+    BDRVNullState *s = bs->opaque;
+    off_t start = sector_num * BDRV_SECTOR_SIZE;
+
+    *pnum = nb_sectors;
+    *file = bs;
+
+    if (s->read_zeroes) {
+        return BDRV_BLOCK_OFFSET_VALID | start | BDRV_BLOCK_ZERO;
+    } else {
+        return BDRV_BLOCK_OFFSET_VALID | start;
+    }
+}
+
 static BlockDriver bdrv_null_co = {
     .format_name            = "null-co",
     .protocol_name          = "null-co",
@@ -197,6 +236,8 @@ static BlockDriver bdrv_null_co = {
     .bdrv_co_writev         = null_co_writev,
     .bdrv_co_flush_to_disk  = null_co_flush,
     .bdrv_reopen_prepare    = null_reopen_prepare,
+
+    .bdrv_co_get_block_status   = null_co_get_block_status,
 };
 
 static BlockDriver bdrv_null_aio = {
@@ -212,6 +253,8 @@ static BlockDriver bdrv_null_aio = {
     .bdrv_aio_writev        = null_aio_writev,
     .bdrv_aio_flush         = null_aio_flush,
     .bdrv_reopen_prepare    = null_reopen_prepare,
+
+    .bdrv_co_get_block_status   = null_co_get_block_status,
 };
 
 static void bdrv_null_init(void)

block/parallels.c

@@ -28,6 +28,7 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "sysemu/block-backend.h"
@@ -479,8 +480,7 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     file = blk_new_open(filename, NULL, NULL,
-                        BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
-                        &local_err);
+                        BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
     if (file == NULL) {
         error_propagate(errp, local_err);
         return -EIO;

block/qapi.c

@@ -32,8 +32,10 @@
 #include "qapi/qmp-output-visitor.h"
 #include "qapi/qmp/types.h"
 #include "sysemu/block-backend.h"
+#include "qemu/cutils.h"
 
-BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs, Error **errp)
+BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk,
+                                        BlockDriverState *bs, Error **errp)
 {
     ImageInfo **p_image_info;
     BlockDriverState *bs0;
@@ -47,7 +49,7 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs, Error **errp)
 
     info->cache = g_new(BlockdevCacheInfo, 1);
     *info->cache = (BlockdevCacheInfo) {
-        .writeback      = bdrv_enable_write_cache(bs),
+        .writeback      = blk ? blk_enable_write_cache(blk) : true,
         .direct         = !!(bs->open_flags & BDRV_O_NOCACHE),
         .no_flush       = !!(bs->open_flags & BDRV_O_NO_FLUSH),
     };
@@ -342,7 +344,7 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
 
     if (bs && bs->drv) {
         info->has_inserted = true;
-        info->inserted = bdrv_block_device_info(bs, errp);
+        info->inserted = bdrv_block_device_info(blk, bs, errp);
         if (info->inserted == NULL) {
             goto err;
         }
@@ -359,50 +361,47 @@ static BlockStats *bdrv_query_stats(BlockBackend *blk,
                                     const BlockDriverState *bs,
                                     bool query_backing);
 
-static void bdrv_query_blk_stats(BlockStats *s, BlockBackend *blk)
+static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
 {
     BlockAcctStats *stats = blk_get_stats(blk);
     BlockAcctTimedStats *ts = NULL;
 
-    s->has_device = true;
-    s->device = g_strdup(blk_name(blk));
+    ds->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
+    ds->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
+    ds->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
+    ds->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
 
-    s->stats->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
-    s->stats->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
-    s->stats->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
-    s->stats->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
+    ds->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
+    ds->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
+    ds->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
 
-    s->stats->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
-    s->stats->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
-    s->stats->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
-
-    s->stats->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
-    s->stats->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
-    s->stats->invalid_flush_operations =
+    ds->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
+    ds->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
+    ds->invalid_flush_operations =
         stats->invalid_ops[BLOCK_ACCT_FLUSH];
 
-    s->stats->rd_merged = stats->merged[BLOCK_ACCT_READ];
-    s->stats->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
-    s->stats->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
-    s->stats->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
-    s->stats->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
-    s->stats->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
+    ds->rd_merged = stats->merged[BLOCK_ACCT_READ];
+    ds->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
+    ds->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
+    ds->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
+    ds->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
+    ds->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
 
-    s->stats->has_idle_time_ns = stats->last_access_time_ns > 0;
-    if (s->stats->has_idle_time_ns) {
-        s->stats->idle_time_ns = block_acct_idle_time_ns(stats);
+    ds->has_idle_time_ns = stats->last_access_time_ns > 0;
+    if (ds->has_idle_time_ns) {
+        ds->idle_time_ns = block_acct_idle_time_ns(stats);
     }
 
-    s->stats->account_invalid = stats->account_invalid;
-    s->stats->account_failed = stats->account_failed;
+    ds->account_invalid = stats->account_invalid;
+    ds->account_failed = stats->account_failed;
 
     while ((ts = block_acct_interval_next(stats, ts))) {
         BlockDeviceTimedStatsList *timed_stats =
             g_malloc0(sizeof(*timed_stats));
         BlockDeviceTimedStats *dev_stats = g_malloc0(sizeof(*dev_stats));
-        timed_stats->next = s->stats->timed_stats;
+        timed_stats->next = ds->timed_stats;
         timed_stats->value = dev_stats;
-        s->stats->timed_stats = timed_stats;
+        ds->timed_stats = timed_stats;
 
         TimedAverage *rd = &ts->latency[BLOCK_ACCT_READ];
         TimedAverage *wr = &ts->latency[BLOCK_ACCT_WRITE];
@@ -461,7 +460,9 @@ static BlockStats *bdrv_query_stats(BlockBackend *blk,
     s->stats = g_malloc0(sizeof(*s->stats));
 
     if (blk) {
-        bdrv_query_blk_stats(s, blk);
+        s->has_device = true;
+        s->device = g_strdup(blk_name(blk));
+        bdrv_query_blk_stats(s->stats, blk);
     }
     if (bs) {
         bdrv_query_bds_stats(s, bs, query_backing);
@@ -651,9 +652,8 @@ static void dump_qlist(fprintf_function func_fprintf, void *f, int indentation,
     for (entry = qlist_first(list); entry; entry = qlist_next(entry), i++) {
         QType type = qobject_type(entry->value);
         bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
-        const char *format = composite ? "%*s[%i]:\n" : "%*s[%i]: ";
-
-        func_fprintf(f, format, indentation * 4, "", i);
+        func_fprintf(f, "%*s[%i]:%c", indentation * 4, "", i,
+                     composite ? '\n' : ' ');
         dump_qobject(func_fprintf, f, indentation + 1, entry->value);
         if (!composite) {
             func_fprintf(f, "\n");
@@ -669,8 +669,7 @@ static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
     for (entry = qdict_first(dict); entry; entry = qdict_next(dict, entry)) {
         QType type = qobject_type(entry->value);
         bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
-        const char *format = composite ? "%*s%s:\n" : "%*s%s: ";
-        char key[strlen(entry->key) + 1];
+        char *key = g_malloc(strlen(entry->key) + 1);
         int i;
 
         /* replace dashes with spaces in key (variable) names */
@@ -678,12 +677,13 @@ static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
             key[i] = entry->key[i] == '-' ? ' ' : entry->key[i];
         }
         key[i] = 0;
-
-        func_fprintf(f, format, indentation * 4, "", key);
+        func_fprintf(f, "%*s%s:%c", indentation * 4, "", key,
+                     composite ? '\n' : ' ');
         dump_qobject(func_fprintf, f, indentation + 1, entry->value);
         if (!composite) {
             func_fprintf(f, "\n");
         }
+        g_free(key);
     }
 }
 

block/qcow.c

@@ -22,7 +22,9 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
+#include "qemu/error-report.h"
 #include "block/block_int.h"
 #include "sysemu/block-backend.h"
 #include "qemu/module.h"
@@ -157,6 +159,14 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     }
     s->crypt_method_header = header.crypt_method;
     if (s->crypt_method_header) {
+        if (bdrv_uses_whitelist() &&
+            s->crypt_method_header == QCOW_CRYPT_AES) {
+            error_report("qcow built-in AES encryption is deprecated");
+            error_printf("Support for it will be removed in a future release.\n"
+                         "You can use 'qemu-img convert' to switch to an\n"
+                         "unencrypted qcow image, or a LUKS raw image.\n");
+        }
+
         bs->encrypted = 1;
     }
     s->cluster_bits = header.cluster_bits;
@@ -794,8 +804,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     qcow_blk = blk_new_open(filename, NULL, NULL,
-                            BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
-                            &local_err);
+                            BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
     if (qcow_blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;

block/qcow2-cluster.c

@@ -25,6 +25,7 @@
 #include "qemu/osdep.h"
 #include <zlib.h>
 
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "block/qcow2.h"
@@ -63,7 +64,8 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
         }
     }
 
-    if (new_l1_size > INT_MAX / sizeof(uint64_t)) {
+    QEMU_BUILD_BUG_ON(QCOW_MAX_L1_SIZE > INT_MAX);
+    if (new_l1_size > QCOW_MAX_L1_SIZE / sizeof(uint64_t)) {
         return -EFBIG;
     }
 

block/qcow2-refcount.c

@@ -23,6 +23,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "block/qcow2.h"

block/qcow2-snapshot.c

@@ -23,10 +23,11 @@
  */
 
 #include "qemu/osdep.h"
-#include "qemu-common.h"
+#include "qapi/error.h"
 #include "block/block_int.h"
 #include "block/qcow2.h"
 #include "qemu/error-report.h"
+#include "qemu/cutils.h"
 
 void qcow2_free_snapshots(BlockDriverState *bs)
 {

block/qcow2.c

@@ -22,7 +22,6 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
-#include "qemu-common.h"
 #include "block/block_int.h"
 #include "sysemu/block-backend.h"
 #include "qemu/module.h"
@@ -36,6 +35,7 @@
 #include "qapi-event.h"
 #include "trace.h"
 #include "qemu/option_int.h"
+#include "qemu/cutils.h"
 
 /*
   Differences with QCOW:
@@ -965,6 +965,14 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     }
     s->crypt_method_header = header.crypt_method;
     if (s->crypt_method_header) {
+        if (bdrv_uses_whitelist() &&
+            s->crypt_method_header == QCOW_CRYPT_AES) {
+            error_report("qcow2 built-in AES encryption is deprecated");
+            error_printf("Support for it will be removed in a future release.\n"
+                         "You can use 'qemu-img convert' to switch to an\n"
+                         "unencrypted qcow2 image, or a LUKS raw image.\n");
+        }
+
         bs->encrypted = 1;
     }
 
@@ -1978,6 +1986,10 @@ static int qcow2_change_backing_file(BlockDriverState *bs,
 {
     BDRVQcow2State *s = bs->opaque;
 
+    if (backing_file && strlen(backing_file) > 1023) {
+        return -EINVAL;
+    }
+
     pstrcpy(bs->backing_file, sizeof(bs->backing_file), backing_file ?: "");
     pstrcpy(bs->backing_format, sizeof(bs->backing_format), backing_fmt ?: "");
 
@@ -2160,8 +2172,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
-                       &local_err);
+                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         return -EIO;
@@ -2225,8 +2236,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     options = qdict_new();
     qdict_put(options, "driver", qstring_from_str("qcow2"));
     blk = blk_new_open(filename, NULL, options,
-                       BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH,
-                       &local_err);
+                       BDRV_O_RDWR | BDRV_O_NO_FLUSH, &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -2287,8 +2297,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     options = qdict_new();
     qdict_put(options, "driver", qstring_from_str("qcow2"));
     blk = blk_new_open(filename, NULL, options,
-                       BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_BACKING,
-                       &local_err);
+                       BDRV_O_RDWR | BDRV_O_NO_BACKING, &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;

block/qed.c

@@ -13,6 +13,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu/timer.h"
 #include "trace.h"
 #include "qed.h"
@@ -346,7 +347,7 @@ static void qed_start_need_check_timer(BDRVQEDState *s)
      * migration.
      */
     timer_mod(s->need_check_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
-                   get_ticks_per_sec() * QED_NEED_CHECK_TIMEOUT);
+                   NANOSECONDS_PER_SECOND * QED_NEED_CHECK_TIMEOUT);
 }
 
 /* It's okay to call this multiple times or when no timer is started */
@@ -575,8 +576,7 @@ static int qed_create(const char *filename, uint32_t cluster_size,
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
-                       &local_err);
+                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         return -EIO;

block/qed.h

@@ -16,6 +16,7 @@
 #define BLOCK_QED_H
 
 #include "block/block_int.h"
+#include "qemu/cutils.h"
 
 /* The layout of a QED file is as follows:
  *

block/raw-aio.h

@@ -15,6 +15,8 @@
 #ifndef QEMU_RAW_AIO_H
 #define QEMU_RAW_AIO_H
 
+#include "qemu/iov.h"
+
 /* AIO request types */
 #define QEMU_AIO_READ         0x0001
 #define QEMU_AIO_WRITE        0x0002

block/raw-posix.c

@@ -22,7 +22,8 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
-#include "qemu-common.h"
+#include "qapi/error.h"
+#include "qemu/cutils.h"
 #include "qemu/error-report.h"
 #include "qemu/timer.h"
 #include "qemu/log.h"
@@ -44,6 +45,7 @@
 #include <IOKit/storage/IOMedia.h>
 #include <IOKit/storage/IOCDMedia.h>
 //#include <IOKit/storage/IOCDTypes.h>
+#include <IOKit/storage/IODVDMedia.h>
 #include <CoreFoundation/CoreFoundation.h>
 #endif
 
@@ -1965,33 +1967,47 @@ BlockDriver bdrv_file = {
 /* host device */
 
 #if defined(__APPLE__) && defined(__MACH__)
-static kern_return_t FindEjectableCDMedia( io_iterator_t *mediaIterator );
 static kern_return_t GetBSDPath(io_iterator_t mediaIterator, char *bsdPath,
                                 CFIndex maxPathSize, int flags);
-kern_return_t FindEjectableCDMedia( io_iterator_t *mediaIterator )
+static char *FindEjectableOpticalMedia(io_iterator_t *mediaIterator)
 {
-    kern_return_t       kernResult;
+    kern_return_t kernResult = KERN_FAILURE;
     mach_port_t     masterPort;
     CFMutableDictionaryRef  classesToMatch;
+    const char *matching_array[] = {kIODVDMediaClass, kIOCDMediaClass};
+    char *mediaType = NULL;
 
     kernResult = IOMasterPort( MACH_PORT_NULL, &masterPort );
     if ( KERN_SUCCESS != kernResult ) {
         printf( "IOMasterPort returned %d\n", kernResult );
     }
 
-    classesToMatch = IOServiceMatching( kIOCDMediaClass );
-    if ( classesToMatch == NULL ) {
-        printf( "IOServiceMatching returned a NULL dictionary.\n" );
-    } else {
-    CFDictionarySetValue( classesToMatch, CFSTR( kIOMediaEjectableKey ), kCFBooleanTrue );
-    }
-    kernResult = IOServiceGetMatchingServices( masterPort, classesToMatch, mediaIterator );
-    if ( KERN_SUCCESS != kernResult )
-    {
-        printf( "IOServiceGetMatchingServices returned %d\n", kernResult );
-    }
+    int index;
+    for (index = 0; index < ARRAY_SIZE(matching_array); index++) {
+        classesToMatch = IOServiceMatching(matching_array[index]);
+        if (classesToMatch == NULL) {
+            error_report("IOServiceMatching returned NULL for %s",
+                         matching_array[index]);
+            continue;
+        }
+        CFDictionarySetValue(classesToMatch, CFSTR(kIOMediaEjectableKey),
+                             kCFBooleanTrue);
+        kernResult = IOServiceGetMatchingServices(masterPort, classesToMatch,
+                                                  mediaIterator);
+        if (kernResult != KERN_SUCCESS) {
+            error_report("Note: IOServiceGetMatchingServices returned %d",
+                         kernResult);
+            continue;
+        }
 
-    return kernResult;
+        /* If a match was found, leave the loop */
+        if (*mediaIterator != 0) {
+            DPRINTF("Matching using %s\n", matching_array[index]);
+            mediaType = g_strdup(matching_array[index]);
+            break;
+        }
+    }
+    return mediaType;
 }
 
 kern_return_t GetBSDPath(io_iterator_t mediaIterator, char *bsdPath,
@@ -2023,7 +2039,46 @@ kern_return_t GetBSDPath(io_iterator_t mediaIterator, char *bsdPath,
     return kernResult;
 }
 
-#endif
+/* Sets up a real cdrom for use in QEMU */
+static bool setup_cdrom(char *bsd_path, Error **errp)
+{
+    int index, num_of_test_partitions = 2, fd;
+    char test_partition[MAXPATHLEN];
+    bool partition_found = false;
+
+    /* look for a working partition */
+    for (index = 0; index < num_of_test_partitions; index++) {
+        snprintf(test_partition, sizeof(test_partition), "%ss%d", bsd_path,
+                 index);
+        fd = qemu_open(test_partition, O_RDONLY | O_BINARY | O_LARGEFILE);
+        if (fd >= 0) {
+            partition_found = true;
+            qemu_close(fd);
+            break;
+        }
+    }
+
+    /* if a working partition on the device was not found */
+    if (partition_found == false) {
+        error_setg(errp, "Failed to find a working partition on disc");
+    } else {
+        DPRINTF("Using %s as optical disc\n", test_partition);
+        pstrcpy(bsd_path, MAXPATHLEN, test_partition);
+    }
+    return partition_found;
+}
+
+/* Prints directions on mounting and unmounting a device */
+static void print_unmounting_directions(const char *file_name)
+{
+    error_report("If device %s is mounted on the desktop, unmount"
+                 " it first before using it in QEMU", file_name);
+    error_report("Command to unmount device: diskutil unmountDisk %s",
+                 file_name);
+    error_report("Command to mount device: diskutil mountDisk %s", file_name);
+}
+
+#endif /* defined(__APPLE__) && defined(__MACH__) */
 
 static int hdev_probe_device(const char *filename)
 {
@@ -2114,33 +2169,57 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
 
 #if defined(__APPLE__) && defined(__MACH__)
     const char *filename = qdict_get_str(options, "filename");
+    char bsd_path[MAXPATHLEN] = "";
+    bool error_occurred = false;
 
-    if (strstart(filename, "/dev/cdrom", NULL)) {
-        kern_return_t kernResult;
-        io_iterator_t mediaIterator;
-        char bsdPath[ MAXPATHLEN ];
-        int fd;
+    /* If using a real cdrom */
+    if (strcmp(filename, "/dev/cdrom") == 0) {
+        char *mediaType = NULL;
+        kern_return_t ret_val;
+        io_iterator_t mediaIterator = 0;
 
-        kernResult = FindEjectableCDMedia( &mediaIterator );
-        kernResult = GetBSDPath(mediaIterator, bsdPath, sizeof(bsdPath),
-                                flags);
-        if ( bsdPath[ 0 ] != '\0' ) {
-            strcat(bsdPath,"s0");
-            /* some CDs don't have a partition 0 */
-            fd = qemu_open(bsdPath, O_RDONLY | O_BINARY | O_LARGEFILE);
-            if (fd < 0) {
-                bsdPath[strlen(bsdPath)-1] = '1';
-            } else {
-                qemu_close(fd);
-            }
-            filename = bsdPath;
-            qdict_put(options, "filename", qstring_from_str(filename));
+        mediaType = FindEjectableOpticalMedia(&mediaIterator);
+        if (mediaType == NULL) {
+            error_setg(errp, "Please make sure your CD/DVD is in the optical"
+                       " drive");
+            error_occurred = true;
+            goto hdev_open_Mac_error;
         }
 
-        if ( mediaIterator )
-            IOObjectRelease( mediaIterator );
+        ret_val = GetBSDPath(mediaIterator, bsd_path, sizeof(bsd_path), flags);
+        if (ret_val != KERN_SUCCESS) {
+            error_setg(errp, "Could not get BSD path for optical drive");
+            error_occurred = true;
+            goto hdev_open_Mac_error;
+        }
+
+        /* If a real optical drive was not found */
+        if (bsd_path[0] == '\0') {
+            error_setg(errp, "Failed to obtain bsd path for optical drive");
+            error_occurred = true;
+            goto hdev_open_Mac_error;
+        }
+
+        /* If using a cdrom disc and finding a partition on the disc failed */
+        if (strncmp(mediaType, kIOCDMediaClass, 9) == 0 &&
+            setup_cdrom(bsd_path, errp) == false) {
+            print_unmounting_directions(bsd_path);
+            error_occurred = true;
+            goto hdev_open_Mac_error;
+        }
+
+        qdict_put(options, "filename", qstring_from_str(bsd_path));
+
+hdev_open_Mac_error:
+        g_free(mediaType);
+        if (mediaIterator) {
+            IOObjectRelease(mediaIterator);
+        }
+        if (error_occurred) {
+            return -ENOENT;
+        }
     }
-#endif
+#endif /* defined(__APPLE__) && defined(__MACH__) */
 
     s->type = FTYPE_FILE;
 
@@ -2149,6 +2228,15 @@ static int hdev_open(BlockDriverState *bs, QDict *options, int flags,
         if (local_err) {
             error_propagate(errp, local_err);
         }
+#if defined(__APPLE__) && defined(__MACH__)
+        if (*bsd_path) {
+            filename = bsd_path;
+        }
+        /* if a physical device experienced an error while being opened */
+        if (strncmp(filename, "/dev/", 5) == 0) {
+            print_unmounting_directions(filename);
+        }
+#endif /* defined(__APPLE__) && defined(__MACH__) */
         return ret;
     }
 

block/raw-win32.c

@@ -22,7 +22,8 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
-#include "qemu-common.h"
+#include "qapi/error.h"
+#include "qemu/cutils.h"
 #include "qemu/timer.h"
 #include "block/block_int.h"
 #include "qemu/module.h"

block/raw_bsd.c

@@ -28,6 +28,7 @@
 
 #include "qemu/osdep.h"
 #include "block/block_int.h"
+#include "qapi/error.h"
 #include "qemu/option.h"
 
 static QemuOptsList raw_create_opts = {
@@ -56,8 +57,9 @@ static int coroutine_fn raw_co_readv(BlockDriverState *bs, int64_t sector_num,
     return bdrv_co_readv(bs->file->bs, sector_num, nb_sectors, qiov);
 }
 
-static int coroutine_fn raw_co_writev(BlockDriverState *bs, int64_t sector_num,
-                                      int nb_sectors, QEMUIOVector *qiov)
+static int coroutine_fn
+raw_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
+                    QEMUIOVector *qiov, int flags)
 {
     void *buf = NULL;
     BlockDriver *drv;
@@ -103,7 +105,8 @@ static int coroutine_fn raw_co_writev(BlockDriverState *bs, int64_t sector_num,
     }
 
     BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
-    ret = bdrv_co_writev(bs->file->bs, sector_num, nb_sectors, qiov);
+    ret = bdrv_co_do_pwritev(bs->file->bs, sector_num * BDRV_SECTOR_SIZE,
+                             nb_sectors * BDRV_SECTOR_SIZE, qiov, flags);
 
 fail:
     if (qiov == &local_qiov) {
@@ -113,6 +116,13 @@ fail:
     return ret;
 }
 
+static int coroutine_fn
+raw_co_writev(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
+              QEMUIOVector *qiov)
+{
+    return raw_co_writev_flags(bs, sector_num, nb_sectors, qiov, 0);
+}
+
 static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
                                             int64_t sector_num,
                                             int nb_sectors, int *pnum,
@@ -247,6 +257,8 @@ BlockDriver bdrv_raw = {
     .bdrv_create          = &raw_create,
     .bdrv_co_readv        = &raw_co_readv,
     .bdrv_co_writev       = &raw_co_writev,
+    .bdrv_co_writev_flags = &raw_co_writev_flags,
+    .supported_write_flags = BDRV_REQ_FUA,
     .bdrv_co_write_zeroes = &raw_co_write_zeroes,
     .bdrv_co_discard      = &raw_co_discard,
     .bdrv_co_get_block_status = &raw_co_get_block_status,

block/rbd.c

@@ -13,10 +13,11 @@
 
 #include "qemu/osdep.h"
 
-#include "qemu-common.h"
+#include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "block/block_int.h"
 #include "crypto/secret.h"
+#include "qemu/cutils.h"
 
 #include <rbd/librbd.h>
 

block/sheepdog.c

@@ -13,13 +13,14 @@
  */
 
 #include "qemu/osdep.h"
-#include "qemu-common.h"
+#include "qapi/error.h"
 #include "qemu/uri.h"
 #include "qemu/error-report.h"
 #include "qemu/sockets.h"
 #include "block/block_int.h"
 #include "sysemu/block-backend.h"
 #include "qemu/bitops.h"
+#include "qemu/cutils.h"
 
 #define SD_PROTO_VER 0x01
 
@@ -1647,8 +1648,7 @@ static int sd_prealloc(const char *filename, Error **errp)
     int ret;
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
-                       errp);
+                       BDRV_O_RDWR | BDRV_O_PROTOCOL, errp);
     if (blk == NULL) {
         ret = -EIO;
         goto out_with_err_set;
@@ -1844,7 +1844,7 @@ static int sd_create(const char *filename, QemuOpts *opts,
         }
 
         blk = blk_new_open(backing_file, NULL, NULL,
-                           BDRV_O_PROTOCOL | BDRV_O_CACHE_WB, errp);
+                           BDRV_O_PROTOCOL, errp);
         if (blk == NULL) {
             ret = -EIO;
             goto out;

block/snapshot.c

@@ -25,6 +25,7 @@
 #include "qemu/osdep.h"
 #include "block/snapshot.h"
 #include "block/block_int.h"
+#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 
 QemuOptsList internal_snapshot_opts = {

block/ssh.c

@@ -28,6 +28,7 @@
 #include <libssh2_sftp.h>
 
 #include "block/block_int.h"
+#include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "qemu/sockets.h"
 #include "qemu/uri.h"

block/stream.c

@@ -15,6 +15,7 @@
 #include "trace.h"
 #include "block/block_int.h"
 #include "block/blockjob.h"
+#include "qapi/error.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/ratelimit.h"
 #include "sysemu/block-backend.h"
@@ -89,21 +90,21 @@ static void coroutine_fn stream_run(void *opaque)
     StreamCompleteData *data;
     BlockDriverState *bs = s->common.bs;
     BlockDriverState *base = s->base;
-    int64_t sector_num, end;
+    int64_t sector_num = 0;
+    int64_t end = -1;
     int error = 0;
     int ret = 0;
     int n = 0;
     void *buf;
 
     if (!bs->backing) {
-        block_job_completed(&s->common, 0);
-        return;
+        goto out;
     }
 
     s->common.len = bdrv_getlength(bs);
     if (s->common.len < 0) {
-        block_job_completed(&s->common, s->common.len);
-        return;
+        ret = s->common.len;
+        goto out;
     }
 
     end = s->common.len >> BDRV_SECTOR_BITS;
@@ -190,6 +191,7 @@ wait:
 
     qemu_vfree(buf);
 
+out:
     /* Modify backing chain and close BDSes in main loop */
     data = g_malloc(sizeof(*data));
     data->ret = ret;

block/vdi.c

@@ -50,12 +50,13 @@
  */
 
 #include "qemu/osdep.h"
-#include "qemu-common.h"
+#include "qapi/error.h"
 #include "block/block_int.h"
 #include "sysemu/block-backend.h"
 #include "qemu/module.h"
 #include "migration/migration.h"
 #include "qemu/coroutine.h"
+#include "qemu/cutils.h"
 
 #if defined(CONFIG_UUID)
 #include <uuid/uuid.h>
@@ -769,8 +770,7 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
-                       &local_err);
+                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;

block/vhdx-log.c

@@ -18,6 +18,7 @@
  *
  */
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "qemu/error-report.h"

block/vhdx.c

@@ -16,6 +16,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "sysemu/block-backend.h"
@@ -1839,8 +1840,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
-                       &local_err);
+                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;

block/vmdk.c

@@ -24,13 +24,14 @@
  */
 
 #include "qemu/osdep.h"
-#include "qemu-common.h"
+#include "qapi/error.h"
 #include "block/block_int.h"
 #include "sysemu/block-backend.h"
 #include "qapi/qmp/qerror.h"
 #include "qemu/error-report.h"
 #include "qemu/module.h"
 #include "migration/migration.h"
+#include "qemu/cutils.h"
 #include <zlib.h>
 #include <glib.h>
 
@@ -1662,8 +1663,7 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
-                       &local_err);
+                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -1947,7 +1947,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
         }
 
         blk = blk_new_open(full_backing, NULL, NULL,
-                           BDRV_O_NO_BACKING | BDRV_O_CACHE_WB, errp);
+                           BDRV_O_NO_BACKING, errp);
         g_free(full_backing);
         if (blk == NULL) {
             ret = -EIO;
@@ -2019,8 +2019,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     new_blk = blk_new_open(filename, NULL, NULL,
-                           BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
-                           &local_err);
+                           BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
     if (new_blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;

block/vpc.c

@@ -23,6 +23,7 @@
  * THE SOFTWARE.
  */
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "qemu-common.h"
 #include "block/block_int.h"
 #include "sysemu/block-backend.h"
@@ -44,34 +45,34 @@ enum vhd_type {
     VHD_DIFFERENCING    = 4,
 };
 
-// Seconds since Jan 1, 2000 0:00:00 (UTC)
+/* Seconds since Jan 1, 2000 0:00:00 (UTC) */
 #define VHD_TIMESTAMP_BASE 946684800
 
 #define VHD_CHS_MAX_C   65535LL
 #define VHD_CHS_MAX_H   16
 #define VHD_CHS_MAX_S   255
 
-#define VHD_MAX_SECTORS       (65535LL * 255 * 255)
+#define VHD_MAX_SECTORS       0xff000000    /* 2040 GiB max image size */
 #define VHD_MAX_GEOMETRY      (VHD_CHS_MAX_C * VHD_CHS_MAX_H * VHD_CHS_MAX_S)
 
 #define VPC_OPT_FORCE_SIZE "force_size"
 
-// always big-endian
+/* always big-endian */
 typedef struct vhd_footer {
-    char        creator[8]; // "conectix"
+    char        creator[8]; /* "conectix" */
     uint32_t    features;
     uint32_t    version;
 
-    // Offset of next header structure, 0xFFFFFFFF if none
+    /* Offset of next header structure, 0xFFFFFFFF if none */
     uint64_t    data_offset;
 
-    // Seconds since Jan 1, 2000 0:00:00 (UTC)
+    /* Seconds since Jan 1, 2000 0:00:00 (UTC) */
     uint32_t    timestamp;
 
-    char        creator_app[4]; // "vpc "
+    char        creator_app[4]; /*  e.g., "vpc " */
     uint16_t    major;
     uint16_t    minor;
-    char        creator_os[4]; // "Wi2k"
+    char        creator_os[4]; /* "Wi2k" */
 
     uint64_t    orig_size;
     uint64_t    current_size;
@@ -82,29 +83,29 @@ typedef struct vhd_footer {
 
     uint32_t    type;
 
-    // Checksum of the Hard Disk Footer ("one's complement of the sum of all
-    // the bytes in the footer without the checksum field")
+    /* Checksum of the Hard Disk Footer ("one's complement of the sum of all
+       the bytes in the footer without the checksum field") */
     uint32_t    checksum;
 
-    // UUID used to identify a parent hard disk (backing file)
+    /* UUID used to identify a parent hard disk (backing file) */
     uint8_t     uuid[16];
 
     uint8_t     in_saved_state;
 } QEMU_PACKED VHDFooter;
 
 typedef struct vhd_dyndisk_header {
-    char        magic[8]; // "cxsparse"
+    char        magic[8]; /* "cxsparse" */
 
-    // Offset of next header structure, 0xFFFFFFFF if none
+    /* Offset of next header structure, 0xFFFFFFFF if none */
     uint64_t    data_offset;
 
-    // Offset of the Block Allocation Table (BAT)
+    /* Offset of the Block Allocation Table (BAT) */
     uint64_t    table_offset;
 
     uint32_t    version;
-    uint32_t    max_table_entries; // 32bit/entry
+    uint32_t    max_table_entries; /* 32bit/entry */
 
-    // 2 MB by default, must be a power of two
+    /* 2 MB by default, must be a power of two */
     uint32_t    block_size;
 
     uint32_t    checksum;
@@ -112,7 +113,7 @@ typedef struct vhd_dyndisk_header {
     uint32_t    parent_timestamp;
     uint32_t    reserved;
 
-    // Backing file name (in UTF-16)
+    /* Backing file name (in UTF-16) */
     uint8_t     parent_name[512];
 
     struct {
@@ -237,6 +238,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
 
     ret = bdrv_pread(bs->file->bs, 0, s->footer_buf, HEADER_SIZE);
     if (ret < 0) {
+        error_setg(errp, "Unable to read VHD header");
         goto fail;
     }
 
@@ -245,9 +247,11 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
         int64_t offset = bdrv_getlength(bs->file->bs);
         if (offset < 0) {
             ret = offset;
+            error_setg(errp, "Invalid file size");
             goto fail;
         } else if (offset < HEADER_SIZE) {
             ret = -EINVAL;
+            error_setg(errp, "File too small for a VHD header");
             goto fail;
         }
 
@@ -274,9 +278,9 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     /* Write 'checksum' back to footer, or else will leave it with zero. */
     footer->checksum = cpu_to_be32(checksum);
 
-    // The visible size of a image in Virtual PC depends on the geometry
-    // rather than on the size stored in the footer (the size in the footer
-    // is too large usually)
+    /* The visible size of a image in Virtual PC depends on the geometry
+       rather than on the size stored in the footer (the size in the footer
+       is too large usually) */
     bs->total_sectors = (int64_t)
         be16_to_cpu(footer->cyls) * footer->heads * footer->secs_per_cyl;
 
@@ -298,6 +302,8 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
      *      'qem2'  :  current_size     QEMU (uses current_size)
      *      'win '  :  current_size     Hyper-V
      *      'd2v '  :  current_size     Disk2vhd
+     *      'tap\0' :  current_size     XenServer
+     *      'CTXS'  :  current_size     XenConverter
      *
      *  The user can override the table values via drive options, however
      *  even with an override we will still use current_size for images
@@ -305,15 +311,17 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
      */
     use_chs = (!!strncmp(footer->creator_app, "win ", 4) &&
                !!strncmp(footer->creator_app, "qem2", 4) &&
-               !!strncmp(footer->creator_app, "d2v ", 4)) || s->force_use_chs;
+               !!strncmp(footer->creator_app, "d2v ", 4) &&
+               !!strncmp(footer->creator_app, "CTXS", 4) &&
+               !!memcmp(footer->creator_app, "tap", 4)) || s->force_use_chs;
 
     if (!use_chs || bs->total_sectors == VHD_MAX_GEOMETRY || s->force_use_sz) {
         bs->total_sectors = be64_to_cpu(footer->current_size) /
                                         BDRV_SECTOR_SIZE;
     }
 
-    /* Allow a maximum disk size of approximately 2 TB */
-    if (bs->total_sectors >= VHD_MAX_SECTORS) {
+    /* Allow a maximum disk size of 2040 GiB */
+    if (bs->total_sectors > VHD_MAX_SECTORS) {
         ret = -EFBIG;
         goto fail;
     }
@@ -322,12 +330,14 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
         ret = bdrv_pread(bs->file->bs, be64_to_cpu(footer->data_offset), buf,
                          HEADER_SIZE);
         if (ret < 0) {
+            error_setg(errp, "Error reading dynamic VHD header");
             goto fail;
         }
 
         dyndisk_header = (VHDDynDiskHeader *) buf;
 
         if (strncmp(dyndisk_header->magic, "cxsparse", 8)) {
+            error_setg(errp, "Invalid header magic");
             ret = -EINVAL;
             goto fail;
         }
@@ -343,16 +353,14 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
         s->max_table_entries = be32_to_cpu(dyndisk_header->max_table_entries);
 
         if ((bs->total_sectors * 512) / s->block_size > 0xffffffffU) {
-            ret = -EINVAL;
-            goto fail;
-        }
-        if (s->max_table_entries > (VHD_MAX_SECTORS * 512) / s->block_size) {
+            error_setg(errp, "Too many blocks");
             ret = -EINVAL;
             goto fail;
         }
 
         computed_size = (uint64_t) s->max_table_entries * s->block_size;
         if (computed_size < bs->total_sectors * 512) {
+            error_setg(errp, "Page table too small");
             ret = -EINVAL;
             goto fail;
         }
@@ -369,6 +377,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
 
         s->pagetable = qemu_try_blockalign(bs->file->bs, pagetable_size);
         if (s->pagetable == NULL) {
+            error_setg(errp, "Unable to allocate memory for page table");
             ret = -ENOMEM;
             goto fail;
         }
@@ -378,6 +387,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
         ret = bdrv_pread(bs->file->bs, s->bat_offset, s->pagetable,
                          pagetable_size);
         if (ret < 0) {
+            error_setg(errp, "Error reading pagetable");
             goto fail;
         }
 
@@ -456,16 +466,16 @@ static inline int64_t get_sector_offset(BlockDriverState *bs,
     pageentry_index = (offset % s->block_size) / 512;
 
     if (pagetable_index >= s->max_table_entries || s->pagetable[pagetable_index] == 0xffffffff)
-        return -1; // not allocated
+        return -1; /* not allocated */
 
     bitmap_offset = 512 * (uint64_t) s->pagetable[pagetable_index];
     block_offset = bitmap_offset + s->bitmap_size + (512 * pageentry_index);
 
-    // We must ensure that we don't write to any sectors which are marked as
-    // unused in the bitmap. We get away with setting all bits in the block
-    // bitmap each time we write to a new block. This might cause Virtual PC to
-    // miss sparse read optimization, but it's not a problem in terms of
-    // correctness.
+    /* We must ensure that we don't write to any sectors which are marked as
+       unused in the bitmap. We get away with setting all bits in the block
+       bitmap each time we write to a new block. This might cause Virtual PC to
+       miss sparse read optimization, but it's not a problem in terms of
+       correctness. */
     if (write && (s->last_bitmap_offset != bitmap_offset)) {
         uint8_t bitmap[s->bitmap_size];
 
@@ -511,18 +521,18 @@ static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
     int ret;
     uint8_t bitmap[s->bitmap_size];
 
-    // Check if sector_num is valid
+    /* Check if sector_num is valid */
     if ((sector_num < 0) || (sector_num > bs->total_sectors))
         return -1;
 
-    // Write entry into in-memory BAT
+    /* Write entry into in-memory BAT */
     index = (sector_num * 512) / s->block_size;
     if (s->pagetable[index] != 0xFFFFFFFF)
         return -1;
 
     s->pagetable[index] = s->free_data_block_offset / 512;
 
-    // Initialize the block's bitmap
+    /* Initialize the block's bitmap */
     memset(bitmap, 0xff, s->bitmap_size);
     ret = bdrv_pwrite_sync(bs->file->bs, s->free_data_block_offset, bitmap,
         s->bitmap_size);
@@ -530,13 +540,13 @@ static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
         return ret;
     }
 
-    // Write new footer (the old one will be overwritten)
+    /* Write new footer (the old one will be overwritten) */
     s->free_data_block_offset += s->block_size + s->bitmap_size;
     ret = rewrite_footer(bs);
     if (ret < 0)
         goto fail;
 
-    // Write BAT entry to disk
+    /* Write BAT entry to disk */
     bat_offset = s->bat_offset + (4 * index);
     bat_value = cpu_to_be32(s->pagetable[index]);
     ret = bdrv_pwrite_sync(bs->file->bs, bat_offset, &bat_value, 4);
@@ -717,7 +727,7 @@ static int64_t coroutine_fn vpc_co_get_block_status(BlockDriverState *bs,
  * Note that the geometry doesn't always exactly match total_sectors but
  * may round it down.
  *
- * Returns 0 on success, -EFBIG if the size is larger than ~2 TB. Override
+ * Returns 0 on success, -EFBIG if the size is larger than 2040 GiB. Override
  * the hardware EIDE and ATA-2 limit of 16 heads (max disk size of 127 GB)
  * and instead allow up to 255 heads.
  */
@@ -769,12 +779,12 @@ static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
     int ret;
     int64_t offset = 0;
 
-    // Write the footer (twice: at the beginning and at the end)
+    /* Write the footer (twice: at the beginning and at the end) */
     block_size = 0x200000;
     num_bat_entries = (total_sectors + block_size / 512) / (block_size / 512);
 
     ret = blk_pwrite(blk, offset, buf, HEADER_SIZE);
-    if (ret) {
+    if (ret < 0) {
         goto fail;
     }
 
@@ -784,7 +794,7 @@ static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
         goto fail;
     }
 
-    // Write the initial BAT
+    /* Write the initial BAT */
     offset = 3 * 512;
 
     memset(buf, 0xFF, 512);
@@ -796,7 +806,7 @@ static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
         offset += 512;
     }
 
-    // Prepare the Dynamic Disk Header
+    /* Prepare the Dynamic Disk Header */
     memset(buf, 0, 1024);
 
     memcpy(dyndisk_header->magic, "cxsparse", 8);
@@ -813,7 +823,7 @@ static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
 
     dyndisk_header->checksum = cpu_to_be32(vpc_checksum(buf, 1024));
 
-    // Write the header
+    /* Write the header */
     offset = 512;
 
     ret = blk_pwrite(blk, offset, buf, 1024);
@@ -873,6 +883,7 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
         } else if (!strcmp(disk_type_param, "fixed")) {
             disk_type = VHD_FIXED;
         } else {
+            error_setg(errp, "Invalid disk type, %s", disk_type_param);
             ret = -EINVAL;
             goto out;
         }
@@ -889,8 +900,7 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
     }
 
     blk = blk_new_open(filename, NULL, NULL,
-                       BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
-                       &local_err);
+                       BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
     if (blk == NULL) {
         error_propagate(errp, local_err);
         ret = -EIO;
@@ -922,8 +932,9 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
 
     if ((int64_t)cyls * heads * secs_per_cyl == VHD_MAX_GEOMETRY) {
         total_sectors = total_size / BDRV_SECTOR_SIZE;
-        /* Allow a maximum disk size of approximately 2 TB */
+        /* Allow a maximum disk size of 2040 GiB */
         if (total_sectors > VHD_MAX_SECTORS) {
+            error_setg(errp, "Disk size is too large, max size is 2040 GiB");
             ret = -EFBIG;
             goto out;
         }
@@ -974,6 +985,9 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
     } else {
         ret = create_fixed_disk(blk, buf, total_size);
     }
+    if (ret < 0) {
+        error_setg(errp, "Unable to create or write VHD header");
+    }
 
 out:
     blk_unref(blk);

block/vvfat.c

@@ -24,13 +24,14 @@
  */
 #include "qemu/osdep.h"
 #include <dirent.h>
-#include "qemu-common.h"
+#include "qapi/error.h"
 #include "block/block_int.h"
 #include "qemu/module.h"
 #include "migration/migration.h"
 #include "qapi/qmp/qint.h"
 #include "qapi/qmp/qbool.h"
 #include "qapi/qmp/qstring.h"
+#include "qemu/cutils.h"
 
 #ifndef S_IWGRP
 #define S_IWGRP 0
@@ -1108,6 +1109,8 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
             goto fail;
         }
         memcpy(s->volume_label, label, label_length);
+    } else {
+        memcpy(s->volume_label, "QEMU VVFAT", 10);
     }
 
     if (floppy) {
@@ -2282,12 +2285,17 @@ DLOG(fprintf(stderr, "commit_direntries for %s, parent_mapping_index %d\n", mapp
 		factor * (old_cluster_count - new_cluster_count));
 
     for (c = first_cluster; !fat_eof(s, c); c = modified_fat_get(s, c)) {
+        direntry_t *first_direntry;
 	void* direntry = array_get(&(s->directory), current_dir_index);
 	int ret = vvfat_read(s->bs, cluster2sector(s, c), direntry,
 		s->sectors_per_cluster);
 	if (ret)
 	    return ret;
-	assert(!strncmp(s->directory.pointer, "QEMU", 4));
+
+        /* The first directory entry on the filesystem is the volume name */
+        first_direntry = (direntry_t*) s->directory.pointer;
+        assert(!memcmp(first_direntry->name, s->volume_label, 11));
+
 	current_dir_index += factor;
     }
 
@@ -2956,8 +2964,7 @@ static int enable_write_target(BDRVVVFATState *s, Error **errp)
     options = qdict_new();
     qdict_put(options, "driver", qstring_from_str("qcow"));
     ret = bdrv_open(&s->qcow, s->qcow_filename, NULL, options,
-                    BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH,
-                    errp);
+                    BDRV_O_RDWR | BDRV_O_NO_FLUSH, errp);
     if (ret < 0) {
         goto err;
     }

blockdev.c

@@ -50,6 +50,8 @@
 #include "qmp-commands.h"
 #include "trace.h"
 #include "sysemu/arch_init.h"
+#include "qemu/cutils.h"
+#include "qemu/help_option.h"
 
 static QTAILQ_HEAD(, BlockDriverState) monitor_bdrv_states =
     QTAILQ_HEAD_INITIALIZER(monitor_bdrv_states);
@@ -467,6 +469,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
     int bdrv_flags = 0;
     int on_read_error, on_write_error;
     bool account_invalid, account_failed;
+    bool writethrough;
     BlockBackend *blk;
     BlockDriverState *bs;
     ThrottleConfig cfg;
@@ -478,6 +481,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
     const char *id;
     BlockdevDetectZeroesOptions detect_zeroes =
         BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF;
+    const char *blk_id;
     const char *throttling_group = NULL;
 
     /* Check common options by copying from bs_opts to opts, all other options
@@ -505,6 +509,10 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
     account_invalid = qemu_opt_get_bool(opts, "stats-account-invalid", true);
     account_failed = qemu_opt_get_bool(opts, "stats-account-failed", true);
 
+    writethrough = !qemu_opt_get_bool(opts, BDRV_OPT_CACHE_WB, true);
+
+    blk_id = qemu_opts_id(opts);
+
     qdict_extract_subqdict(bs_opts, &interval_dict, "stats-intervals.");
     qdict_array_split(interval_dict, &interval_list);
 
@@ -574,7 +582,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
 
         if (throttle_enabled(&cfg)) {
             if (!throttling_group) {
-                throttling_group = blk_name(blk);
+                throttling_group = blk_id;
             }
             blk_rs->throttle_group = g_strdup(throttling_group);
             blk_rs->throttle_state = throttle_group_incref(throttling_group);
@@ -590,9 +598,9 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
         /* bdrv_open() defaults to the values in bdrv_flags (for compatibility
          * with other callers) rather than what we want as the real defaults.
          * Apply the defaults here instead. */
-        qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_WB, "on");
         qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_DIRECT, "off");
         qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_NO_FLUSH, "off");
+        assert((bdrv_flags & BDRV_O_CACHE_MASK) == 0);
 
         if (runstate_check(RUN_STATE_INMIGRATE)) {
             bdrv_flags |= BDRV_O_INACTIVE;
@@ -609,7 +617,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
         /* disk I/O throttling */
         if (throttle_enabled(&cfg)) {
             if (!throttling_group) {
-                throttling_group = blk_name(blk);
+                throttling_group = blk_id;
             }
             bdrv_io_limits_enable(bs, throttling_group);
             bdrv_set_io_limits(bs, &cfg);
@@ -628,9 +636,10 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
         }
     }
 
+    blk_set_enable_write_cache(blk, !writethrough);
     blk_set_on_error(blk, on_read_error, on_write_error);
 
-    if (!monitor_add_blk(blk, qemu_opts_id(opts), errp)) {
+    if (!monitor_add_blk(blk, blk_id, errp)) {
         blk_unref(blk);
         blk = NULL;
         goto err_no_bs_opts;
@@ -684,7 +693,6 @@ static BlockDriverState *bds_tree_init(QDict *bs_opts, Error **errp)
     /* bdrv_open() defaults to the values in bdrv_flags (for compatibility
      * with other callers) rather than what we want as the real defaults.
      * Apply the defaults here instead. */
-    qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_WB, "on");
     qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_DIRECT, "off");
     qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_NO_FLUSH, "off");
 
@@ -892,8 +900,9 @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type)
     value = qemu_opt_get(all_opts, "cache");
     if (value) {
         int flags = 0;
+        bool writethrough;
 
-        if (bdrv_parse_cache_flags(value, &flags) != 0) {
+        if (bdrv_parse_cache_mode(value, &flags, &writethrough) != 0) {
             error_report("invalid cache option");
             return NULL;
         }
@@ -901,7 +910,7 @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type)
         /* Specific options take precedence */
         if (!qemu_opt_get(all_opts, BDRV_OPT_CACHE_WB)) {
             qemu_opt_set_bool(all_opts, BDRV_OPT_CACHE_WB,
-                              !!(flags & BDRV_O_CACHE_WB), &error_abort);
+                              !writethrough, &error_abort);
         }
         if (!qemu_opt_get(all_opts, BDRV_OPT_CACHE_DIRECT)) {
             qemu_opt_set_bool(all_opts, BDRV_OPT_CACHE_DIRECT,
@@ -1741,6 +1750,7 @@ static void external_snapshot_prepare(BlkActionState *common,
         }
 
         flags = state->old_bs->open_flags;
+        flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING | BDRV_O_COPY_ON_READ);
 
         /* create new image w/backing file */
         mode = s->has_mode ? s->mode : NEW_IMAGE_MODE_ABSOLUTE_PATHS;
@@ -1811,8 +1821,10 @@ static void external_snapshot_commit(BlkActionState *common)
     /* We don't need (or want) to use the transactional
      * bdrv_reopen_multiple() across all the entries at once, because we
      * don't want to abort all of them if one of them fails the reopen */
-    bdrv_reopen(state->old_bs, state->old_bs->open_flags & ~BDRV_O_RDWR,
-                NULL);
+    if (!state->old_bs->copy_on_read) {
+        bdrv_reopen(state->old_bs, state->old_bs->open_flags & ~BDRV_O_RDWR,
+                    NULL);
+    }
 }
 
 static void external_snapshot_abort(BlkActionState *common)
@@ -2652,6 +2664,13 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
         goto out;
     }
 
+    /* The BlockBackend must be the only parent */
+    assert(QLIST_FIRST(&bs->parents));
+    if (QLIST_NEXT(QLIST_FIRST(&bs->parents), next_parent)) {
+        error_setg(errp, "Cannot throttle device with multiple parents");
+        goto out;
+    }
+
     throttle_config_init(&cfg);
     cfg.buckets[THROTTLE_BPS_TOTAL].avg = bps;
     cfg.buckets[THROTTLE_BPS_READ].avg  = bps_rd;
@@ -2867,9 +2886,6 @@ void hmp_drive_del(Monitor *mon, const QDict *qdict)
 
     /* Make the BlockBackend and the attached BlockDriverState anonymous */
     monitor_remove_blk(blk);
-    if (blk_bs(blk)) {
-        bdrv_make_anon(blk_bs(blk));
-    }
 
     /* If this BlockBackend has a device attached to it, its refcount will be
      * decremented when the device is removed; otherwise we have to do so here.
@@ -4021,6 +4037,11 @@ void qmp_x_blockdev_del(bool has_id, const char *id,
             error_setg(errp, "Cannot find block backend %s", id);
             return;
         }
+        if (blk_legacy_dinfo(blk)) {
+            error_setg(errp, "Deleting block backend added with drive-add"
+                       " is not supported");
+            return;
+        }
         if (blk_get_refcnt(blk) > 1) {
             error_setg(errp, "Block backend %s is in use", id);
             return;
@@ -4113,6 +4134,10 @@ QemuOptsList qemu_common_drive_opts = {
             .name = "aio",
             .type = QEMU_OPT_STRING,
             .help = "host AIO implementation (threads, native)",
+        },{
+            .name = BDRV_OPT_CACHE_WB,
+            .type = QEMU_OPT_BOOL,
+            .help = "Enable writeback mode",
         },{
             .name = "format",
             .type = QEMU_OPT_STRING,

bootdevice.c

@@ -23,6 +23,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "sysemu/sysemu.h"
 #include "qapi/visitor.h"
 #include "qemu/error-report.h"

bsd-user/elfload.c

@@ -5,6 +5,7 @@
 
 #include "qemu.h"
 #include "disas/disas.h"
+#include "qemu/path.h"
 
 #ifdef _ARCH_PPC64
 #undef ARCH_DLINFO

bsd-user/main.c

@@ -21,7 +21,8 @@
 #include <sys/mman.h>
 
 #include "qemu.h"
-#include "qemu-common.h"
+#include "qemu/path.h"
+#include "qemu/help_option.h"
 /* For tb_lock */
 #include "cpu.h"
 #include "tcg.h"

bsd-user/syscall.c

@@ -17,6 +17,8 @@
  *  along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 #include "qemu/osdep.h"
+#include "qemu/cutils.h"
+#include "qemu/path.h"
 #include <sys/mman.h>
 #include <sys/syscall.h>
 #include <sys/param.h>

bsd-user/uaccess.c

@@ -1,5 +1,6 @@
 /* User memory access */
 #include "qemu/osdep.h"
+#include "qemu/cutils.h"
 
 #include "qemu.h"
 
@@ -50,7 +51,7 @@ abi_long target_strlen(abi_ulong guest_addr1)
         ptr = lock_user(VERIFY_READ, guest_addr, max_len, 1);
         if (!ptr)
             return -TARGET_EFAULT;
-        len = qemu_strnlen((char *)ptr, max_len);
+        len = qemu_strnlen((const char *)ptr, max_len);
         unlock_user(ptr, guest_addr, 0);
         guest_addr += len;
         /* we don't allow wrapping or integer overflow */

configure

@@ -298,6 +298,7 @@ coroutine=""
 coroutine_pool=""
 seccomp=""
 glusterfs=""
+glusterfs_xlator_opt="no"
 glusterfs_discard="no"
 glusterfs_zerofill="no"
 archipelago="no"
@@ -308,6 +309,7 @@ gnutls=""
 gnutls_hash=""
 gnutls_rnd=""
 nettle=""
+nettle_kdf="no"
 gcrypt=""
 gcrypt_kdf="no"
 vte=""
@@ -1871,6 +1873,9 @@ if test "$seccomp" != "no" ; then
     i386|x86_64)
         libseccomp_minver="2.1.0"
         ;;
+    mips)
+        libseccomp_minver="2.2.0"
+        ;;
     arm|aarch64)
         libseccomp_minver="2.2.3"
         ;;
@@ -2335,6 +2340,18 @@ if test "$nettle" != "no"; then
         libs_tools="$nettle_libs $libs_tools"
         QEMU_CFLAGS="$QEMU_CFLAGS $nettle_cflags"
         nettle="yes"
+
+        cat > $TMPC << EOF
+#include <stddef.h>
+#include <nettle/pbkdf2.h>
+int main(void) {
+     pbkdf2_hmac_sha256(8, NULL, 1000, 8, NULL, 8, NULL);
+     return 0;
+}
+EOF
+        if compile_prog "$nettle_cflags" "$nettle_libs" ; then
+            nettle_kdf=yes
+        fi
     else
         if test "$nettle" = "yes"; then
             feature_not_found "nettle" "Install nettle devel"
@@ -2951,7 +2968,7 @@ int main(void) {
 }
 EOF
 
-if ! compile_prog "-Werror $CFLAGS" "$LIBS" ; then
+if ! compile_prog "$CFLAGS" "$LIBS" ; then
     error_exit "sizeof(size_t) doesn't match GLIB_SIZEOF_SIZE_T."\
                "You probably need to set PKG_CONFIG_LIBDIR"\
 	       "to point to the right pkg-config files for your"\
@@ -3385,6 +3402,9 @@ if test "$glusterfs" != "no" ; then
     glusterfs="yes"
     glusterfs_cflags=`$pkg_config --cflags glusterfs-api`
     glusterfs_libs=`$pkg_config --libs glusterfs-api`
+    if $pkg_config --atleast-version=4 glusterfs-api; then
+      glusterfs_xlator_opt="yes"
+    fi
     if $pkg_config --atleast-version=5 glusterfs-api; then
       glusterfs_discard="yes"
     fi
@@ -4474,6 +4494,21 @@ if test "$fortify_source" != "no"; then
   fi
 fi
 
+##########################################
+# check if struct fsxattr is available via linux/fs.h
+
+have_fsxattr=no
+cat > $TMPC << EOF
+#include <linux/fs.h>
+struct fsxattr foo;
+int main(void) {
+  return 0;
+}
+EOF
+if compile_prog "" "" ; then
+    have_fsxattr=yes
+fi
+
 ##########################################
 # End of CC checks
 # After here, no more $cc or $ld runs
@@ -4746,6 +4781,7 @@ if test "$nettle" = "yes"; then
 else
     echo "nettle            $nettle"
 fi
+echo "nettle kdf        $nettle_kdf"
 echo "libtasn1          $tasn1"
 echo "VTE support       $vte"
 echo "curses support    $curses"
@@ -5130,6 +5166,9 @@ fi
 if test "$nettle" = "yes" ; then
   echo "CONFIG_NETTLE=y" >> $config_host_mak
   echo "CONFIG_NETTLE_VERSION_MAJOR=${nettle_version%%.*}" >> $config_host_mak
+  if test "$nettle_kdf" = "yes" ; then
+    echo "CONFIG_NETTLE_KDF=y" >> $config_host_mak
+  fi
 fi
 if test "$tasn1" = "yes" ; then
   echo "CONFIG_TASN1=y" >> $config_host_mak
@@ -5137,6 +5176,14 @@ fi
 if test "$have_ifaddrs_h" = "yes" ; then
     echo "HAVE_IFADDRS_H=y" >> $config_host_mak
 fi
+
+# Work around a system header bug with some kernel/XFS header
+# versions where they both try to define 'struct fsxattr':
+# xfs headers will not try to redefine structs from linux headers
+# if this macro is set.
+if test "$have_fsxattr" = "yes" ; then
+    echo "HAVE_FSXATTR=y" >> $config_host_mak
+fi
 if test "$vte" = "yes" ; then
   echo "CONFIG_VTE=y" >> $config_host_mak
   echo "VTE_CFLAGS=$vte_cflags" >> $config_host_mak
@@ -5323,6 +5370,10 @@ if test "$glusterfs" = "yes" ; then
   echo "GLUSTERFS_LIBS=$glusterfs_libs" >> $config_host_mak
 fi
 
+if test "$glusterfs_xlator_opt" = "yes" ; then
+  echo "CONFIG_GLUSTERFS_XLATOR_OPT=y" >> $config_host_mak
+fi
+
 if test "$glusterfs_discard" = "yes" ; then
   echo "CONFIG_GLUSTERFS_DISCARD=y" >> $config_host_mak
 fi
@@ -5942,7 +5993,7 @@ cat <<EOD >config.status
 EOD
 printf "exec" >>config.status
 printf " '%s'" "$0" "$@" >>config.status
-echo >>config.status
+echo ' "$@"' >>config.status
 chmod +x config.status
 
 rm -r "$TMPDIR1"

contrib/ivshmem-server/ivshmem-server.h

@@ -15,7 +15,7 @@
  * unix socket. For each client, the server will create some eventfd
  * (see EVENTFD(2)), one per vector. These fd are transmitted to all
  * clients using the SCM_RIGHTS cmsg message. Therefore, each client is
- * able to send a notification to another client without beeing
+ * able to send a notification to another client without being
  * "profixied" by the server.
  *
  * We use this mechanism to send interruptions between guests.

contrib/ivshmem-server/main.c

@@ -7,7 +7,8 @@
  */
 
 #include "qemu/osdep.h"
-#include "qemu-common.h"
+#include "qapi/error.h"
+#include "qemu/cutils.h"
 
 #include "ivshmem-server.h"
 

cpu-exec.c

@@ -133,10 +133,15 @@ static void init_delay_params(SyncClocks *sc, const CPUState *cpu)
 #endif /* CONFIG USER ONLY */
 
 /* Execute a TB, and fix up the CPU state afterwards if necessary */
-static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, uint8_t *tb_ptr)
+static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb)
 {
     CPUArchState *env = cpu->env_ptr;
     uintptr_t next_tb;
+    uint8_t *tb_ptr = itb->tc_ptr;
+
+    qemu_log_mask_and_addr(CPU_LOG_EXEC, itb->pc,
+                           "Trace %p [" TARGET_FMT_lx "] %s\n",
+                           itb->tc_ptr, itb->pc, lookup_symbol(itb->pc));
 
 #if defined(DEBUG_DISAS)
     if (qemu_loglevel_mask(CPU_LOG_TB_CPU)) {
@@ -167,6 +172,10 @@ static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, uint8_t *tb_ptr)
          */
         CPUClass *cc = CPU_GET_CLASS(cpu);
         TranslationBlock *tb = (TranslationBlock *)(next_tb & ~TB_EXIT_MASK);
+        qemu_log_mask_and_addr(CPU_LOG_EXEC, itb->pc,
+                               "Stopped execution of TB chain before %p ["
+                               TARGET_FMT_lx "] %s\n",
+                               itb->tc_ptr, itb->pc, lookup_symbol(itb->pc));
         if (cc->synchronize_from_tb) {
             cc->synchronize_from_tb(cpu, tb);
         } else {
@@ -202,7 +211,7 @@ static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
     cpu->current_tb = tb;
     /* execute the generated code */
     trace_exec_tb_nocache(tb, tb->pc);
-    cpu_tb_exec(cpu, tb->tc_ptr);
+    cpu_tb_exec(cpu, tb);
     cpu->current_tb = NULL;
     tb_phys_invalidate(tb, -1);
     tb_free(tb);
@@ -344,7 +353,6 @@ int cpu_exec(CPUState *cpu)
 #endif
     int ret, interrupt_request;
     TranslationBlock *tb;
-    uint8_t *tc_ptr;
     uintptr_t next_tb;
     SyncClocks sc;
 
@@ -500,10 +508,6 @@ int cpu_exec(CPUState *cpu)
                     next_tb = 0;
                     tcg_ctx.tb_ctx.tb_invalidated_flag = 0;
                 }
-                if (qemu_loglevel_mask(CPU_LOG_EXEC)) {
-                    qemu_log("Trace %p [" TARGET_FMT_lx "] %s\n",
-                             tb->tc_ptr, tb->pc, lookup_symbol(tb->pc));
-                }
                 /* see if we can patch the calling TB. When the TB
                    spans two pages, we cannot safely do a direct
                    jump. */
@@ -515,10 +519,9 @@ int cpu_exec(CPUState *cpu)
                 tb_unlock();
                 if (likely(!cpu->exit_request)) {
                     trace_exec_tb(tb, tb->pc);
-                    tc_ptr = tb->tc_ptr;
                     /* execute the generated code */
                     cpu->current_tb = tb;
-                    next_tb = cpu_tb_exec(cpu, tc_ptr);
+                    next_tb = cpu_tb_exec(cpu, tb);
                     cpu->current_tb = NULL;
                     switch (next_tb & TB_EXIT_MASK) {
                     case TB_EXIT_REQUESTED:

cpus.c

@@ -276,7 +276,7 @@ void cpu_disable_ticks(void)
    fairly approximate, so ignore small variation.
    When the guest is idle real and virtual time will be aligned in
    the IO wait loop.  */
-#define ICOUNT_WOBBLE (get_ticks_per_sec() / 10)
+#define ICOUNT_WOBBLE (NANOSECONDS_PER_SECOND / 10)
 
 static void icount_adjust(void)
 {
@@ -327,7 +327,7 @@ static void icount_adjust_vm(void *opaque)
 {
     timer_mod(icount_vm_timer,
                    qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
-                   get_ticks_per_sec() / 10);
+                   NANOSECONDS_PER_SECOND / 10);
     icount_adjust();
 }
 
@@ -338,10 +338,18 @@ static int64_t qemu_icount_round(int64_t count)
 
 static void icount_warp_rt(void)
 {
+    unsigned seq;
+    int64_t warp_start;
+
     /* The icount_warp_timer is rescheduled soon after vm_clock_warp_start
      * changes from -1 to another value, so the race here is okay.
      */
-    if (atomic_read(&vm_clock_warp_start) == -1) {
+    do {
+        seq = seqlock_read_begin(&timers_state.vm_clock_seqlock);
+        warp_start = vm_clock_warp_start;
+    } while (seqlock_read_retry(&timers_state.vm_clock_seqlock, seq));
+
+    if (warp_start == -1) {
         return;
     }
 
@@ -674,7 +682,7 @@ void configure_icount(QemuOpts *opts, Error **errp)
                                         icount_adjust_vm, NULL);
     timer_mod(icount_vm_timer,
                    qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
-                   get_ticks_per_sec() / 10);
+                   NANOSECONDS_PER_SECOND / 10);
 }
 
 /***********************************************************/

cputlb.c

@@ -30,8 +30,30 @@
 #include "exec/ram_addr.h"
 #include "tcg/tcg.h"
 
-//#define DEBUG_TLB
-//#define DEBUG_TLB_CHECK
+/* DEBUG defines, enable DEBUG_TLB_LOG to log to the CPU_LOG_MMU target */
+/* #define DEBUG_TLB */
+/* #define DEBUG_TLB_LOG */
+
+#ifdef DEBUG_TLB
+# define DEBUG_TLB_GATE 1
+# ifdef DEBUG_TLB_LOG
+#  define DEBUG_TLB_LOG_GATE 1
+# else
+#  define DEBUG_TLB_LOG_GATE 0
+# endif
+#else
+# define DEBUG_TLB_GATE 0
+# define DEBUG_TLB_LOG_GATE 0
+#endif
+
+#define tlb_debug(fmt, ...) do { \
+    if (DEBUG_TLB_LOG_GATE) { \
+        qemu_log_mask(CPU_LOG_MMU, "%s: " fmt, __func__, \
+                      ## __VA_ARGS__); \
+    } else if (DEBUG_TLB_GATE) { \
+        fprintf(stderr, "%s: " fmt, __func__, ## __VA_ARGS__); \
+    } \
+} while (0)
 
 /* statistics */
 int tlb_flush_count;
@@ -52,9 +74,8 @@ void tlb_flush(CPUState *cpu, int flush_global)
 {
     CPUArchState *env = cpu->env_ptr;
 
-#if defined(DEBUG_TLB)
-    printf("tlb_flush:\n");
-#endif
+    tlb_debug("(%d)\n", flush_global);
+
     /* must reset current TB so that interrupts cannot modify the
        links while we are modifying them */
     cpu->current_tb = NULL;
@@ -73,9 +94,7 @@ static inline void v_tlb_flush_by_mmuidx(CPUState *cpu, va_list argp)
 {
     CPUArchState *env = cpu->env_ptr;
 
-#if defined(DEBUG_TLB)
-    printf("tlb_flush_by_mmuidx:");
-#endif
+    tlb_debug("start\n");
     /* must reset current TB so that interrupts cannot modify the
        links while we are modifying them */
     cpu->current_tb = NULL;
@@ -87,18 +106,12 @@ static inline void v_tlb_flush_by_mmuidx(CPUState *cpu, va_list argp)
             break;
         }
 
-#if defined(DEBUG_TLB)
-        printf(" %d", mmu_idx);
-#endif
+        tlb_debug("%d\n", mmu_idx);
 
         memset(env->tlb_table[mmu_idx], -1, sizeof(env->tlb_table[0]));
         memset(env->tlb_v_table[mmu_idx], -1, sizeof(env->tlb_v_table[0]));
     }
 
-#if defined(DEBUG_TLB)
-    printf("\n");
-#endif
-
     memset(cpu->tb_jmp_cache, 0, sizeof(cpu->tb_jmp_cache));
 }
 
@@ -128,16 +141,14 @@ void tlb_flush_page(CPUState *cpu, target_ulong addr)
     int i;
     int mmu_idx;
 
-#if defined(DEBUG_TLB)
-    printf("tlb_flush_page: " TARGET_FMT_lx "\n", addr);
-#endif
+    tlb_debug("page :" TARGET_FMT_lx "\n", addr);
+
     /* Check if we need to flush due to large pages.  */
     if ((addr & env->tlb_flush_mask) == env->tlb_flush_addr) {
-#if defined(DEBUG_TLB)
-        printf("tlb_flush_page: forced full flush ("
-               TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
-               env->tlb_flush_addr, env->tlb_flush_mask);
-#endif
+        tlb_debug("forcing full flush ("
+                  TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
+                  env->tlb_flush_addr, env->tlb_flush_mask);
+
         tlb_flush(cpu, 1);
         return;
     }
@@ -170,16 +181,14 @@ void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong addr, ...)
 
     va_start(argp, addr);
 
-#if defined(DEBUG_TLB)
-    printf("tlb_flush_page_by_mmu_idx: " TARGET_FMT_lx, addr);
-#endif
+    tlb_debug("addr "TARGET_FMT_lx"\n", addr);
+
     /* Check if we need to flush due to large pages.  */
     if ((addr & env->tlb_flush_mask) == env->tlb_flush_addr) {
-#if defined(DEBUG_TLB)
-        printf(" forced full flush ("
-               TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
-               env->tlb_flush_addr, env->tlb_flush_mask);
-#endif
+        tlb_debug("forced full flush ("
+                  TARGET_FMT_lx "/" TARGET_FMT_lx ")\n",
+                  env->tlb_flush_addr, env->tlb_flush_mask);
+
         v_tlb_flush_by_mmuidx(cpu, argp);
         va_end(argp);
         return;
@@ -198,9 +207,7 @@ void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong addr, ...)
             break;
         }
 
-#if defined(DEBUG_TLB)
-        printf(" %d", mmu_idx);
-#endif
+        tlb_debug("idx %d\n", mmu_idx);
 
         tlb_flush_entry(&env->tlb_table[mmu_idx][i], addr);
 
@@ -211,10 +218,6 @@ void tlb_flush_page_by_mmuidx(CPUState *cpu, target_ulong addr, ...)
     }
     va_end(argp);
 
-#if defined(DEBUG_TLB)
-    printf("\n");
-#endif
-
     tb_flush_jmp_cache(cpu, addr);
 }
 
@@ -367,12 +370,9 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
     section = address_space_translate_for_iotlb(cpu, asidx, paddr, &xlat, &sz);
     assert(sz >= TARGET_PAGE_SIZE);
 
-#if defined(DEBUG_TLB)
-    qemu_log_mask(CPU_LOG_MMU,
-           "tlb_set_page: vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx
-           " prot=%x idx=%d\n",
-           vaddr, paddr, prot, mmu_idx);
-#endif
+    tlb_debug("vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx
+              " prot=%x idx=%d\n",
+              vaddr, paddr, prot, mmu_idx);
 
     address = vaddr;
     if (!memory_region_is_ram(section->mr) && !memory_region_is_romd(section->mr)) {

crypto/Makefile.objs

@@ -11,8 +11,8 @@ crypto-obj-y += secret.o
 crypto-obj-$(CONFIG_GCRYPT) += random-gcrypt.o
 crypto-obj-$(if $(CONFIG_GCRYPT),n,$(CONFIG_GNUTLS_RND)) += random-gnutls.o
 crypto-obj-y += pbkdf.o
-crypto-obj-$(CONFIG_NETTLE) += pbkdf-nettle.o
-crypto-obj-$(if $(CONFIG_NETTLE),n,$(CONFIG_GCRYPT_KDF)) += pbkdf-gcrypt.o
+crypto-obj-$(CONFIG_NETTLE_KDF) += pbkdf-nettle.o
+crypto-obj-$(if $(CONFIG_NETTLE_KDF),n,$(CONFIG_GCRYPT_KDF)) += pbkdf-gcrypt.o
 crypto-obj-y += ivgen.o
 crypto-obj-y += ivgen-essiv.o
 crypto-obj-y += ivgen-plain.o

crypto/block-luks.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 
 #include "crypto/block-luks.h"
 

crypto/block-qcow.c

@@ -25,6 +25,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 
 #include "crypto/block-qcow.h"
 #include "crypto/secret.h"

crypto/block.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "crypto/blockpriv.h"
 #include "crypto/block-qcow.h"
 #include "crypto/block-luks.h"

crypto/cipher-gcrypt.c

@@ -192,6 +192,12 @@ QCryptoCipher *qcrypto_cipher_new(QCryptoCipherAlgorithm alg,
     }
 
     if (cipher->mode == QCRYPTO_CIPHER_MODE_XTS) {
+        if (ctx->blocksize != XTS_BLOCK_SIZE) {
+            error_setg(errp,
+                       "Cipher block size %zu must equal XTS block size %d",
+                       ctx->blocksize, XTS_BLOCK_SIZE);
+            goto error;
+        }
         ctx->iv = g_new0(uint8_t, ctx->blocksize);
     }
 

crypto/cipher-nettle.c

@@ -361,6 +361,13 @@ QCryptoCipher *qcrypto_cipher_new(QCryptoCipherAlgorithm alg,
         goto error;
     }
 
+    if (mode == QCRYPTO_CIPHER_MODE_XTS &&
+        ctx->blocksize != XTS_BLOCK_SIZE) {
+        error_setg(errp, "Cipher block size %zu must equal XTS block size %d",
+                   ctx->blocksize, XTS_BLOCK_SIZE);
+        goto error;
+    }
+
     ctx->iv = g_new0(uint8_t, ctx->blocksize);
     cipher->opaque = ctx;
 
@@ -456,11 +463,6 @@ int qcrypto_cipher_decrypt(QCryptoCipher *cipher,
         break;
 
     case QCRYPTO_CIPHER_MODE_XTS:
-        if (ctx->blocksize != XTS_BLOCK_SIZE) {
-            error_setg(errp, "Block size must be %d not %zu",
-                       XTS_BLOCK_SIZE, ctx->blocksize);
-            return -1;
-        }
         xts_decrypt(ctx->ctx, ctx->ctx_tweak,
                     ctx->alg_encrypt_wrapper, ctx->alg_decrypt_wrapper,
                     ctx->iv, len, out, in);

crypto/cipher.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "crypto/cipher.h"
 
 

crypto/hash.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "crypto/hash.h"
 
 #ifdef CONFIG_GNUTLS_HASH

crypto/init.c

@@ -20,6 +20,7 @@
 
 #include "qemu/osdep.h"
 #include "crypto/init.h"
+#include "qapi/error.h"
 #include "qemu/thread.h"
 
 #ifdef CONFIG_GNUTLS

crypto/ivgen-essiv.c

@@ -19,6 +19,8 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/bswap.h"
 #include "crypto/ivgen-essiv.h"
 
 typedef struct QCryptoIVGenESSIV QCryptoIVGenESSIV;

crypto/ivgen-plain.c

@@ -19,6 +19,8 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/bswap.h"
 #include "crypto/ivgen-plain.h"
 
 static int qcrypto_ivgen_plain_init(QCryptoIVGen *ivgen,

crypto/ivgen-plain64.c

@@ -19,6 +19,8 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/bswap.h"
 #include "crypto/ivgen-plain.h"
 
 static int qcrypto_ivgen_plain_init(QCryptoIVGen *ivgen,

crypto/ivgen.c

@@ -19,6 +19,8 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
+
 #include "crypto/ivgenpriv.h"
 #include "crypto/ivgen-plain.h"
 #include "crypto/ivgen-plain64.h"

crypto/pbkdf-gcrypt.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "crypto/pbkdf.h"
 #include "gcrypt.h"
 

crypto/pbkdf-nettle.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "crypto/pbkdf.h"
 #include "nettle/pbkdf2.h"
 

crypto/pbkdf-stub.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "crypto/pbkdf.h"
 
 bool qcrypto_pbkdf2_supports(QCryptoHashAlgorithm hash G_GNUC_UNUSED)

crypto/pbkdf.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "crypto/pbkdf.h"
 #ifndef _WIN32
 #include <sys/resource.h>

crypto/secret.c

@@ -21,6 +21,7 @@
 #include "qemu/osdep.h"
 #include "crypto/secret.h"
 #include "crypto/cipher.h"
+#include "qapi/error.h"
 #include "qom/object_interfaces.h"
 #include "qemu/base64.h"
 #include "trace.h"

crypto/tlscreds.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qapi/error.h"
 #include "crypto/tlscredspriv.h"
 #include "trace.h"
 

crypto/tlscredsanon.c

@@ -21,6 +21,7 @@
 #include "qemu/osdep.h"
 #include "crypto/tlscredsanon.h"
 #include "crypto/tlscredspriv.h"
+#include "qapi/error.h"
 #include "qom/object_interfaces.h"
 #include "trace.h"