target-i386: Broadwell CPU model

This adds a new CPU model named "Broadwell". It has all the features
from Haswell, plus PREFETCHW, RDSEED, ADX, SMAP.

PREFETCHW was already supported as "3dnowprefetch".

RDSEED, ADX was added on Linux v3.15-rc1.

SMAP was added on Linux v3.15-rc2.

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Cc: Wang, Yong Y <yong.y.wang@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Dugger, Donald D <donald.d.dugger@intel.com>
Signed-off-by: Andreas Färber <afaerber@suse.de>

.gitmodules

@@ -28,3 +28,6 @@
 [submodule "dtc"]
 	path = dtc
 	url = git://git.qemu-project.org/dtc.git
+[submodule "roms/u-boot"]
+	path = roms/u-boot
+	url = git://git.qemu-project.org/u-boot.git

.travis.yml

@@ -66,16 +66,16 @@ matrix:
       compiler: gcc
     # All the trace backends (apart from dtrace)
     - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backend=stderr"
+           EXTRA_CONFIG="--enable-trace-backends=stderr"
       compiler: gcc
     - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backend=simple"
+           EXTRA_CONFIG="--enable-trace-backends=simple"
       compiler: gcc
     - env: TARGETS=i386-softmmu,x86_64-softmmu
-           EXTRA_CONFIG="--enable-trace-backend=ftrace"
+           EXTRA_CONFIG="--enable-trace-backends=ftrace"
            TEST_CMD=""
       compiler: gcc
     - env: TARGETS=i386-softmmu,x86_64-softmmu
           EXTRA_PKGS="liblttng-ust-dev liburcu-dev"
-          EXTRA_CONFIG="--enable-trace-backend=ust"
+          EXTRA_CONFIG="--enable-trace-backends=ust"
       compiler: gcc

MAINTAINERS

@@ -176,6 +176,11 @@ M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: target-arm/kvm.c
 
+MIPS
+M: James Hogan <james.hogan@imgtec.com>
+S: Maintained
+F: target-mips/kvm.c
+
 PPC
 M: Alexander Graf <agraf@suse.de>
 S: Maintained
@@ -726,6 +731,16 @@ S: Odd Fixes
 F: gdbstub*
 F: gdb-xml/
 
+Memory API
+M: Paolo Bonzini <pbonzini@redhat.com>
+S: Supported
+F: include/exec/ioport.h
+F: ioport.c
+F: include/exec/memory.h
+F: memory.c
+F: include/exec/memory-internal.h
+F: exec.c
+
 SPICE
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Supported

Makefile

@@ -45,19 +45,19 @@ endif
 endif
 
 GENERATED_HEADERS = config-host.h qemu-options.def
-GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h
-GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c
+GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h qapi-event.h
+GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c qapi-event.c
 
 GENERATED_HEADERS += trace/generated-events.h
 GENERATED_SOURCES += trace/generated-events.c
 
 GENERATED_HEADERS += trace/generated-tracers.h
-ifeq ($(TRACE_BACKEND),dtrace)
+ifeq ($(findstring dtrace,$(TRACE_BACKENDS)),dtrace)
 GENERATED_HEADERS += trace/generated-tracers-dtrace.h
 endif
 GENERATED_SOURCES += trace/generated-tracers.c
 
-ifeq ($(TRACE_BACKEND),ust)
+ifeq ($(findstring ust,$(TRACE_BACKENDS)),ust)
 GENERATED_HEADERS += trace/generated-ust-provider.h
 GENERATED_SOURCES += trace/generated-ust.c
 endif
@@ -202,7 +202,7 @@ Makefile: $(version-obj-y) $(version-lobj-y)
 # Build libraries
 
 libqemustub.a: $(stub-obj-y)
-libqemuutil.a: $(util-obj-y) qapi-types.o qapi-visit.o
+libqemuutil.a: $(util-obj-y) qapi-types.o qapi-visit.o qapi-event.o
 
 block-modules = $(foreach o,$(block-obj-m),"$(basename $(subst /,-,$o))",) NULL
 util/module.o-cflags = -D'CONFIG_BLOCK_MODULES=$(block-modules)'
@@ -246,18 +246,27 @@ $(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
 		$(gen-out-type) -o qga/qapi-generated -p "qga-" -i $<, \
 		"  GEN   $@")
 
+qapi-modules = $(SRC_PATH)/qapi-schema.json $(SRC_PATH)/qapi/common.json \
+               $(SRC_PATH)/qapi/block.json $(SRC_PATH)/qapi/block-core.json \
+               $(SRC_PATH)/qapi-event.json
+
 qapi-types.c qapi-types.h :\
-$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
+$(qapi-modules) $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py \
 		$(gen-out-type) -o "." -b -i $<, \
 		"  GEN   $@")
 qapi-visit.c qapi-visit.h :\
-$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
+$(qapi-modules) $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py \
 		$(gen-out-type) -o "." -b -i $<, \
 		"  GEN   $@")
+qapi-event.c qapi-event.h :\
+$(qapi-modules) $(SRC_PATH)/scripts/qapi-event.py $(qapi-py)
+	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-event.py \
+		$(gen-out-type) -o "." -b -i $<, \
+		"  GEN   $@")
 qmp-commands.h qmp-marshal.c :\
-$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
+$(qapi-modules) $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
 	$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py \
 		$(gen-out-type) -o "." -m -i $<, \
 		"  GEN   $@")
@@ -376,12 +385,8 @@ install-sysconfig: install-datadir install-confdir
 
 install: all $(if $(BUILD_DOCS),install-doc) install-sysconfig \
 install-datadir install-localstatedir
-	$(INSTALL_DIR) "$(DESTDIR)$(bindir)"
 ifneq ($(TOOLS),)
-	$(INSTALL_PROG) $(TOOLS) "$(DESTDIR)$(bindir)"
-ifneq ($(STRIP),)
-	$(STRIP) $(TOOLS:%="$(DESTDIR)$(bindir)/%")
-endif
+	$(call install-prog,$(TOOLS),$(DESTDIR)$(bindir))
 endif
 ifneq ($(CONFIG_MODULES),)
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_moddir)"
@@ -392,11 +397,7 @@ ifneq ($(CONFIG_MODULES),)
 	done
 endif
 ifneq ($(HELPERS-y),)
-	$(INSTALL_DIR) "$(DESTDIR)$(libexecdir)"
-	$(INSTALL_PROG) $(HELPERS-y) "$(DESTDIR)$(libexecdir)"
-ifneq ($(STRIP),)
-	$(STRIP) $(HELPERS-y:%="$(DESTDIR)$(libexecdir)/%")
-endif
+	$(call install-prog,$(HELPERS-y),$(DESTDIR)$(libexecdir))
 endif
 ifneq ($(BLOBS),)
 	set -e; for x in $(BLOBS); do \

Makefile.objs

@@ -12,7 +12,7 @@ block-obj-y += main-loop.o iohandler.o qemu-timer.o
 block-obj-$(CONFIG_POSIX) += aio-posix.o
 block-obj-$(CONFIG_WIN32) += aio-win32.o
 block-obj-y += block/
-block-obj-y += qapi-types.o qapi-visit.o
+block-obj-y += qapi-types.o qapi-visit.o qapi-event.o
 block-obj-y += qemu-io-cmds.o
 
 block-obj-y += qemu-coroutine.o qemu-coroutine-lock.o qemu-coroutine-io.o

Makefile.target

@@ -49,7 +49,7 @@ endif
 $(QEMU_PROG).stp-installed: $(SRC_PATH)/trace-events
 	$(call quiet-command,$(TRACETOOL) \
 		--format=stap \
-		--backend=$(TRACE_BACKEND) \
+		--backends=$(TRACE_BACKENDS) \
 		--binary=$(bindir)/$(QEMU_PROG) \
 		--target-name=$(TARGET_NAME) \
 		--target-type=$(TARGET_TYPE) \
@@ -58,7 +58,7 @@ $(QEMU_PROG).stp-installed: $(SRC_PATH)/trace-events
 $(QEMU_PROG).stp: $(SRC_PATH)/trace-events
 	$(call quiet-command,$(TRACETOOL) \
 		--format=stap \
-		--backend=$(TRACE_BACKEND) \
+		--backends=$(TRACE_BACKENDS) \
 		--binary=$(realpath .)/$(QEMU_PROG) \
 		--target-name=$(TARGET_NAME) \
 		--target-type=$(TARGET_TYPE) \
@@ -85,6 +85,12 @@ obj-y += disas.o
 obj-$(call notempty,$(TARGET_XML_FILES)) += gdbstub-xml.o
 obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o
 
+obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decContext.o
+obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decNumber.o
+obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal32.o
+obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal64.o
+obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal128.o
+
 #########################################################
 # Linux user emulator target
 
@@ -102,7 +108,8 @@ endif #CONFIG_LINUX_USER
 
 ifdef CONFIG_BSD_USER
 
-QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR)
+QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR) \
+			 -I$(SRC_PATH)/bsd-user/$(HOST_VARIANT_DIR)
 
 obj-y += bsd-user/
 obj-y += gdbstub.o user-exec.o
@@ -112,7 +119,7 @@ endif #CONFIG_BSD_USER
 #########################################################
 # System emulator target
 ifdef CONFIG_SOFTMMU
-obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o
+obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o numa.o
 obj-y += qtest.o
 obj-y += hw/
 obj-$(CONFIG_FDT) += device_tree.o
@@ -183,10 +190,7 @@ endif
 
 install: all
 ifneq ($(PROGS),)
-	$(INSTALL_PROG) $(PROGS) "$(DESTDIR)$(bindir)"
-ifneq ($(STRIP),)
-	$(STRIP) $(PROGS:%="$(DESTDIR)$(bindir)/%")
-endif
+	$(call install-prog,$(PROGS),$(DESTDIR)$(bindir))
 endif
 ifdef CONFIG_TRACE_SYSTEMTAP
 	$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset"

arch_init.c

@@ -739,7 +739,6 @@ static void migration_end(void)
     XBZRLE_cache_lock();
     if (XBZRLE.cache) {
         cache_fini(XBZRLE.cache);
-        g_free(XBZRLE.cache);
         g_free(XBZRLE.encoded_buf);
         g_free(XBZRLE.current_buf);
         XBZRLE.cache = NULL;
@@ -1041,17 +1040,15 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
 {
     ram_addr_t addr;
     int flags, ret = 0;
-    int error;
     static uint64_t seq_iter;
 
     seq_iter++;
 
     if (version_id != 4) {
         ret = -EINVAL;
-        goto done;
     }
 
-    do {
+    while (!ret) {
         addr = qemu_get_be64(f);
 
         flags = addr & ~TARGET_PAGE_MASK;
@@ -1079,7 +1076,6 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                                          " in != " RAM_ADDR_FMT, id, length,
                                          block->length);
                             ret =  -EINVAL;
-                            goto done;
                         }
                         break;
                     }
@@ -1089,21 +1085,22 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                     error_report("Unknown ramblock \"%s\", cannot "
                                  "accept migration", id);
                     ret = -EINVAL;
-                    goto done;
+                }
+                if (ret) {
+                    break;
                 }
 
                 total_ram_bytes -= length;
             }
-        }
-
-        if (flags & RAM_SAVE_FLAG_COMPRESS) {
+        } else if (flags & RAM_SAVE_FLAG_COMPRESS) {
             void *host;
             uint8_t ch;
 
             host = host_from_stream_offset(f, addr, flags);
             if (!host) {
+                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                 ret = -EINVAL;
-                goto done;
+                break;
             }
 
             ch = qemu_get_byte(f);
@@ -1113,33 +1110,39 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
 
             host = host_from_stream_offset(f, addr, flags);
             if (!host) {
+                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                 ret = -EINVAL;
-                goto done;
+                break;
             }
 
             qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
         } else if (flags & RAM_SAVE_FLAG_XBZRLE) {
             void *host = host_from_stream_offset(f, addr, flags);
             if (!host) {
+                error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
                 ret = -EINVAL;
-                goto done;
+                break;
             }
 
             if (load_xbzrle(f, addr, host) < 0) {
+                error_report("Failed to decompress XBZRLE page at "
+                             RAM_ADDR_FMT, addr);
                 ret = -EINVAL;
-                goto done;
+                break;
             }
         } else if (flags & RAM_SAVE_FLAG_HOOK) {
             ram_control_load_hook(f, flags);
+        } else if (flags & RAM_SAVE_FLAG_EOS) {
+            /* normal exit */
+            break;
+        } else {
+            error_report("Unknown migration flags: %#x", flags);
+            ret = -EINVAL;
+            break;
         }
-        error = qemu_file_get_error(f);
-        if (error) {
-            ret = error;
-            goto done;
-        }
-    } while (!(flags & RAM_SAVE_FLAG_EOS));
+        ret = qemu_file_get_error(f);
+    }
 
-done:
     DPRINTF("Completed load of VM with exit code %d seq iteration "
             "%" PRIu64 "\n", ret, seq_iter);
     return ret;

async.c

@@ -117,15 +117,21 @@ void qemu_bh_schedule_idle(QEMUBH *bh)
 
 void qemu_bh_schedule(QEMUBH *bh)
 {
+    AioContext *ctx;
+
     if (bh->scheduled)
         return;
+    ctx = bh->ctx;
     bh->idle = 0;
-    /* Make sure that idle & any writes needed by the callback are done
-     * before the locations are read in the aio_bh_poll.
+    /* Make sure that:
+     * 1. idle & any writes needed by the callback are done before the
+     *    locations are read in the aio_bh_poll.
+     * 2. ctx is loaded before scheduled is set and the callback has a chance
+     *    to execute.
      */
-    smp_wmb();
+    smp_mb();
     bh->scheduled = 1;
-    aio_notify(bh->ctx);
+    aio_notify(ctx);
 }
 
 

audio/alsaaudio.c

@@ -815,10 +815,8 @@ static void alsa_fini_out (HWVoiceOut *hw)
     ldebug ("alsa_fini\n");
     alsa_anal_close (&alsa->handle, &alsa->pollhlp);
 
-    if (alsa->pcm_buf) {
-        g_free (alsa->pcm_buf);
-        alsa->pcm_buf = NULL;
-    }
+    g_free(alsa->pcm_buf);
+    alsa->pcm_buf = NULL;
 }
 
 static int alsa_init_out (HWVoiceOut *hw, struct audsettings *as)
@@ -978,10 +976,8 @@ static void alsa_fini_in (HWVoiceIn *hw)
 
     alsa_anal_close (&alsa->handle, &alsa->pollhlp);
 
-    if (alsa->pcm_buf) {
-        g_free (alsa->pcm_buf);
-        alsa->pcm_buf = NULL;
-    }
+    g_free(alsa->pcm_buf);
+    alsa->pcm_buf = NULL;
 }
 
 static int alsa_run_in (HWVoiceIn *hw)

audio/audio_template.h

@@ -71,10 +71,7 @@ static void glue (audio_init_nb_voices_, TYPE) (struct audio_driver *drv)
 
 static void glue (audio_pcm_hw_free_resources_, TYPE) (HW *hw)
 {
-    if (HWBUF) {
-        g_free (HWBUF);
-    }
-
+    g_free (HWBUF);
     HWBUF = NULL;
 }
 
@@ -92,9 +89,7 @@ static int glue (audio_pcm_hw_alloc_resources_, TYPE) (HW *hw)
 
 static void glue (audio_pcm_sw_free_resources_, TYPE) (SW *sw)
 {
-    if (sw->buf) {
-        g_free (sw->buf);
-    }
+    g_free (sw->buf);
 
     if (sw->rate) {
         st_rate_stop (sw->rate);
@@ -172,10 +167,8 @@ static int glue (audio_pcm_sw_init_, TYPE) (
 static void glue (audio_pcm_sw_fini_, TYPE) (SW *sw)
 {
     glue (audio_pcm_sw_free_resources_, TYPE) (sw);
-    if (sw->name) {
-        g_free (sw->name);
-        sw->name = NULL;
-    }
+    g_free (sw->name);
+    sw->name = NULL;
 }
 
 static void glue (audio_pcm_hw_add_sw_, TYPE) (HW *hw, SW *sw)

audio/ossaudio.c

@@ -736,10 +736,8 @@ static void oss_fini_in (HWVoiceIn *hw)
 
     oss_anal_close (&oss->fd);
 
-    if (oss->pcm_buf) {
-        g_free (oss->pcm_buf);
-        oss->pcm_buf = NULL;
-    }
+    g_free(oss->pcm_buf);
+    oss->pcm_buf = NULL;
 }
 
 static int oss_run_in (HWVoiceIn *hw)

backends/Makefile.objs

@@ -6,3 +6,6 @@ common-obj-$(CONFIG_BRLAPI) += baum.o
 baum.o-cflags := $(SDL_CFLAGS)
 
 common-obj-$(CONFIG_TPM) += tpm.o
+
+common-obj-y += hostmem.o hostmem-ram.o
+common-obj-$(CONFIG_LINUX) += hostmem-file.o

backends/baum.c

@@ -574,7 +574,7 @@ CharDriverState *chr_baum_init(void)
     int tty;
 
     baum = g_malloc0(sizeof(BaumDriverState));
-    baum->chr = chr = g_malloc0(sizeof(CharDriverState));
+    baum->chr = chr = qemu_chr_alloc();
 
     chr->opaque = baum;
     chr->chr_write = baum_write;

backends/hostmem-file.c

@@ -0,0 +1,134 @@
+/*
+ * QEMU Host Memory Backend for hugetlbfs
+ *
+ * Copyright (C) 2013-2014 Red Hat Inc
+ *
+ * Authors:
+ *   Paolo Bonzini <pbonzini@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#include "qemu-common.h"
+#include "sysemu/hostmem.h"
+#include "sysemu/sysemu.h"
+#include "qom/object_interfaces.h"
+
+/* hostmem-file.c */
+/**
+ * @TYPE_MEMORY_BACKEND_FILE:
+ * name of backend that uses mmap on a file descriptor
+ */
+#define TYPE_MEMORY_BACKEND_FILE "memory-backend-file"
+
+#define MEMORY_BACKEND_FILE(obj) \
+    OBJECT_CHECK(HostMemoryBackendFile, (obj), TYPE_MEMORY_BACKEND_FILE)
+
+typedef struct HostMemoryBackendFile HostMemoryBackendFile;
+
+struct HostMemoryBackendFile {
+    HostMemoryBackend parent_obj;
+
+    bool share;
+    char *mem_path;
+};
+
+static void
+file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
+{
+    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(backend);
+
+    if (!backend->size) {
+        error_setg(errp, "can't create backend with size 0");
+        return;
+    }
+    if (!fb->mem_path) {
+        error_setg(errp, "mem_path property not set");
+        return;
+    }
+#ifndef CONFIG_LINUX
+    error_setg(errp, "-mem-path not supported on this host");
+#else
+    if (!memory_region_size(&backend->mr)) {
+        backend->force_prealloc = mem_prealloc;
+        memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
+                                 object_get_canonical_path(OBJECT(backend)),
+                                 backend->size, fb->share,
+                                 fb->mem_path, errp);
+    }
+#endif
+}
+
+static void
+file_backend_class_init(ObjectClass *oc, void *data)
+{
+    HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
+
+    bc->alloc = file_backend_memory_alloc;
+}
+
+static char *get_mem_path(Object *o, Error **errp)
+{
+    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
+
+    return g_strdup(fb->mem_path);
+}
+
+static void set_mem_path(Object *o, const char *str, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(o);
+    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
+
+    if (memory_region_size(&backend->mr)) {
+        error_setg(errp, "cannot change property value");
+        return;
+    }
+    if (fb->mem_path) {
+        g_free(fb->mem_path);
+    }
+    fb->mem_path = g_strdup(str);
+}
+
+static bool file_memory_backend_get_share(Object *o, Error **errp)
+{
+    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
+
+    return fb->share;
+}
+
+static void file_memory_backend_set_share(Object *o, bool value, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(o);
+    HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
+
+    if (memory_region_size(&backend->mr)) {
+        error_setg(errp, "cannot change property value");
+        return;
+    }
+    fb->share = value;
+}
+
+static void
+file_backend_instance_init(Object *o)
+{
+    object_property_add_bool(o, "share",
+                        file_memory_backend_get_share,
+                        file_memory_backend_set_share, NULL);
+    object_property_add_str(o, "mem-path", get_mem_path,
+                            set_mem_path, NULL);
+}
+
+static const TypeInfo file_backend_info = {
+    .name = TYPE_MEMORY_BACKEND_FILE,
+    .parent = TYPE_MEMORY_BACKEND,
+    .class_init = file_backend_class_init,
+    .instance_init = file_backend_instance_init,
+    .instance_size = sizeof(HostMemoryBackendFile),
+};
+
+static void register_types(void)
+{
+    type_register_static(&file_backend_info);
+}
+
+type_init(register_types);

backends/hostmem-ram.c

@@ -0,0 +1,53 @@
+/*
+ * QEMU Host Memory Backend
+ *
+ * Copyright (C) 2013-2014 Red Hat Inc
+ *
+ * Authors:
+ *   Igor Mammedov <imammedo@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#include "sysemu/hostmem.h"
+#include "qom/object_interfaces.h"
+
+#define TYPE_MEMORY_BACKEND_RAM "memory-backend-ram"
+
+
+static void
+ram_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
+{
+    char *path;
+
+    if (!backend->size) {
+        error_setg(errp, "can't create backend with size 0");
+        return;
+    }
+
+    path = object_get_canonical_path_component(OBJECT(backend));
+    memory_region_init_ram(&backend->mr, OBJECT(backend), path,
+                           backend->size);
+    g_free(path);
+}
+
+static void
+ram_backend_class_init(ObjectClass *oc, void *data)
+{
+    HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
+
+    bc->alloc = ram_backend_memory_alloc;
+}
+
+static const TypeInfo ram_backend_info = {
+    .name = TYPE_MEMORY_BACKEND_RAM,
+    .parent = TYPE_MEMORY_BACKEND,
+    .class_init = ram_backend_class_init,
+};
+
+static void register_types(void)
+{
+    type_register_static(&ram_backend_info);
+}
+
+type_init(register_types);

backends/hostmem.c

@@ -0,0 +1,375 @@
+/*
+ * QEMU Host Memory Backend
+ *
+ * Copyright (C) 2013-2014 Red Hat Inc
+ *
+ * Authors:
+ *   Igor Mammedov <imammedo@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+#include "sysemu/hostmem.h"
+#include "qapi/visitor.h"
+#include "qapi-types.h"
+#include "qapi-visit.h"
+#include "qapi/qmp/qerror.h"
+#include "qemu/config-file.h"
+#include "qom/object_interfaces.h"
+
+#ifdef CONFIG_NUMA
+#include <numaif.h>
+QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_DEFAULT != MPOL_DEFAULT);
+QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_PREFERRED != MPOL_PREFERRED);
+QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_BIND != MPOL_BIND);
+QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_INTERLEAVE != MPOL_INTERLEAVE);
+#endif
+
+static void
+host_memory_backend_get_size(Object *obj, Visitor *v, void *opaque,
+                             const char *name, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    uint64_t value = backend->size;
+
+    visit_type_size(v, &value, name, errp);
+}
+
+static void
+host_memory_backend_set_size(Object *obj, Visitor *v, void *opaque,
+                             const char *name, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    Error *local_err = NULL;
+    uint64_t value;
+
+    if (memory_region_size(&backend->mr)) {
+        error_setg(&local_err, "cannot change property value");
+        goto out;
+    }
+
+    visit_type_size(v, &value, name, &local_err);
+    if (local_err) {
+        goto out;
+    }
+    if (!value) {
+        error_setg(&local_err, "Property '%s.%s' doesn't take value '%"
+                   PRIu64 "'", object_get_typename(obj), name, value);
+        goto out;
+    }
+    backend->size = value;
+out:
+    error_propagate(errp, local_err);
+}
+
+static void
+host_memory_backend_get_host_nodes(Object *obj, Visitor *v, void *opaque,
+                                   const char *name, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    uint16List *host_nodes = NULL;
+    uint16List **node = &host_nodes;
+    unsigned long value;
+
+    value = find_first_bit(backend->host_nodes, MAX_NODES);
+    if (value == MAX_NODES) {
+        return;
+    }
+
+    *node = g_malloc0(sizeof(**node));
+    (*node)->value = value;
+    node = &(*node)->next;
+
+    do {
+        value = find_next_bit(backend->host_nodes, MAX_NODES, value + 1);
+        if (value == MAX_NODES) {
+            break;
+        }
+
+        *node = g_malloc0(sizeof(**node));
+        (*node)->value = value;
+        node = &(*node)->next;
+    } while (true);
+
+    visit_type_uint16List(v, &host_nodes, name, errp);
+}
+
+static void
+host_memory_backend_set_host_nodes(Object *obj, Visitor *v, void *opaque,
+                                   const char *name, Error **errp)
+{
+#ifdef CONFIG_NUMA
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    uint16List *l = NULL;
+
+    visit_type_uint16List(v, &l, name, errp);
+
+    while (l) {
+        bitmap_set(backend->host_nodes, l->value, 1);
+        l = l->next;
+    }
+#else
+    error_setg(errp, "NUMA node binding are not supported by this QEMU");
+#endif
+}
+
+static void
+host_memory_backend_get_policy(Object *obj, Visitor *v, void *opaque,
+                               const char *name, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    int policy = backend->policy;
+
+    visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
+}
+
+static void
+host_memory_backend_set_policy(Object *obj, Visitor *v, void *opaque,
+                               const char *name, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+    int policy;
+
+    visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
+    backend->policy = policy;
+
+#ifndef CONFIG_NUMA
+    if (policy != HOST_MEM_POLICY_DEFAULT) {
+        error_setg(errp, "NUMA policies are not supported by this QEMU");
+    }
+#endif
+}
+
+static bool host_memory_backend_get_merge(Object *obj, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+
+    return backend->merge;
+}
+
+static void host_memory_backend_set_merge(Object *obj, bool value, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+
+    if (!memory_region_size(&backend->mr)) {
+        backend->merge = value;
+        return;
+    }
+
+    if (value != backend->merge) {
+        void *ptr = memory_region_get_ram_ptr(&backend->mr);
+        uint64_t sz = memory_region_size(&backend->mr);
+
+        qemu_madvise(ptr, sz,
+                     value ? QEMU_MADV_MERGEABLE : QEMU_MADV_UNMERGEABLE);
+        backend->merge = value;
+    }
+}
+
+static bool host_memory_backend_get_dump(Object *obj, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+
+    return backend->dump;
+}
+
+static void host_memory_backend_set_dump(Object *obj, bool value, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+
+    if (!memory_region_size(&backend->mr)) {
+        backend->dump = value;
+        return;
+    }
+
+    if (value != backend->dump) {
+        void *ptr = memory_region_get_ram_ptr(&backend->mr);
+        uint64_t sz = memory_region_size(&backend->mr);
+
+        qemu_madvise(ptr, sz,
+                     value ? QEMU_MADV_DODUMP : QEMU_MADV_DONTDUMP);
+        backend->dump = value;
+    }
+}
+
+static bool host_memory_backend_get_prealloc(Object *obj, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+
+    return backend->prealloc || backend->force_prealloc;
+}
+
+static void host_memory_backend_set_prealloc(Object *obj, bool value,
+                                             Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+
+    if (backend->force_prealloc) {
+        if (value) {
+            error_setg(errp,
+                       "remove -mem-prealloc to use the prealloc property");
+            return;
+        }
+    }
+
+    if (!memory_region_size(&backend->mr)) {
+        backend->prealloc = value;
+        return;
+    }
+
+    if (value && !backend->prealloc) {
+        int fd = memory_region_get_fd(&backend->mr);
+        void *ptr = memory_region_get_ram_ptr(&backend->mr);
+        uint64_t sz = memory_region_size(&backend->mr);
+
+        os_mem_prealloc(fd, ptr, sz);
+        backend->prealloc = true;
+    }
+}
+
+static void host_memory_backend_init(Object *obj)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+
+    backend->merge = qemu_opt_get_bool(qemu_get_machine_opts(),
+                                       "mem-merge", true);
+    backend->dump = qemu_opt_get_bool(qemu_get_machine_opts(),
+                                      "dump-guest-core", true);
+    backend->prealloc = mem_prealloc;
+
+    object_property_add_bool(obj, "merge",
+                        host_memory_backend_get_merge,
+                        host_memory_backend_set_merge, NULL);
+    object_property_add_bool(obj, "dump",
+                        host_memory_backend_get_dump,
+                        host_memory_backend_set_dump, NULL);
+    object_property_add_bool(obj, "prealloc",
+                        host_memory_backend_get_prealloc,
+                        host_memory_backend_set_prealloc, NULL);
+    object_property_add(obj, "size", "int",
+                        host_memory_backend_get_size,
+                        host_memory_backend_set_size, NULL, NULL, NULL);
+    object_property_add(obj, "host-nodes", "int",
+                        host_memory_backend_get_host_nodes,
+                        host_memory_backend_set_host_nodes, NULL, NULL, NULL);
+    object_property_add(obj, "policy", "str",
+                        host_memory_backend_get_policy,
+                        host_memory_backend_set_policy, NULL, NULL, NULL);
+}
+
+static void host_memory_backend_finalize(Object *obj)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+
+    if (memory_region_size(&backend->mr)) {
+        memory_region_destroy(&backend->mr);
+    }
+}
+
+MemoryRegion *
+host_memory_backend_get_memory(HostMemoryBackend *backend, Error **errp)
+{
+    return memory_region_size(&backend->mr) ? &backend->mr : NULL;
+}
+
+static void
+host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
+{
+    HostMemoryBackend *backend = MEMORY_BACKEND(uc);
+    HostMemoryBackendClass *bc = MEMORY_BACKEND_GET_CLASS(uc);
+    Error *local_err = NULL;
+    void *ptr;
+    uint64_t sz;
+
+    if (bc->alloc) {
+        bc->alloc(backend, &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            return;
+        }
+
+        ptr = memory_region_get_ram_ptr(&backend->mr);
+        sz = memory_region_size(&backend->mr);
+
+        if (backend->merge) {
+            qemu_madvise(ptr, sz, QEMU_MADV_MERGEABLE);
+        }
+        if (!backend->dump) {
+            qemu_madvise(ptr, sz, QEMU_MADV_DONTDUMP);
+        }
+#ifdef CONFIG_NUMA
+        unsigned long lastbit = find_last_bit(backend->host_nodes, MAX_NODES);
+        /* lastbit == MAX_NODES means maxnode = 0 */
+        unsigned long maxnode = (lastbit + 1) % (MAX_NODES + 1);
+        /* ensure policy won't be ignored in case memory is preallocated
+         * before mbind(). note: MPOL_MF_STRICT is ignored on hugepages so
+         * this doesn't catch hugepage case. */
+        unsigned flags = MPOL_MF_STRICT;
+
+        /* check for invalid host-nodes and policies and give more verbose
+         * error messages than mbind(). */
+        if (maxnode && backend->policy == MPOL_DEFAULT) {
+            error_setg(errp, "host-nodes must be empty for policy default,"
+                       " or you should explicitly specify a policy other"
+                       " than default");
+            return;
+        } else if (maxnode == 0 && backend->policy != MPOL_DEFAULT) {
+            error_setg(errp, "host-nodes must be set for policy %s",
+                       HostMemPolicy_lookup[backend->policy]);
+            return;
+        }
+
+        /* We can have up to MAX_NODES nodes, but we need to pass maxnode+1
+         * as argument to mbind() due to an old Linux bug (feature?) which
+         * cuts off the last specified node. This means backend->host_nodes
+         * must have MAX_NODES+1 bits available.
+         */
+        assert(sizeof(backend->host_nodes) >=
+               BITS_TO_LONGS(MAX_NODES + 1) * sizeof(unsigned long));
+        assert(maxnode <= MAX_NODES);
+        if (mbind(ptr, sz, backend->policy,
+                  maxnode ? backend->host_nodes : NULL, maxnode + 1, flags)) {
+            error_setg_errno(errp, errno,
+                             "cannot bind memory to host NUMA nodes");
+            return;
+        }
+#endif
+        /* Preallocate memory after the NUMA policy has been instantiated.
+         * This is necessary to guarantee memory is allocated with
+         * specified NUMA policy in place.
+         */
+        if (backend->prealloc) {
+            os_mem_prealloc(memory_region_get_fd(&backend->mr), ptr, sz);
+        }
+    }
+}
+
+static void
+host_memory_backend_class_init(ObjectClass *oc, void *data)
+{
+    UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
+
+    ucc->complete = host_memory_backend_memory_complete;
+}
+
+static const TypeInfo host_memory_backend_info = {
+    .name = TYPE_MEMORY_BACKEND,
+    .parent = TYPE_OBJECT,
+    .abstract = true,
+    .class_size = sizeof(HostMemoryBackendClass),
+    .class_init = host_memory_backend_class_init,
+    .instance_size = sizeof(HostMemoryBackend),
+    .instance_init = host_memory_backend_init,
+    .instance_finalize = host_memory_backend_finalize,
+    .interfaces = (InterfaceInfo[]) {
+        { TYPE_USER_CREATABLE },
+        { }
+    }
+};
+
+static void register_types(void)
+{
+    type_register_static(&host_memory_backend_info);
+}
+
+type_init(register_types);

backends/msmouse.c

@@ -67,7 +67,7 @@ CharDriverState *qemu_chr_open_msmouse(void)
 {
     CharDriverState *chr;
 
-    chr = g_malloc0(sizeof(CharDriverState));
+    chr = qemu_chr_alloc();
     chr->chr_write = msmouse_chr_write;
     chr->chr_close = msmouse_chr_close;
     chr->explicit_be_open = true;

backends/rng-random.c

@@ -106,10 +106,7 @@ static void rng_random_set_filename(Object *obj, const char *filename,
         return;
     }
 
-    if (s->filename) {
-        g_free(s->filename);
-    }
-
+    g_free(s->filename);
     s->filename = g_strdup(filename);
 }
 

balloon.c

@@ -81,19 +81,6 @@ static int qemu_balloon_status(BalloonInfo *info)
     return 1;
 }
 
-void qemu_balloon_changed(int64_t actual)
-{
-    QObject *data;
-
-    data = qobject_from_jsonf("{ 'actual': %" PRId64 " }",
-                              actual);
-
-    monitor_protocol_event(QEVENT_BALLOON_CHANGE, data);
-
-    qobject_decref(data);
-}
-
-
 BalloonInfo *qmp_query_balloon(Error **errp)
 {
     BalloonInfo *info;

block-migration.c

@@ -629,6 +629,7 @@ static int block_save_setup(QEMUFile *f, void *opaque)
             block_mig_state.submitted, block_mig_state.transferred);
 
     qemu_mutex_lock_iothread();
+    init_blk_migration(f);
 
     /* start track dirty blocks */
     ret = set_dirty_tracking();
@@ -638,8 +639,6 @@ static int block_save_setup(QEMUFile *f, void *opaque)
         return ret;
     }
 
-    init_blk_migration(f);
-
     qemu_mutex_unlock_iothread();
 
     ret = flush_blks(f);

block.c

@@ -24,7 +24,6 @@
 #include "config-host.h"
 #include "qemu-common.h"
 #include "trace.h"
-#include "monitor/monitor.h"
 #include "block/block_int.h"
 #include "block/blockjob.h"
 #include "qemu/module.h"
@@ -35,6 +34,7 @@
 #include "block/qapi.h"
 #include "qmp-commands.h"
 #include "qemu/timer.h"
+#include "qapi-event.h"
 
 #ifdef CONFIG_BSD
 #include <sys/types.h>
@@ -179,6 +179,7 @@ void bdrv_io_limits_enable(BlockDriverState *bs)
 {
     assert(!bs->io_limits_enabled);
     throttle_init(&bs->throttle_state,
+                  bdrv_get_aio_context(bs),
                   QEMU_CLOCK_VIRTUAL,
                   bdrv_throttle_read_timer_cb,
                   bdrv_throttle_write_timer_cb,
@@ -363,6 +364,7 @@ BlockDriverState *bdrv_new(const char *device_name, Error **errp)
     qemu_co_queue_init(&bs->throttled_reqs[0]);
     qemu_co_queue_init(&bs->throttled_reqs[1]);
     bs->refcnt = 1;
+    bs->aio_context = qemu_get_aio_context();
 
     return bs;
 }
@@ -422,7 +424,7 @@ BlockDriver *bdrv_find_whitelisted_format(const char *format_name,
 typedef struct CreateCo {
     BlockDriver *drv;
     char *filename;
-    QEMUOptionParameter *options;
+    QemuOpts *opts;
     int ret;
     Error *err;
 } CreateCo;
@@ -435,7 +437,7 @@ static void coroutine_fn bdrv_create_co_entry(void *opaque)
     CreateCo *cco = opaque;
     assert(cco->drv);
 
-    ret = cco->drv->bdrv_create(cco->filename, cco->options, &local_err);
+    ret = cco->drv->bdrv_create(cco->filename, cco->opts, &local_err);
     if (local_err) {
         error_propagate(&cco->err, local_err);
     }
@@ -443,7 +445,7 @@ static void coroutine_fn bdrv_create_co_entry(void *opaque)
 }
 
 int bdrv_create(BlockDriver *drv, const char* filename,
-    QEMUOptionParameter *options, Error **errp)
+                QemuOpts *opts, Error **errp)
 {
     int ret;
 
@@ -451,7 +453,7 @@ int bdrv_create(BlockDriver *drv, const char* filename,
     CreateCo cco = {
         .drv = drv,
         .filename = g_strdup(filename),
-        .options = options,
+        .opts = opts,
         .ret = NOT_DONE,
         .err = NULL,
     };
@@ -487,8 +489,7 @@ out:
     return ret;
 }
 
-int bdrv_create_file(const char* filename, QEMUOptionParameter *options,
-                     Error **errp)
+int bdrv_create_file(const char *filename, QemuOpts *opts, Error **errp)
 {
     BlockDriver *drv;
     Error *local_err = NULL;
@@ -500,7 +501,7 @@ int bdrv_create_file(const char* filename, QEMUOptionParameter *options,
         return -ENOENT;
     }
 
-    ret = bdrv_create(drv, filename, options, &local_err);
+    ret = bdrv_create(drv, filename, opts, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
     }
@@ -1245,7 +1246,7 @@ void bdrv_append_temp_snapshot(BlockDriverState *bs, int flags, Error **errp)
     char *tmp_filename = g_malloc0(PATH_MAX + 1);
     int64_t total_size;
     BlockDriver *bdrv_qcow2;
-    QEMUOptionParameter *create_options;
+    QemuOpts *opts = NULL;
     QDict *snapshot_options;
     BlockDriverState *bs_snapshot;
     Error *local_err;
@@ -1270,13 +1271,11 @@ void bdrv_append_temp_snapshot(BlockDriverState *bs, int flags, Error **errp)
     }
 
     bdrv_qcow2 = bdrv_find_format("qcow2");
-    create_options = parse_option_parameters("", bdrv_qcow2->create_options,
-                                             NULL);
-
-    set_option_parameter_int(create_options, BLOCK_OPT_SIZE, total_size);
-
-    ret = bdrv_create(bdrv_qcow2, tmp_filename, create_options, &local_err);
-    free_option_parameters(create_options);
+    opts = qemu_opts_create(bdrv_qcow2->create_opts, NULL, 0,
+                            &error_abort);
+    qemu_opt_set_number(opts, BLOCK_OPT_SIZE, total_size);
+    ret = bdrv_create(bdrv_qcow2, tmp_filename, opts, &local_err);
+    qemu_opts_del(opts);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not create temporary overlay "
                          "'%s': %s", tmp_filename,
@@ -1856,7 +1855,11 @@ void bdrv_close_all(void)
     BlockDriverState *bs;
 
     QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
+        AioContext *aio_context = bdrv_get_aio_context(bs);
+
+        aio_context_acquire(aio_context);
         bdrv_close(bs);
+        aio_context_release(aio_context);
     }
 }
 
@@ -1881,17 +1884,6 @@ static bool bdrv_requests_pending(BlockDriverState *bs)
     return false;
 }
 
-static bool bdrv_requests_pending_all(void)
-{
-    BlockDriverState *bs;
-    QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
-        if (bdrv_requests_pending(bs)) {
-            return true;
-        }
-    }
-    return false;
-}
-
 /*
  * Wait for pending requests to complete across all BlockDriverStates
  *
@@ -1911,12 +1903,20 @@ void bdrv_drain_all(void)
     BlockDriverState *bs;
 
     while (busy) {
-        QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
-            bdrv_start_throttled_reqs(bs);
-        }
+        busy = false;
 
-        busy = bdrv_requests_pending_all();
-        busy |= aio_poll(qemu_get_aio_context(), busy);
+        QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
+            AioContext *aio_context = bdrv_get_aio_context(bs);
+            bool bs_busy;
+
+            aio_context_acquire(aio_context);
+            bdrv_start_throttled_reqs(bs);
+            bs_busy = bdrv_requests_pending(bs);
+            bs_busy |= aio_poll(aio_context, bs_busy);
+            aio_context_release(aio_context);
+
+            busy |= bs_busy;
+        }
     }
 }
 
@@ -2132,47 +2132,6 @@ void bdrv_set_dev_ops(BlockDriverState *bs, const BlockDevOps *ops,
     bs->dev_opaque = opaque;
 }
 
-void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
-                               enum MonitorEvent ev,
-                               BlockErrorAction action, bool is_read)
-{
-    QObject *data;
-    const char *action_str;
-
-    switch (action) {
-    case BDRV_ACTION_REPORT:
-        action_str = "report";
-        break;
-    case BDRV_ACTION_IGNORE:
-        action_str = "ignore";
-        break;
-    case BDRV_ACTION_STOP:
-        action_str = "stop";
-        break;
-    default:
-        abort();
-    }
-
-    data = qobject_from_jsonf("{ 'device': %s, 'action': %s, 'operation': %s }",
-                              bdrv->device_name,
-                              action_str,
-                              is_read ? "read" : "write");
-    monitor_protocol_event(ev, data);
-
-    qobject_decref(data);
-}
-
-static void bdrv_emit_qmp_eject_event(BlockDriverState *bs, bool ejected)
-{
-    QObject *data;
-
-    data = qobject_from_jsonf("{ 'device': %s, 'tray-open': %i }",
-                              bdrv_get_device_name(bs), ejected);
-    monitor_protocol_event(QEVENT_DEVICE_TRAY_MOVED, data);
-
-    qobject_decref(data);
-}
-
 static void bdrv_dev_change_media_cb(BlockDriverState *bs, bool load)
 {
     if (bs->dev_ops && bs->dev_ops->change_media_cb) {
@@ -2180,11 +2139,13 @@ static void bdrv_dev_change_media_cb(BlockDriverState *bs, bool load)
         bs->dev_ops->change_media_cb(bs->dev_opaque, load);
         if (tray_was_closed) {
             /* tray open */
-            bdrv_emit_qmp_eject_event(bs, true);
+            qapi_event_send_device_tray_moved(bdrv_get_device_name(bs),
+                                              true, &error_abort);
         }
         if (load) {
             /* tray close */
-            bdrv_emit_qmp_eject_event(bs, false);
+            qapi_event_send_device_tray_moved(bdrv_get_device_name(bs),
+                                              false, &error_abort);
         }
     }
 }
@@ -2352,12 +2313,17 @@ int bdrv_commit_all(void)
     BlockDriverState *bs;
 
     QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
+        AioContext *aio_context = bdrv_get_aio_context(bs);
+
+        aio_context_acquire(aio_context);
         if (bs->drv && bs->backing_hd) {
             int ret = bdrv_commit(bs);
             if (ret < 0) {
+                aio_context_release(aio_context);
                 return ret;
             }
         }
+        aio_context_release(aio_context);
     }
     return 0;
 }
@@ -2775,10 +2741,12 @@ static int bdrv_prwv_co(BlockDriverState *bs, int64_t offset,
         /* Fast-path if already in coroutine context */
         bdrv_rw_co_entry(&rwco);
     } else {
+        AioContext *aio_context = bdrv_get_aio_context(bs);
+
         co = qemu_coroutine_create(bdrv_rw_co_entry);
         qemu_coroutine_enter(co, &rwco);
         while (rwco.ret == NOT_DONE) {
-            qemu_aio_wait();
+            aio_poll(aio_context, true);
         }
     }
     return rwco.ret;
@@ -3599,13 +3567,14 @@ BlockErrorAction bdrv_get_error_action(BlockDriverState *bs, bool is_read, int e
 
     switch (on_err) {
     case BLOCKDEV_ON_ERROR_ENOSPC:
-        return (error == ENOSPC) ? BDRV_ACTION_STOP : BDRV_ACTION_REPORT;
+        return (error == ENOSPC) ?
+               BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
     case BLOCKDEV_ON_ERROR_STOP:
-        return BDRV_ACTION_STOP;
+        return BLOCK_ERROR_ACTION_STOP;
     case BLOCKDEV_ON_ERROR_REPORT:
-        return BDRV_ACTION_REPORT;
+        return BLOCK_ERROR_ACTION_REPORT;
     case BLOCKDEV_ON_ERROR_IGNORE:
-        return BDRV_ACTION_IGNORE;
+        return BLOCK_ERROR_ACTION_IGNORE;
     default:
         abort();
     }
@@ -3619,10 +3588,33 @@ void bdrv_error_action(BlockDriverState *bs, BlockErrorAction action,
                        bool is_read, int error)
 {
     assert(error >= 0);
-    bdrv_emit_qmp_error_event(bs, QEVENT_BLOCK_IO_ERROR, action, is_read);
-    if (action == BDRV_ACTION_STOP) {
-        vm_stop(RUN_STATE_IO_ERROR);
+
+    if (action == BLOCK_ERROR_ACTION_STOP) {
+        /* First set the iostatus, so that "info block" returns an iostatus
+         * that matches the events raised so far (an additional error iostatus
+         * is fine, but not a lost one).
+         */
         bdrv_iostatus_set_err(bs, error);
+
+        /* Then raise the request to stop the VM and the event.
+         * qemu_system_vmstop_request_prepare has two effects.  First,
+         * it ensures that the STOP event always comes after the
+         * BLOCK_IO_ERROR event.  Second, it ensures that even if management
+         * can observe the STOP event and do a "cont" before the STOP
+         * event is issued, the VM will not stop.  In this case, vm_start()
+         * also ensures that the STOP/RESUME pair of events is emitted.
+         */
+        qemu_system_vmstop_request_prepare();
+        qapi_event_send_block_io_error(bdrv_get_device_name(bs),
+                                       is_read ? IO_OPERATION_TYPE_READ :
+                                       IO_OPERATION_TYPE_WRITE,
+                                       action, &error_abort);
+        qemu_system_vmstop_request(RUN_STATE_IO_ERROR);
+    } else {
+        qapi_event_send_block_io_error(bdrv_get_device_name(bs),
+                                       is_read ? IO_OPERATION_TYPE_READ :
+                                       IO_OPERATION_TYPE_WRITE,
+                                       action, &error_abort);
     }
 }
 
@@ -3831,10 +3823,15 @@ int bdrv_flush_all(void)
     int result = 0;
 
     QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
-        int ret = bdrv_flush(bs);
+        AioContext *aio_context = bdrv_get_aio_context(bs);
+        int ret;
+
+        aio_context_acquire(aio_context);
+        ret = bdrv_flush(bs);
         if (ret < 0 && !result) {
             result = ret;
         }
+        aio_context_release(aio_context);
     }
 
     return result;
@@ -4025,10 +4022,12 @@ int64_t bdrv_get_block_status(BlockDriverState *bs, int64_t sector_num,
         /* Fast-path if already in coroutine context */
         bdrv_get_block_status_co_entry(&data);
     } else {
+        AioContext *aio_context = bdrv_get_aio_context(bs);
+
         co = qemu_coroutine_create(bdrv_get_block_status_co_entry);
         qemu_coroutine_enter(co, &data);
         while (!data.done) {
-            qemu_aio_wait();
+            aio_poll(aio_context, true);
         }
     }
     return data.ret;
@@ -4621,7 +4620,7 @@ static BlockDriverAIOCB *bdrv_aio_rw_vector(BlockDriverState *bs,
     acb->is_write = is_write;
     acb->qiov = qiov;
     acb->bounce = qemu_blockalign(bs, qiov->size);
-    acb->bh = qemu_bh_new(bdrv_aio_bh_cb, acb);
+    acb->bh = aio_bh_new(bdrv_get_aio_context(bs), bdrv_aio_bh_cb, acb);
 
     if (is_write) {
         qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
@@ -4660,13 +4659,14 @@ typedef struct BlockDriverAIOCBCoroutine {
 
 static void bdrv_aio_co_cancel_em(BlockDriverAIOCB *blockacb)
 {
+    AioContext *aio_context = bdrv_get_aio_context(blockacb->bs);
     BlockDriverAIOCBCoroutine *acb =
         container_of(blockacb, BlockDriverAIOCBCoroutine, common);
     bool done = false;
 
     acb->done = &done;
     while (!done) {
-        qemu_aio_wait();
+        aio_poll(aio_context, true);
     }
 }
 
@@ -4703,7 +4703,7 @@ static void coroutine_fn bdrv_co_do_rw(void *opaque)
             acb->req.nb_sectors, acb->req.qiov, acb->req.flags);
     }
 
-    acb->bh = qemu_bh_new(bdrv_co_em_bh, acb);
+    acb->bh = aio_bh_new(bdrv_get_aio_context(bs), bdrv_co_em_bh, acb);
     qemu_bh_schedule(acb->bh);
 }
 
@@ -4739,7 +4739,7 @@ static void coroutine_fn bdrv_aio_flush_co_entry(void *opaque)
     BlockDriverState *bs = acb->common.bs;
 
     acb->req.error = bdrv_co_flush(bs);
-    acb->bh = qemu_bh_new(bdrv_co_em_bh, acb);
+    acb->bh = aio_bh_new(bdrv_get_aio_context(bs), bdrv_co_em_bh, acb);
     qemu_bh_schedule(acb->bh);
 }
 
@@ -4766,7 +4766,7 @@ static void coroutine_fn bdrv_aio_discard_co_entry(void *opaque)
     BlockDriverState *bs = acb->common.bs;
 
     acb->req.error = bdrv_co_discard(bs, acb->req.sector, acb->req.nb_sectors);
-    acb->bh = qemu_bh_new(bdrv_co_em_bh, acb);
+    acb->bh = aio_bh_new(bdrv_get_aio_context(bs), bdrv_co_em_bh, acb);
     qemu_bh_schedule(acb->bh);
 }
 
@@ -4977,7 +4977,11 @@ void bdrv_invalidate_cache_all(Error **errp)
     Error *local_err = NULL;
 
     QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
+        AioContext *aio_context = bdrv_get_aio_context(bs);
+
+        aio_context_acquire(aio_context);
         bdrv_invalidate_cache(bs, &local_err);
+        aio_context_release(aio_context);
         if (local_err) {
             error_propagate(errp, local_err);
             return;
@@ -4990,7 +4994,11 @@ void bdrv_clear_incoming_migration_all(void)
     BlockDriverState *bs;
 
     QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
+        AioContext *aio_context = bdrv_get_aio_context(bs);
+
+        aio_context_acquire(aio_context);
         bs->open_flags = bs->open_flags & ~(BDRV_O_INCOMING);
+        aio_context_release(aio_context);
     }
 }
 
@@ -5006,10 +5014,12 @@ int bdrv_flush(BlockDriverState *bs)
         /* Fast-path if already in coroutine context */
         bdrv_flush_co_entry(&rwco);
     } else {
+        AioContext *aio_context = bdrv_get_aio_context(bs);
+
         co = qemu_coroutine_create(bdrv_flush_co_entry);
         qemu_coroutine_enter(co, &rwco);
         while (rwco.ret == NOT_DONE) {
-            qemu_aio_wait();
+            aio_poll(aio_context, true);
         }
     }
 
@@ -5119,10 +5129,12 @@ int bdrv_discard(BlockDriverState *bs, int64_t sector_num, int nb_sectors)
         /* Fast-path if already in coroutine context */
         bdrv_discard_co_entry(&rwco);
     } else {
+        AioContext *aio_context = bdrv_get_aio_context(bs);
+
         co = qemu_coroutine_create(bdrv_discard_co_entry);
         qemu_coroutine_enter(co, &rwco);
         while (rwco.ret == NOT_DONE) {
-            qemu_aio_wait();
+            aio_poll(aio_context, true);
         }
     }
 
@@ -5172,7 +5184,8 @@ void bdrv_eject(BlockDriverState *bs, bool eject_flag)
     }
 
     if (bs->device_name[0] != '\0') {
-        bdrv_emit_qmp_eject_event(bs, eject_flag);
+        qapi_event_send_device_tray_moved(bdrv_get_device_name(bs),
+                                          eject_flag, &error_abort);
     }
 }
 
@@ -5489,8 +5502,10 @@ void bdrv_img_create(const char *filename, const char *fmt,
                      char *options, uint64_t img_size, int flags,
                      Error **errp, bool quiet)
 {
-    QEMUOptionParameter *param = NULL, *create_options = NULL;
-    QEMUOptionParameter *backing_fmt, *backing_file, *size;
+    QemuOptsList *create_opts = NULL;
+    QemuOpts *opts = NULL;
+    const char *backing_fmt, *backing_file;
+    int64_t size;
     BlockDriver *drv, *proto_drv;
     BlockDriver *backing_drv = NULL;
     Error *local_err = NULL;
@@ -5509,28 +5524,23 @@ void bdrv_img_create(const char *filename, const char *fmt,
         return;
     }
 
-    create_options = append_option_parameters(create_options,
-                                              drv->create_options);
-    create_options = append_option_parameters(create_options,
-                                              proto_drv->create_options);
+    create_opts = qemu_opts_append(create_opts, drv->create_opts);
+    create_opts = qemu_opts_append(create_opts, proto_drv->create_opts);
 
     /* Create parameter list with default values */
-    param = parse_option_parameters("", create_options, param);
-
-    set_option_parameter_int(param, BLOCK_OPT_SIZE, img_size);
+    opts = qemu_opts_create(create_opts, NULL, 0, &error_abort);
+    qemu_opt_set_number(opts, BLOCK_OPT_SIZE, img_size);
 
     /* Parse -o options */
     if (options) {
-        param = parse_option_parameters(options, create_options, param);
-        if (param == NULL) {
-            error_setg(errp, "Invalid options for file format '%s'.", fmt);
+        if (qemu_opts_do_parse(opts, options, NULL) != 0) {
+            error_setg(errp, "Invalid options for file format '%s'", fmt);
             goto out;
         }
     }
 
     if (base_filename) {
-        if (set_option_parameter(param, BLOCK_OPT_BACKING_FILE,
-                                 base_filename)) {
+        if (qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, base_filename)) {
             error_setg(errp, "Backing file not supported for file format '%s'",
                        fmt);
             goto out;
@@ -5538,40 +5548,39 @@ void bdrv_img_create(const char *filename, const char *fmt,
     }
 
     if (base_fmt) {
-        if (set_option_parameter(param, BLOCK_OPT_BACKING_FMT, base_fmt)) {
+        if (qemu_opt_set(opts, BLOCK_OPT_BACKING_FMT, base_fmt)) {
             error_setg(errp, "Backing file format not supported for file "
                              "format '%s'", fmt);
             goto out;
         }
     }
 
-    backing_file = get_option_parameter(param, BLOCK_OPT_BACKING_FILE);
-    if (backing_file && backing_file->value.s) {
-        if (!strcmp(filename, backing_file->value.s)) {
+    backing_file = qemu_opt_get(opts, BLOCK_OPT_BACKING_FILE);
+    if (backing_file) {
+        if (!strcmp(filename, backing_file)) {
             error_setg(errp, "Error: Trying to create an image with the "
                              "same filename as the backing file");
             goto out;
         }
     }
 
-    backing_fmt = get_option_parameter(param, BLOCK_OPT_BACKING_FMT);
-    if (backing_fmt && backing_fmt->value.s) {
-        backing_drv = bdrv_find_format(backing_fmt->value.s);
+    backing_fmt = qemu_opt_get(opts, BLOCK_OPT_BACKING_FMT);
+    if (backing_fmt) {
+        backing_drv = bdrv_find_format(backing_fmt);
         if (!backing_drv) {
             error_setg(errp, "Unknown backing file format '%s'",
-                       backing_fmt->value.s);
+                       backing_fmt);
             goto out;
         }
     }
 
     // The size for the image must always be specified, with one exception:
     // If we are using a backing file, we can obtain the size from there
-    size = get_option_parameter(param, BLOCK_OPT_SIZE);
-    if (size && size->value.n == -1) {
-        if (backing_file && backing_file->value.s) {
+    size = qemu_opt_get_size(opts, BLOCK_OPT_SIZE, 0);
+    if (size == -1) {
+        if (backing_file) {
             BlockDriverState *bs;
             uint64_t size;
-            char buf[32];
             int back_flags;
 
             /* backing files always opened read-only */
@@ -5579,11 +5588,11 @@ void bdrv_img_create(const char *filename, const char *fmt,
                 flags & ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
 
             bs = NULL;
-            ret = bdrv_open(&bs, backing_file->value.s, NULL, NULL, back_flags,
+            ret = bdrv_open(&bs, backing_file, NULL, NULL, back_flags,
                             backing_drv, &local_err);
             if (ret < 0) {
                 error_setg_errno(errp, -ret, "Could not open '%s': %s",
-                                 backing_file->value.s,
+                                 backing_file,
                                  error_get_pretty(local_err));
                 error_free(local_err);
                 local_err = NULL;
@@ -5592,8 +5601,7 @@ void bdrv_img_create(const char *filename, const char *fmt,
             bdrv_get_geometry(bs, &size);
             size *= 512;
 
-            snprintf(buf, sizeof(buf), "%" PRId64, size);
-            set_option_parameter(param, BLOCK_OPT_SIZE, buf);
+            qemu_opt_set_number(opts, BLOCK_OPT_SIZE, size);
 
             bdrv_unref(bs);
         } else {
@@ -5604,16 +5612,18 @@ void bdrv_img_create(const char *filename, const char *fmt,
 
     if (!quiet) {
         printf("Formatting '%s', fmt=%s ", filename, fmt);
-        print_option_parameters(param);
+        qemu_opts_print(opts);
         puts("");
     }
-    ret = bdrv_create(drv, filename, param, &local_err);
+
+    ret = bdrv_create(drv, filename, opts, &local_err);
+
     if (ret == -EFBIG) {
         /* This is generally a better message than whatever the driver would
          * deliver (especially because of the cluster_size_hint), since that
          * is most probably not much different from "image too large". */
         const char *cluster_size_hint = "";
-        if (get_option_parameter(create_options, BLOCK_OPT_CLUSTER_SIZE)) {
+        if (qemu_opt_get_size(opts, BLOCK_OPT_CLUSTER_SIZE, 0)) {
             cluster_size_hint = " (try using a larger cluster size)";
         }
         error_setg(errp, "The image size is too large for file format '%s'"
@@ -5623,9 +5633,8 @@ void bdrv_img_create(const char *filename, const char *fmt,
     }
 
 out:
-    free_option_parameters(create_options);
-    free_option_parameters(param);
-
+    qemu_opts_del(opts);
+    qemu_opts_free(create_opts);
     if (local_err) {
         error_propagate(errp, local_err);
     }
@@ -5633,8 +5642,66 @@ out:
 
 AioContext *bdrv_get_aio_context(BlockDriverState *bs)
 {
-    /* Currently BlockDriverState always uses the main loop AioContext */
-    return qemu_get_aio_context();
+    return bs->aio_context;
+}
+
+void bdrv_detach_aio_context(BlockDriverState *bs)
+{
+    if (!bs->drv) {
+        return;
+    }
+
+    if (bs->io_limits_enabled) {
+        throttle_detach_aio_context(&bs->throttle_state);
+    }
+    if (bs->drv->bdrv_detach_aio_context) {
+        bs->drv->bdrv_detach_aio_context(bs);
+    }
+    if (bs->file) {
+        bdrv_detach_aio_context(bs->file);
+    }
+    if (bs->backing_hd) {
+        bdrv_detach_aio_context(bs->backing_hd);
+    }
+
+    bs->aio_context = NULL;
+}
+
+void bdrv_attach_aio_context(BlockDriverState *bs,
+                             AioContext *new_context)
+{
+    if (!bs->drv) {
+        return;
+    }
+
+    bs->aio_context = new_context;
+
+    if (bs->backing_hd) {
+        bdrv_attach_aio_context(bs->backing_hd, new_context);
+    }
+    if (bs->file) {
+        bdrv_attach_aio_context(bs->file, new_context);
+    }
+    if (bs->drv->bdrv_attach_aio_context) {
+        bs->drv->bdrv_attach_aio_context(bs, new_context);
+    }
+    if (bs->io_limits_enabled) {
+        throttle_attach_aio_context(&bs->throttle_state, new_context);
+    }
+}
+
+void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context)
+{
+    bdrv_drain_all(); /* ensure there are no in-flight requests */
+
+    bdrv_detach_aio_context(bs);
+
+    /* This function executes in the old AioContext so acquire the new one in
+     * case it runs in a different thread.
+     */
+    aio_context_acquire(new_context);
+    bdrv_attach_aio_context(bs, new_context);
+    aio_context_release(new_context);
 }
 
 void bdrv_add_before_write_notifier(BlockDriverState *bs,
@@ -5643,12 +5710,12 @@ void bdrv_add_before_write_notifier(BlockDriverState *bs,
     notifier_with_return_list_add(&bs->before_write_notifiers, notifier);
 }
 
-int bdrv_amend_options(BlockDriverState *bs, QEMUOptionParameter *options)
+int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts)
 {
-    if (bs->drv->bdrv_amend_options == NULL) {
+    if (!bs->drv->bdrv_amend_options) {
         return -ENOTSUP;
     }
-    return bs->drv->bdrv_amend_options(bs, options);
+    return bs->drv->bdrv_amend_options(bs, opts);
 }
 
 /* This function will be called by the bdrv_recurse_is_first_non_filter method

block/backup.c

@@ -325,7 +325,7 @@ static void coroutine_fn backup_run(void *opaque)
                 /* Depending on error action, fail now or retry cluster */
                 BlockErrorAction action =
                     backup_error_action(job, error_is_read, -ret);
-                if (action == BDRV_ACTION_REPORT) {
+                if (action == BLOCK_ERROR_ACTION_REPORT) {
                     break;
                 } else {
                     start--;

block/blkdebug.c

@@ -471,7 +471,7 @@ static BlockDriverAIOCB *inject_error(BlockDriverState *bs,
     acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque);
     acb->ret = -error;
 
-    bh = qemu_bh_new(error_callback_bh, acb);
+    bh = aio_bh_new(bdrv_get_aio_context(bs), error_callback_bh, acb);
     acb->bh = bh;
     qemu_bh_schedule(bh);
 

block/blkverify.c

@@ -39,12 +39,13 @@ struct BlkverifyAIOCB {
 static void blkverify_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     BlkverifyAIOCB *acb = (BlkverifyAIOCB *)blockacb;
+    AioContext *aio_context = bdrv_get_aio_context(blockacb->bs);
     bool finished = false;
 
     /* Wait until request completes, invokes its callback, and frees itself */
     acb->finished = &finished;
     while (!finished) {
-        qemu_aio_wait();
+        aio_poll(aio_context, true);
     }
 }
 
@@ -228,7 +229,8 @@ static void blkverify_aio_cb(void *opaque, int ret)
             acb->verify(acb);
         }
 
-        acb->bh = qemu_bh_new(blkverify_aio_bh, acb);
+        acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
+                             blkverify_aio_bh, acb);
         qemu_bh_schedule(acb->bh);
         break;
     }
@@ -302,21 +304,40 @@ static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs,
     return bdrv_recurse_is_first_non_filter(s->test_file, candidate);
 }
 
+/* Propagate AioContext changes to ->test_file */
+static void blkverify_detach_aio_context(BlockDriverState *bs)
+{
+    BDRVBlkverifyState *s = bs->opaque;
+
+    bdrv_detach_aio_context(s->test_file);
+}
+
+static void blkverify_attach_aio_context(BlockDriverState *bs,
+                                         AioContext *new_context)
+{
+    BDRVBlkverifyState *s = bs->opaque;
+
+    bdrv_attach_aio_context(s->test_file, new_context);
+}
+
 static BlockDriver bdrv_blkverify = {
-    .format_name            = "blkverify",
-    .protocol_name          = "blkverify",
-    .instance_size          = sizeof(BDRVBlkverifyState),
+    .format_name                      = "blkverify",
+    .protocol_name                    = "blkverify",
+    .instance_size                    = sizeof(BDRVBlkverifyState),
 
-    .bdrv_parse_filename    = blkverify_parse_filename,
-    .bdrv_file_open         = blkverify_open,
-    .bdrv_close             = blkverify_close,
-    .bdrv_getlength         = blkverify_getlength,
+    .bdrv_parse_filename              = blkverify_parse_filename,
+    .bdrv_file_open                   = blkverify_open,
+    .bdrv_close                       = blkverify_close,
+    .bdrv_getlength                   = blkverify_getlength,
 
-    .bdrv_aio_readv         = blkverify_aio_readv,
-    .bdrv_aio_writev        = blkverify_aio_writev,
-    .bdrv_aio_flush         = blkverify_aio_flush,
+    .bdrv_aio_readv                   = blkverify_aio_readv,
+    .bdrv_aio_writev                  = blkverify_aio_writev,
+    .bdrv_aio_flush                   = blkverify_aio_flush,
 
-    .is_filter              = true,
+    .bdrv_attach_aio_context          = blkverify_attach_aio_context,
+    .bdrv_detach_aio_context          = blkverify_detach_aio_context,
+
+    .is_filter                        = true,
     .bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter,
 };
 

block/cow.c

@@ -324,31 +324,24 @@ static void cow_close(BlockDriverState *bs)
 {
 }
 
-static int cow_create(const char *filename, QEMUOptionParameter *options,
-                      Error **errp)
+static int cow_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     struct cow_header_v2 cow_header;
     struct stat st;
     int64_t image_sectors = 0;
-    const char *image_filename = NULL;
+    char *image_filename = NULL;
     Error *local_err = NULL;
     int ret;
     BlockDriverState *cow_bs;
 
     /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            image_sectors = options->value.n / 512;
-        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
-            image_filename = options->value.s;
-        }
-        options++;
-    }
+    image_sectors = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
+    image_filename = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
 
-    ret = bdrv_create_file(filename, options, &local_err);
+    ret = bdrv_create_file(filename, opts, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
-        return ret;
+        goto exit;
     }
 
     cow_bs = NULL;
@@ -356,7 +349,7 @@ static int cow_create(const char *filename, QEMUOptionParameter *options,
                     BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
-        return ret;
+        goto exit;
     }
 
     memset(&cow_header, 0, sizeof(cow_header));
@@ -389,22 +382,27 @@ static int cow_create(const char *filename, QEMUOptionParameter *options,
     }
 
 exit:
+    g_free(image_filename);
     bdrv_unref(cow_bs);
     return ret;
 }
 
-static QEMUOptionParameter cow_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    {
-        .name = BLOCK_OPT_BACKING_FILE,
-        .type = OPT_STRING,
-        .help = "File name of a base image"
-    },
-    { NULL }
+static QemuOptsList cow_create_opts = {
+    .name = "cow-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(cow_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        {
+            .name = BLOCK_OPT_BACKING_FILE,
+            .type = QEMU_OPT_STRING,
+            .help = "File name of a base image"
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_cow = {
@@ -421,7 +419,7 @@ static BlockDriver bdrv_cow = {
     .bdrv_write             = cow_co_write,
     .bdrv_co_get_block_status   = cow_co_get_block_status,
 
-    .create_options = cow_create_options,
+    .create_opts    = &cow_create_opts,
 };
 
 static void bdrv_cow_init(void)

block/curl.c

@@ -110,6 +110,7 @@ typedef struct BDRVCURLState {
     size_t readahead_size;
     bool sslverify;
     bool accept_range;
+    AioContext *aio_context;
 } BDRVCURLState;
 
 static void curl_clean_state(CURLState *s);
@@ -134,25 +135,29 @@ static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
 #endif
 
 static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
-                        void *s, void *sp)
+                        void *userp, void *sp)
 {
+    BDRVCURLState *s;
     CURLState *state = NULL;
     curl_easy_getinfo(curl, CURLINFO_PRIVATE, (char **)&state);
     state->sock_fd = fd;
+    s = state->s;
 
     DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, fd);
     switch (action) {
         case CURL_POLL_IN:
-            qemu_aio_set_fd_handler(fd, curl_multi_read, NULL, state);
+            aio_set_fd_handler(s->aio_context, fd, curl_multi_read,
+                               NULL, state);
             break;
         case CURL_POLL_OUT:
-            qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, state);
+            aio_set_fd_handler(s->aio_context, fd, NULL, curl_multi_do, state);
             break;
         case CURL_POLL_INOUT:
-            qemu_aio_set_fd_handler(fd, curl_multi_read, curl_multi_do, state);
+            aio_set_fd_handler(s->aio_context, fd, curl_multi_read,
+                               curl_multi_do, state);
             break;
         case CURL_POLL_REMOVE:
-            qemu_aio_set_fd_handler(fd, NULL, NULL, NULL);
+            aio_set_fd_handler(s->aio_context, fd, NULL, NULL, NULL);
             break;
     }
 
@@ -365,7 +370,7 @@ static CURLState *curl_init_state(BDRVCURLState *s)
             break;
         }
         if (!state) {
-            qemu_aio_wait();
+            aio_poll(state->s->aio_context, true);
         }
     } while(!state);
 
@@ -422,6 +427,49 @@ static void curl_parse_filename(const char *filename, QDict *options,
     qdict_put(options, CURL_BLOCK_OPT_URL, qstring_from_str(filename));
 }
 
+static void curl_detach_aio_context(BlockDriverState *bs)
+{
+    BDRVCURLState *s = bs->opaque;
+    int i;
+
+    for (i = 0; i < CURL_NUM_STATES; i++) {
+        if (s->states[i].in_use) {
+            curl_clean_state(&s->states[i]);
+        }
+        if (s->states[i].curl) {
+            curl_easy_cleanup(s->states[i].curl);
+            s->states[i].curl = NULL;
+        }
+        g_free(s->states[i].orig_buf);
+        s->states[i].orig_buf = NULL;
+    }
+    if (s->multi) {
+        curl_multi_cleanup(s->multi);
+        s->multi = NULL;
+    }
+
+    timer_del(&s->timer);
+}
+
+static void curl_attach_aio_context(BlockDriverState *bs,
+                                    AioContext *new_context)
+{
+    BDRVCURLState *s = bs->opaque;
+
+    aio_timer_init(new_context, &s->timer,
+                   QEMU_CLOCK_REALTIME, SCALE_NS,
+                   curl_multi_timeout_do, s);
+
+    assert(!s->multi);
+    s->multi = curl_multi_init();
+    s->aio_context = new_context;
+    curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb);
+#ifdef NEED_CURL_TIMER_CALLBACK
+    curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s);
+    curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb);
+#endif
+}
+
 static QemuOptsList runtime_opts = {
     .name = "curl",
     .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
@@ -491,6 +539,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     DPRINTF("CURL: Opening %s\n", file);
+    s->aio_context = bdrv_get_aio_context(bs);
     s->url = g_strdup(file);
     state = curl_init_state(s);
     if (!state)
@@ -523,19 +572,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 
-    aio_timer_init(bdrv_get_aio_context(bs), &s->timer,
-                   QEMU_CLOCK_REALTIME, SCALE_NS,
-                   curl_multi_timeout_do, s);
-
-    // Now we know the file exists and its size, so let's
-    // initialize the multi interface!
-
-    s->multi = curl_multi_init();
-    curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb);
-#ifdef NEED_CURL_TIMER_CALLBACK
-    curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s);
-    curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb);
-#endif
+    curl_attach_aio_context(bs, bdrv_get_aio_context(bs));
 
     qemu_opts_del(opts);
     return 0;
@@ -599,8 +636,7 @@ static void curl_readv_bh_cb(void *p)
     acb->end = (acb->nb_sectors * SECTOR_SIZE);
 
     state->buf_off = 0;
-    if (state->orig_buf)
-        g_free(state->orig_buf);
+    g_free(state->orig_buf);
     state->buf_start = start;
     state->buf_len = acb->end + s->readahead_size;
     end = MIN(start + state->buf_len, s->len) - 1;
@@ -630,7 +666,7 @@ static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
     acb->sector_num = sector_num;
     acb->nb_sectors = nb_sectors;
 
-    acb->bh = qemu_bh_new(curl_readv_bh_cb, acb);
+    acb->bh = aio_bh_new(bdrv_get_aio_context(bs), curl_readv_bh_cb, acb);
     qemu_bh_schedule(acb->bh);
     return &acb->common;
 }
@@ -638,25 +674,9 @@ static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
 static void curl_close(BlockDriverState *bs)
 {
     BDRVCURLState *s = bs->opaque;
-    int i;
 
     DPRINTF("CURL: Close\n");
-    for (i=0; i<CURL_NUM_STATES; i++) {
-        if (s->states[i].in_use)
-            curl_clean_state(&s->states[i]);
-        if (s->states[i].curl) {
-            curl_easy_cleanup(s->states[i].curl);
-            s->states[i].curl = NULL;
-        }
-        if (s->states[i].orig_buf) {
-            g_free(s->states[i].orig_buf);
-            s->states[i].orig_buf = NULL;
-        }
-    }
-    if (s->multi)
-        curl_multi_cleanup(s->multi);
-
-    timer_del(&s->timer);
+    curl_detach_aio_context(bs);
 
     g_free(s->url);
 }
@@ -668,68 +688,83 @@ static int64_t curl_getlength(BlockDriverState *bs)
 }
 
 static BlockDriver bdrv_http = {
-    .format_name            = "http",
-    .protocol_name          = "http",
+    .format_name                = "http",
+    .protocol_name              = "http",
 
-    .instance_size          = sizeof(BDRVCURLState),
-    .bdrv_parse_filename    = curl_parse_filename,
-    .bdrv_file_open         = curl_open,
-    .bdrv_close             = curl_close,
-    .bdrv_getlength         = curl_getlength,
+    .instance_size              = sizeof(BDRVCURLState),
+    .bdrv_parse_filename        = curl_parse_filename,
+    .bdrv_file_open             = curl_open,
+    .bdrv_close                 = curl_close,
+    .bdrv_getlength             = curl_getlength,
 
-    .bdrv_aio_readv         = curl_aio_readv,
+    .bdrv_aio_readv             = curl_aio_readv,
+
+    .bdrv_detach_aio_context    = curl_detach_aio_context,
+    .bdrv_attach_aio_context    = curl_attach_aio_context,
 };
 
 static BlockDriver bdrv_https = {
-    .format_name            = "https",
-    .protocol_name          = "https",
+    .format_name                = "https",
+    .protocol_name              = "https",
 
-    .instance_size          = sizeof(BDRVCURLState),
-    .bdrv_parse_filename    = curl_parse_filename,
-    .bdrv_file_open         = curl_open,
-    .bdrv_close             = curl_close,
-    .bdrv_getlength         = curl_getlength,
+    .instance_size              = sizeof(BDRVCURLState),
+    .bdrv_parse_filename        = curl_parse_filename,
+    .bdrv_file_open             = curl_open,
+    .bdrv_close                 = curl_close,
+    .bdrv_getlength             = curl_getlength,
 
-    .bdrv_aio_readv         = curl_aio_readv,
+    .bdrv_aio_readv             = curl_aio_readv,
+
+    .bdrv_detach_aio_context    = curl_detach_aio_context,
+    .bdrv_attach_aio_context    = curl_attach_aio_context,
 };
 
 static BlockDriver bdrv_ftp = {
-    .format_name            = "ftp",
-    .protocol_name          = "ftp",
+    .format_name                = "ftp",
+    .protocol_name              = "ftp",
 
-    .instance_size          = sizeof(BDRVCURLState),
-    .bdrv_parse_filename    = curl_parse_filename,
-    .bdrv_file_open         = curl_open,
-    .bdrv_close             = curl_close,
-    .bdrv_getlength         = curl_getlength,
+    .instance_size              = sizeof(BDRVCURLState),
+    .bdrv_parse_filename        = curl_parse_filename,
+    .bdrv_file_open             = curl_open,
+    .bdrv_close                 = curl_close,
+    .bdrv_getlength             = curl_getlength,
 
-    .bdrv_aio_readv         = curl_aio_readv,
+    .bdrv_aio_readv             = curl_aio_readv,
+
+    .bdrv_detach_aio_context    = curl_detach_aio_context,
+    .bdrv_attach_aio_context    = curl_attach_aio_context,
 };
 
 static BlockDriver bdrv_ftps = {
-    .format_name            = "ftps",
-    .protocol_name          = "ftps",
+    .format_name                = "ftps",
+    .protocol_name              = "ftps",
 
-    .instance_size          = sizeof(BDRVCURLState),
-    .bdrv_parse_filename    = curl_parse_filename,
-    .bdrv_file_open         = curl_open,
-    .bdrv_close             = curl_close,
-    .bdrv_getlength         = curl_getlength,
+    .instance_size              = sizeof(BDRVCURLState),
+    .bdrv_parse_filename        = curl_parse_filename,
+    .bdrv_file_open             = curl_open,
+    .bdrv_close                 = curl_close,
+    .bdrv_getlength             = curl_getlength,
 
-    .bdrv_aio_readv         = curl_aio_readv,
+    .bdrv_aio_readv             = curl_aio_readv,
+
+    .bdrv_detach_aio_context    = curl_detach_aio_context,
+    .bdrv_attach_aio_context    = curl_attach_aio_context,
 };
 
 static BlockDriver bdrv_tftp = {
-    .format_name            = "tftp",
-    .protocol_name          = "tftp",
+    .format_name                = "tftp",
+    .protocol_name              = "tftp",
 
-    .instance_size          = sizeof(BDRVCURLState),
-    .bdrv_parse_filename    = curl_parse_filename,
-    .bdrv_file_open         = curl_open,
-    .bdrv_close             = curl_close,
-    .bdrv_getlength         = curl_getlength,
+    .instance_size              = sizeof(BDRVCURLState),
+    .bdrv_parse_filename        = curl_parse_filename,
+    .bdrv_file_open             = curl_open,
+    .bdrv_close                 = curl_close,
+    .bdrv_getlength             = curl_getlength,
 
-    .bdrv_aio_readv         = curl_aio_readv,
+    .bdrv_aio_readv             = curl_aio_readv,
+
+    .bdrv_detach_aio_context    = curl_detach_aio_context,
+    .bdrv_attach_aio_context    = curl_attach_aio_context,
 };
 
 static void curl_block_init(void)

block/gluster.c

@@ -16,6 +16,7 @@ typedef struct GlusterAIOCB {
     int ret;
     QEMUBH *bh;
     Coroutine *coroutine;
+    AioContext *aio_context;
 } GlusterAIOCB;
 
 typedef struct BDRVGlusterState {
@@ -249,7 +250,7 @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
         acb->ret = -EIO; /* Partial read/write - fail it */
     }
 
-    acb->bh = qemu_bh_new(qemu_gluster_complete_aio, acb);
+    acb->bh = aio_bh_new(acb->aio_context, qemu_gluster_complete_aio, acb);
     qemu_bh_schedule(acb->bh);
 }
 
@@ -436,6 +437,7 @@ static coroutine_fn int qemu_gluster_co_write_zeroes(BlockDriverState *bs,
     acb->size = size;
     acb->ret = 0;
     acb->coroutine = qemu_coroutine_self();
+    acb->aio_context = bdrv_get_aio_context(bs);
 
     ret = glfs_zerofill_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
     if (ret < 0) {
@@ -476,13 +478,14 @@ static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset,
 #endif
 
 static int qemu_gluster_create(const char *filename,
-        QEMUOptionParameter *options, Error **errp)
+                               QemuOpts *opts, Error **errp)
 {
     struct glfs *glfs;
     struct glfs_fd *fd;
     int ret = 0;
     int prealloc = 0;
     int64_t total_size = 0;
+    char *tmp = NULL;
     GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
 
     glfs = qemu_gluster_init(gconf, filename, errp);
@@ -491,24 +494,21 @@ static int qemu_gluster_create(const char *filename,
         goto out;
     }
 
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            total_size = options->value.n / BDRV_SECTOR_SIZE;
-        } else if (!strcmp(options->name, BLOCK_OPT_PREALLOC)) {
-            if (!options->value.s || !strcmp(options->value.s, "off")) {
-                prealloc = 0;
-            } else if (!strcmp(options->value.s, "full") &&
-                    gluster_supports_zerofill()) {
-                prealloc = 1;
-            } else {
-                error_setg(errp, "Invalid preallocation mode: '%s'"
-                    " or GlusterFS doesn't support zerofill API",
-                           options->value.s);
-                ret = -EINVAL;
-                goto out;
-            }
-        }
-        options++;
+    total_size =
+        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
+
+    tmp = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
+    if (!tmp || !strcmp(tmp, "off")) {
+        prealloc = 0;
+    } else if (!strcmp(tmp, "full") &&
+               gluster_supports_zerofill()) {
+        prealloc = 1;
+    } else {
+        error_setg(errp, "Invalid preallocation mode: '%s'"
+            " or GlusterFS doesn't support zerofill API",
+            tmp);
+        ret = -EINVAL;
+        goto out;
     }
 
     fd = glfs_creat(glfs, gconf->image,
@@ -530,6 +530,7 @@ static int qemu_gluster_create(const char *filename,
         }
     }
 out:
+    g_free(tmp);
     qemu_gluster_gconf_free(gconf);
     if (glfs) {
         glfs_fini(glfs);
@@ -549,6 +550,7 @@ static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,
     acb->size = size;
     acb->ret = 0;
     acb->coroutine = qemu_coroutine_self();
+    acb->aio_context = bdrv_get_aio_context(bs);
 
     if (write) {
         ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
@@ -605,6 +607,7 @@ static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
     acb->size = 0;
     acb->ret = 0;
     acb->coroutine = qemu_coroutine_self();
+    acb->aio_context = bdrv_get_aio_context(bs);
 
     ret = glfs_fsync_async(s->fd, &gluster_finish_aiocb, acb);
     if (ret < 0) {
@@ -633,6 +636,7 @@ static coroutine_fn int qemu_gluster_co_discard(BlockDriverState *bs,
     acb->size = 0;
     acb->ret = 0;
     acb->coroutine = qemu_coroutine_self();
+    acb->aio_context = bdrv_get_aio_context(bs);
 
     ret = glfs_discard_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
     if (ret < 0) {
@@ -693,18 +697,22 @@ static int qemu_gluster_has_zero_init(BlockDriverState *bs)
     return 0;
 }
 
-static QEMUOptionParameter qemu_gluster_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    {
-        .name = BLOCK_OPT_PREALLOC,
-        .type = OPT_STRING,
-        .help = "Preallocation mode (allowed values: off, full)"
-    },
-    { NULL }
+static QemuOptsList qemu_gluster_create_opts = {
+    .name = "qemu-gluster-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(qemu_gluster_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        {
+            .name = BLOCK_OPT_PREALLOC,
+            .type = QEMU_OPT_STRING,
+            .help = "Preallocation mode (allowed values: off, full)"
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_gluster = {
@@ -731,7 +739,7 @@ static BlockDriver bdrv_gluster = {
 #ifdef CONFIG_GLUSTERFS_ZEROFILL
     .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
 #endif
-    .create_options               = qemu_gluster_create_options,
+    .create_opts                  = &qemu_gluster_create_opts,
 };
 
 static BlockDriver bdrv_gluster_tcp = {
@@ -758,7 +766,7 @@ static BlockDriver bdrv_gluster_tcp = {
 #ifdef CONFIG_GLUSTERFS_ZEROFILL
     .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
 #endif
-    .create_options               = qemu_gluster_create_options,
+    .create_opts                  = &qemu_gluster_create_opts,
 };
 
 static BlockDriver bdrv_gluster_unix = {
@@ -785,7 +793,7 @@ static BlockDriver bdrv_gluster_unix = {
 #ifdef CONFIG_GLUSTERFS_ZEROFILL
     .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
 #endif
-    .create_options               = qemu_gluster_create_options,
+    .create_opts                  = &qemu_gluster_create_opts,
 };
 
 static BlockDriver bdrv_gluster_rdma = {
@@ -812,7 +820,7 @@ static BlockDriver bdrv_gluster_rdma = {
 #ifdef CONFIG_GLUSTERFS_ZEROFILL
     .bdrv_co_write_zeroes         = qemu_gluster_co_write_zeroes,
 #endif
-    .create_options               = qemu_gluster_create_options,
+    .create_opts                  = &qemu_gluster_create_opts,
 };
 
 static void bdrv_gluster_init(void)

block/iscsi.c

@@ -26,6 +26,7 @@
 #include "config-host.h"
 
 #include <poll.h>
+#include <math.h>
 #include <arpa/inet.h>
 #include "qemu-common.h"
 #include "qemu/config-file.h"
@@ -49,6 +50,7 @@
 
 typedef struct IscsiLun {
     struct iscsi_context *iscsi;
+    AioContext *aio_context;
     int lun;
     enum scsi_inquiry_peripheral_device_type type;
     int block_size;
@@ -63,6 +65,7 @@ typedef struct IscsiLun {
     unsigned char *zeroblock;
     unsigned long *allocationmap;
     int cluster_sectors;
+    bool use_16_for_rw;
 } IscsiLun;
 
 typedef struct IscsiTask {
@@ -73,6 +76,8 @@ typedef struct IscsiTask {
     struct scsi_task *task;
     Coroutine *co;
     QEMUBH *bh;
+    IscsiLun *iscsilun;
+    QEMUTimer retry_timer;
 } IscsiTask;
 
 typedef struct IscsiAIOCB {
@@ -84,7 +89,6 @@ typedef struct IscsiAIOCB {
     uint8_t *buf;
     int status;
     int canceled;
-    int retries;
     int64_t sector_num;
     int nb_sectors;
 #ifdef __linux__
@@ -94,9 +98,10 @@ typedef struct IscsiAIOCB {
 
 #define NOP_INTERVAL 5000
 #define MAX_NOP_FAILURES 3
-#define ISCSI_CMD_RETRIES 5
+#define ISCSI_CMD_RETRIES ARRAY_SIZE(iscsi_retry_times)
+static const unsigned iscsi_retry_times[] = {8, 32, 128, 512, 2048};
 
-/* this threshhold is a trade-off knob to choose between
+/* this threshold is a trade-off knob to choose between
  * the potential additional overhead of an extra GET_LBA_STATUS request
  * vs. unnecessarily reading a lot of zero sectors over the wire.
  * If a read request is greater or equal than ISCSI_CHECKALLOC_THRES
@@ -133,17 +138,32 @@ iscsi_schedule_bh(IscsiAIOCB *acb)
     if (acb->bh) {
         return;
     }
-    acb->bh = qemu_bh_new(iscsi_bh_cb, acb);
+    acb->bh = aio_bh_new(acb->iscsilun->aio_context, iscsi_bh_cb, acb);
     qemu_bh_schedule(acb->bh);
 }
 
 static void iscsi_co_generic_bh_cb(void *opaque)
 {
     struct IscsiTask *iTask = opaque;
+    iTask->complete = 1;
     qemu_bh_delete(iTask->bh);
     qemu_coroutine_enter(iTask->co, NULL);
 }
 
+static void iscsi_retry_timer_expired(void *opaque)
+{
+    struct IscsiTask *iTask = opaque;
+    iTask->complete = 1;
+    if (iTask->co) {
+        qemu_coroutine_enter(iTask->co, NULL);
+    }
+}
+
+static inline unsigned exp_random(double mean)
+{
+    return -mean * log((double)rand() / RAND_MAX);
+}
+
 static void
 iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
                         void *command_data, void *opaque)
@@ -151,26 +171,44 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
     struct IscsiTask *iTask = opaque;
     struct scsi_task *task = command_data;
 
-    iTask->complete = 1;
     iTask->status = status;
     iTask->do_retry = 0;
     iTask->task = task;
 
-    if (iTask->retries-- > 0 && status == SCSI_STATUS_CHECK_CONDITION
-        && task->sense.key == SCSI_SENSE_UNIT_ATTENTION) {
-        error_report("iSCSI CheckCondition: %s", iscsi_get_error(iscsi));
-        iTask->do_retry = 1;
-        goto out;
-    }
-
     if (status != SCSI_STATUS_GOOD) {
+        if (iTask->retries++ < ISCSI_CMD_RETRIES) {
+            if (status == SCSI_STATUS_CHECK_CONDITION
+                && task->sense.key == SCSI_SENSE_UNIT_ATTENTION) {
+                error_report("iSCSI CheckCondition: %s",
+                             iscsi_get_error(iscsi));
+                iTask->do_retry = 1;
+                goto out;
+            }
+            if (status == SCSI_STATUS_BUSY) {
+                unsigned retry_time =
+                    exp_random(iscsi_retry_times[iTask->retries - 1]);
+                error_report("iSCSI Busy (retry #%u in %u ms): %s",
+                             iTask->retries, retry_time,
+                             iscsi_get_error(iscsi));
+                aio_timer_init(iTask->iscsilun->aio_context,
+                               &iTask->retry_timer, QEMU_CLOCK_REALTIME,
+                               SCALE_MS, iscsi_retry_timer_expired, iTask);
+                timer_mod(&iTask->retry_timer,
+                          qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + retry_time);
+                iTask->do_retry = 1;
+                return;
+            }
+        }
         error_report("iSCSI Failure: %s", iscsi_get_error(iscsi));
     }
 
 out:
     if (iTask->co) {
-        iTask->bh = qemu_bh_new(iscsi_co_generic_bh_cb, iTask);
+        iTask->bh = aio_bh_new(iTask->iscsilun->aio_context,
+                               iscsi_co_generic_bh_cb, iTask);
         qemu_bh_schedule(iTask->bh);
+    } else {
+        iTask->complete = 1;
     }
 }
 
@@ -178,7 +216,7 @@ static void iscsi_co_init_iscsitask(IscsiLun *iscsilun, struct IscsiTask *iTask)
 {
     *iTask = (struct IscsiTask) {
         .co         = qemu_coroutine_self(),
-        .retries    = ISCSI_CMD_RETRIES,
+        .iscsilun   = iscsilun,
     };
 }
 
@@ -209,7 +247,7 @@ iscsi_aio_cancel(BlockDriverAIOCB *blockacb)
                                      iscsi_abort_task_cb, acb);
 
     while (acb->status == -EINPROGRESS) {
-        qemu_aio_wait();
+        aio_poll(iscsilun->aio_context, true);
     }
 }
 
@@ -232,10 +270,11 @@ iscsi_set_events(IscsiLun *iscsilun)
     ev = POLLIN;
     ev |= iscsi_which_events(iscsi);
     if (ev != iscsilun->events) {
-        qemu_aio_set_fd_handler(iscsi_get_fd(iscsi),
-                      iscsi_process_read,
-                      (ev & POLLOUT) ? iscsi_process_write : NULL,
-                      iscsilun);
+        aio_set_fd_handler(iscsilun->aio_context,
+                           iscsi_get_fd(iscsi),
+                           iscsi_process_read,
+                           (ev & POLLOUT) ? iscsi_process_write : NULL,
+                           iscsilun);
 
     }
 
@@ -320,8 +359,6 @@ static int coroutine_fn iscsi_co_writev(BlockDriverState *bs,
     struct IscsiTask iTask;
     uint64_t lba;
     uint32_t num_sectors;
-    uint8_t *data = NULL;
-    uint8_t *buf = NULL;
 
     if (!is_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
         return -EINVAL;
@@ -329,31 +366,24 @@ static int coroutine_fn iscsi_co_writev(BlockDriverState *bs,
 
     lba = sector_qemu2lun(sector_num, iscsilun);
     num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
-#if !defined(LIBISCSI_FEATURE_IOVECTOR)
-    /* if the iovec only contains one buffer we can pass it directly */
-    if (iov->niov == 1) {
-        data = iov->iov[0].iov_base;
-    } else {
-        size_t size = MIN(nb_sectors * BDRV_SECTOR_SIZE, iov->size);
-        buf = g_malloc(size);
-        qemu_iovec_to_buf(iov, 0, buf, size);
-        data = buf;
-    }
-#endif
     iscsi_co_init_iscsitask(iscsilun, &iTask);
 retry:
-    iTask.task = iscsi_write16_task(iscsilun->iscsi, iscsilun->lun, lba,
-                                    data, num_sectors * iscsilun->block_size,
-                                    iscsilun->block_size, 0, 0, 0, 0, 0,
-                                    iscsi_co_generic_cb, &iTask);
+    if (iscsilun->use_16_for_rw) {
+        iTask.task = iscsi_write16_task(iscsilun->iscsi, iscsilun->lun, lba,
+                                        NULL, num_sectors * iscsilun->block_size,
+                                        iscsilun->block_size, 0, 0, 0, 0, 0,
+                                        iscsi_co_generic_cb, &iTask);
+    } else {
+        iTask.task = iscsi_write10_task(iscsilun->iscsi, iscsilun->lun, lba,
+                                        NULL, num_sectors * iscsilun->block_size,
+                                        iscsilun->block_size, 0, 0, 0, 0, 0,
+                                        iscsi_co_generic_cb, &iTask);
+    }
     if (iTask.task == NULL) {
-        g_free(buf);
         return -ENOMEM;
     }
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
     scsi_task_set_iov_out(iTask.task, (struct scsi_iovec *) iov->iov,
                           iov->niov);
-#endif
     while (!iTask.complete) {
         iscsi_set_events(iscsilun);
         qemu_coroutine_yield();
@@ -369,8 +399,6 @@ retry:
         goto retry;
     }
 
-    g_free(buf);
-
     if (iTask.status != SCSI_STATUS_GOOD) {
         return -EIO;
     }
@@ -381,7 +409,6 @@ retry:
 }
 
 
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
 static bool iscsi_allocationmap_is_allocated(IscsiLun *iscsilun,
                                              int64_t sector_num, int nb_sectors)
 {
@@ -491,9 +518,6 @@ out:
     return ret;
 }
 
-#endif /* LIBISCSI_FEATURE_IOVECTOR */
-
-
 static int coroutine_fn iscsi_co_readv(BlockDriverState *bs,
                                        int64_t sector_num, int nb_sectors,
                                        QEMUIOVector *iov)
@@ -502,15 +526,11 @@ static int coroutine_fn iscsi_co_readv(BlockDriverState *bs,
     struct IscsiTask iTask;
     uint64_t lba;
     uint32_t num_sectors;
-#if !defined(LIBISCSI_FEATURE_IOVECTOR)
-    int i;
-#endif
 
     if (!is_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
         return -EINVAL;
     }
 
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
     if (iscsilun->lbprz && nb_sectors >= ISCSI_CHECKALLOC_THRES &&
         !iscsi_allocationmap_is_allocated(iscsilun, sector_num, nb_sectors)) {
         int64_t ret;
@@ -524,42 +544,28 @@ static int coroutine_fn iscsi_co_readv(BlockDriverState *bs,
             return 0;
         }
     }
-#endif
 
     lba = sector_qemu2lun(sector_num, iscsilun);
     num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
 
     iscsi_co_init_iscsitask(iscsilun, &iTask);
 retry:
-    switch (iscsilun->type) {
-    case TYPE_DISK:
+    if (iscsilun->use_16_for_rw) {
         iTask.task = iscsi_read16_task(iscsilun->iscsi, iscsilun->lun, lba,
                                        num_sectors * iscsilun->block_size,
                                        iscsilun->block_size, 0, 0, 0, 0, 0,
                                        iscsi_co_generic_cb, &iTask);
-        break;
-    default:
+    } else {
         iTask.task = iscsi_read10_task(iscsilun->iscsi, iscsilun->lun, lba,
                                        num_sectors * iscsilun->block_size,
                                        iscsilun->block_size,
-#if !defined(CONFIG_LIBISCSI_1_4) /* API change from 1.4.0 to 1.5.0 */
                                        0, 0, 0, 0, 0,
-#endif
                                        iscsi_co_generic_cb, &iTask);
-        break;
     }
     if (iTask.task == NULL) {
         return -ENOMEM;
     }
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
     scsi_task_set_iov_in(iTask.task, (struct scsi_iovec *) iov->iov, iov->niov);
-#else
-    for (i = 0; i < iov->niov; i++) {
-        scsi_task_add_data_in_buffer(iTask.task,
-                                     iov->iov[i].iov_len,
-                                     iov->iov[i].iov_base);
-    }
-#endif
 
     while (!iTask.complete) {
         iscsi_set_events(iscsilun);
@@ -714,18 +720,9 @@ static BlockDriverAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
             data.data = acb->ioh->dxferp;
             data.size = acb->ioh->dxfer_len;
         } else {
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
             scsi_task_set_iov_out(acb->task,
                                  (struct scsi_iovec *) acb->ioh->dxferp,
                                  acb->ioh->iovec_count);
-#else
-            struct iovec *iov = (struct iovec *)acb->ioh->dxferp;
-
-            acb->buf = g_malloc(acb->ioh->dxfer_len);
-            data.data = acb->buf;
-            data.size = iov_to_buf(iov, acb->ioh->iovec_count, 0,
-                                   acb->buf, acb->ioh->dxfer_len);
-#endif
         }
     }
 
@@ -745,20 +742,9 @@ static BlockDriverAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
                                          acb->ioh->dxfer_len,
                                          acb->ioh->dxferp);
         } else {
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
             scsi_task_set_iov_in(acb->task,
                                  (struct scsi_iovec *) acb->ioh->dxferp,
                                  acb->ioh->iovec_count);
-#else
-            int i;
-            for (i = 0; i < acb->ioh->iovec_count; i++) {
-                struct iovec *iov = (struct iovec *)acb->ioh->dxferp;
-
-                scsi_task_add_data_in_buffer(acb->task,
-                    iov[i].iov_len,
-                    iov[i].iov_base);
-            }
-#endif
         }
     }
 
@@ -767,7 +753,6 @@ static BlockDriverAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
     return &acb->common;
 }
 
-
 static void ioctl_cb(void *opaque, int status)
 {
     int *p_status = opaque;
@@ -791,7 +776,7 @@ static int iscsi_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
         iscsi_aio_ioctl(bs, req, buf, ioctl_cb, &status);
 
         while (status == -EINPROGRESS) {
-            qemu_aio_wait();
+            aio_poll(iscsilun->aio_context, true);
         }
 
         return 0;
@@ -872,8 +857,6 @@ retry:
     return 0;
 }
 
-#if defined(SCSI_SENSE_ASCQ_CAPACITY_DATA_HAS_CHANGED)
-
 static int
 coroutine_fn iscsi_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
                                    int nb_sectors, BdrvRequestFlags flags)
@@ -882,19 +865,27 @@ coroutine_fn iscsi_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
     struct IscsiTask iTask;
     uint64_t lba;
     uint32_t nb_blocks;
+    bool use_16_for_ws = iscsilun->use_16_for_rw;
 
     if (!is_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
         return -EINVAL;
     }
 
-    if ((flags & BDRV_REQ_MAY_UNMAP) && !iscsilun->lbp.lbpws) {
-        /* WRITE SAME with UNMAP is not supported by the target,
-         * fall back and try WRITE SAME without UNMAP */
-        flags &= ~BDRV_REQ_MAY_UNMAP;
+    if (flags & BDRV_REQ_MAY_UNMAP) {
+        if (!use_16_for_ws && !iscsilun->lbp.lbpws10) {
+            /* WRITESAME10 with UNMAP is unsupported try WRITESAME16 */
+            use_16_for_ws = true;
+        }
+        if (use_16_for_ws && !iscsilun->lbp.lbpws) {
+            /* WRITESAME16 with UNMAP is not supported by the target,
+             * fall back and try WRITESAME10/16 without UNMAP */
+            flags &= ~BDRV_REQ_MAY_UNMAP;
+            use_16_for_ws = iscsilun->use_16_for_rw;
+        }
     }
 
     if (!(flags & BDRV_REQ_MAY_UNMAP) && !iscsilun->has_write_same) {
-        /* WRITE SAME without UNMAP is not supported by the target */
+        /* WRITESAME without UNMAP is not supported by the target */
         return -ENOTSUP;
     }
 
@@ -907,10 +898,18 @@ coroutine_fn iscsi_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
 
     iscsi_co_init_iscsitask(iscsilun, &iTask);
 retry:
-    if (iscsi_writesame16_task(iscsilun->iscsi, iscsilun->lun, lba,
-                               iscsilun->zeroblock, iscsilun->block_size,
-                               nb_blocks, 0, !!(flags & BDRV_REQ_MAY_UNMAP),
-                               0, 0, iscsi_co_generic_cb, &iTask) == NULL) {
+    if (use_16_for_ws) {
+        iTask.task = iscsi_writesame16_task(iscsilun->iscsi, iscsilun->lun, lba,
+                                            iscsilun->zeroblock, iscsilun->block_size,
+                                            nb_blocks, 0, !!(flags & BDRV_REQ_MAY_UNMAP),
+                                            0, 0, iscsi_co_generic_cb, &iTask);
+    } else {
+        iTask.task = iscsi_writesame10_task(iscsilun->iscsi, iscsilun->lun, lba,
+                                            iscsilun->zeroblock, iscsilun->block_size,
+                                            nb_blocks, 0, !!(flags & BDRV_REQ_MAY_UNMAP),
+                                            0, 0, iscsi_co_generic_cb, &iTask);
+    }
+    if (iTask.task == NULL) {
         return -ENOMEM;
     }
 
@@ -952,8 +951,6 @@ retry:
     return 0;
 }
 
-#endif /* SCSI_SENSE_ASCQ_CAPACITY_DATA_HAS_CHANGED */
-
 static void parse_chap(struct iscsi_context *iscsi, const char *target,
                        Error **errp)
 {
@@ -1063,7 +1060,6 @@ static char *parse_initiator_name(const char *target)
     return iscsi_name;
 }
 
-#if defined(LIBISCSI_FEATURE_NOP_COUNTER)
 static void iscsi_nop_timed_event(void *opaque)
 {
     IscsiLun *iscsilun = opaque;
@@ -1081,7 +1077,6 @@ static void iscsi_nop_timed_event(void *opaque)
     timer_mod(iscsilun->nop_timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL);
     iscsi_set_events(iscsilun);
 }
-#endif
 
 static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
 {
@@ -1108,6 +1103,7 @@ static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
                     iscsilun->num_blocks = rc16->returned_lba + 1;
                     iscsilun->lbpme = rc16->lbpme;
                     iscsilun->lbprz = rc16->lbprz;
+                    iscsilun->use_16_for_rw = (rc16->returned_lba > 0xffffffff);
                 }
             }
             break;
@@ -1195,6 +1191,38 @@ fail_with_err:
     return NULL;
 }
 
+static void iscsi_detach_aio_context(BlockDriverState *bs)
+{
+    IscsiLun *iscsilun = bs->opaque;
+
+    aio_set_fd_handler(iscsilun->aio_context,
+                       iscsi_get_fd(iscsilun->iscsi),
+                       NULL, NULL, NULL);
+    iscsilun->events = 0;
+
+    if (iscsilun->nop_timer) {
+        timer_del(iscsilun->nop_timer);
+        timer_free(iscsilun->nop_timer);
+        iscsilun->nop_timer = NULL;
+    }
+}
+
+static void iscsi_attach_aio_context(BlockDriverState *bs,
+                                     AioContext *new_context)
+{
+    IscsiLun *iscsilun = bs->opaque;
+
+    iscsilun->aio_context = new_context;
+    iscsi_set_events(iscsilun);
+
+    /* Set up a timer for sending out iSCSI NOPs */
+    iscsilun->nop_timer = aio_timer_new(iscsilun->aio_context,
+                                        QEMU_CLOCK_REALTIME, SCALE_MS,
+                                        iscsi_nop_timed_event, iscsilun);
+    timer_mod(iscsilun->nop_timer,
+              qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL);
+}
+
 /*
  * We support iscsi url's on the form
  * iscsi://[<username>%<password>@]<host>[:<port>]/<targetname>/<lun>
@@ -1301,6 +1329,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     iscsilun->iscsi = iscsi;
+    iscsilun->aio_context = bdrv_get_aio_context(bs);
     iscsilun->lun   = iscsi_url->lun;
     iscsilun->has_write_same = true;
 
@@ -1374,11 +1403,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
     scsi_free_scsi_task(task);
     task = NULL;
 
-#if defined(LIBISCSI_FEATURE_NOP_COUNTER)
-    /* Set up a timer for sending out iSCSI NOPs */
-    iscsilun->nop_timer = timer_new_ms(QEMU_CLOCK_REALTIME, iscsi_nop_timed_event, iscsilun);
-    timer_mod(iscsilun->nop_timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL);
-#endif
+    iscsi_attach_aio_context(bs, iscsilun->aio_context);
 
     /* Guess the internal cluster (page) size of the iscsi target by the means
      * of opt_unmap_gran. Transfer the unmap granularity only if it has a
@@ -1387,20 +1412,16 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
         iscsilun->bl.opt_unmap_gran * iscsilun->block_size <= 16 * 1024 * 1024) {
         iscsilun->cluster_sectors = (iscsilun->bl.opt_unmap_gran *
                                      iscsilun->block_size) >> BDRV_SECTOR_BITS;
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
         if (iscsilun->lbprz && !(bs->open_flags & BDRV_O_NOCACHE)) {
             iscsilun->allocationmap =
                 bitmap_new(DIV_ROUND_UP(bs->total_sectors,
                                         iscsilun->cluster_sectors));
         }
-#endif
     }
 
 out:
     qemu_opts_del(opts);
-    if (initiator_name != NULL) {
-        g_free(initiator_name);
-    }
+    g_free(initiator_name);
     if (iscsi_url != NULL) {
         iscsi_destroy_url(iscsi_url);
     }
@@ -1422,11 +1443,7 @@ static void iscsi_close(BlockDriverState *bs)
     IscsiLun *iscsilun = bs->opaque;
     struct iscsi_context *iscsi = iscsilun->iscsi;
 
-    if (iscsilun->nop_timer) {
-        timer_del(iscsilun->nop_timer);
-        timer_free(iscsilun->nop_timer);
-    }
-    qemu_aio_set_fd_handler(iscsi_get_fd(iscsi), NULL, NULL, NULL);
+    iscsi_detach_aio_context(bs);
     iscsi_destroy_context(iscsi);
     g_free(iscsilun->zeroblock);
     g_free(iscsilun->allocationmap);
@@ -1500,8 +1517,7 @@ static int iscsi_truncate(BlockDriverState *bs, int64_t offset)
     return 0;
 }
 
-static int iscsi_create(const char *filename, QEMUOptionParameter *options,
-                        Error **errp)
+static int iscsi_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     int ret = 0;
     int64_t total_size = 0;
@@ -1512,13 +1528,8 @@ static int iscsi_create(const char *filename, QEMUOptionParameter *options,
     bs = bdrv_new("", &error_abort);
 
     /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, "size")) {
-            total_size = options->value.n / BDRV_SECTOR_SIZE;
-        }
-        options++;
-    }
-
+    total_size =
+        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
     bs->opaque = g_malloc0(sizeof(struct IscsiLun));
     iscsilun = bs->opaque;
 
@@ -1530,10 +1541,7 @@ static int iscsi_create(const char *filename, QEMUOptionParameter *options,
     if (ret != 0) {
         goto out;
     }
-    if (iscsilun->nop_timer) {
-        timer_del(iscsilun->nop_timer);
-        timer_free(iscsilun->nop_timer);
-    }
+    iscsi_detach_aio_context(bs);
     if (iscsilun->type != TYPE_DISK) {
         ret = -ENODEV;
         goto out;
@@ -1563,13 +1571,17 @@ static int iscsi_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     return 0;
 }
 
-static QEMUOptionParameter iscsi_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    { NULL }
+static QemuOptsList iscsi_create_opts = {
+    .name = "iscsi-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(iscsi_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_iscsi = {
@@ -1581,7 +1593,7 @@ static BlockDriver bdrv_iscsi = {
     .bdrv_file_open  = iscsi_open,
     .bdrv_close      = iscsi_close,
     .bdrv_create     = iscsi_create,
-    .create_options  = iscsi_create_options,
+    .create_opts     = &iscsi_create_opts,
     .bdrv_reopen_prepare  = iscsi_reopen_prepare,
 
     .bdrv_getlength  = iscsi_getlength,
@@ -1589,13 +1601,9 @@ static BlockDriver bdrv_iscsi = {
     .bdrv_truncate   = iscsi_truncate,
     .bdrv_refresh_limits = iscsi_refresh_limits,
 
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
     .bdrv_co_get_block_status = iscsi_co_get_block_status,
-#endif
     .bdrv_co_discard      = iscsi_co_discard,
-#if defined(SCSI_SENSE_ASCQ_CAPACITY_DATA_HAS_CHANGED)
     .bdrv_co_write_zeroes = iscsi_co_write_zeroes,
-#endif
     .bdrv_co_readv         = iscsi_co_readv,
     .bdrv_co_writev        = iscsi_co_writev,
     .bdrv_co_flush_to_disk = iscsi_co_flush,
@@ -1604,6 +1612,9 @@ static BlockDriver bdrv_iscsi = {
     .bdrv_ioctl       = iscsi_ioctl,
     .bdrv_aio_ioctl   = iscsi_aio_ioctl,
 #endif
+
+    .bdrv_detach_aio_context = iscsi_detach_aio_context,
+    .bdrv_attach_aio_context = iscsi_attach_aio_context,
 };
 
 static QemuOptsList qemu_iscsi_opts = {

block/linux-aio.c

@@ -177,6 +177,20 @@ out_free_aiocb:
     return NULL;
 }
 
+void laio_detach_aio_context(void *s_, AioContext *old_context)
+{
+    struct qemu_laio_state *s = s_;
+
+    aio_set_event_notifier(old_context, &s->e, NULL);
+}
+
+void laio_attach_aio_context(void *s_, AioContext *new_context)
+{
+    struct qemu_laio_state *s = s_;
+
+    aio_set_event_notifier(new_context, &s->e, qemu_laio_completion_cb);
+}
+
 void *laio_init(void)
 {
     struct qemu_laio_state *s;
@@ -190,8 +204,6 @@ void *laio_init(void)
         goto out_close_efd;
     }
 
-    qemu_aio_set_event_notifier(&s->e, qemu_laio_completion_cb);
-
     return s;
 
 out_close_efd:
@@ -200,3 +212,11 @@ out_free_state:
     g_free(s);
     return NULL;
 }
+
+void laio_cleanup(void *s_)
+{
+    struct qemu_laio_state *s = s_;
+
+    event_notifier_cleanup(&s->e);
+    g_free(s);
+}

block/mirror.c

@@ -118,7 +118,7 @@ static void mirror_write_complete(void *opaque, int ret)
 
         bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
         action = mirror_error_action(s, false, -ret);
-        if (action == BDRV_ACTION_REPORT && s->ret >= 0) {
+        if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) {
             s->ret = ret;
         }
     }
@@ -135,7 +135,7 @@ static void mirror_read_complete(void *opaque, int ret)
 
         bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
         action = mirror_error_action(s, true, -ret);
-        if (action == BDRV_ACTION_REPORT && s->ret >= 0) {
+        if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) {
             s->ret = ret;
         }
 
@@ -415,7 +415,8 @@ static void coroutine_fn mirror_run(void *opaque)
             trace_mirror_before_flush(s);
             ret = bdrv_flush(s->target);
             if (ret < 0) {
-                if (mirror_error_action(s, false, -ret) == BDRV_ACTION_REPORT) {
+                if (mirror_error_action(s, false, -ret) ==
+                    BLOCK_ERROR_ACTION_REPORT) {
                     goto immediate_exit;
                 }
             } else {
@@ -426,7 +427,7 @@ static void coroutine_fn mirror_run(void *opaque)
                  */
                 s->common.offset = end * BDRV_SECTOR_SIZE;
                 if (!s->synced) {
-                    block_job_ready(&s->common);
+                    block_job_event_ready(&s->common);
                     s->synced = true;
                 }
 

block/nbd-client.c

@@ -49,7 +49,7 @@ static void nbd_teardown_connection(NbdClientSession *client)
     shutdown(client->sock, 2);
     nbd_recv_coroutines_enter_all(client);
 
-    qemu_aio_set_fd_handler(client->sock, NULL, NULL, NULL);
+    nbd_client_session_detach_aio_context(client);
     closesocket(client->sock);
     client->sock = -1;
 }
@@ -103,11 +103,14 @@ static int nbd_co_send_request(NbdClientSession *s,
     struct nbd_request *request,
     QEMUIOVector *qiov, int offset)
 {
+    AioContext *aio_context;
     int rc, ret;
 
     qemu_co_mutex_lock(&s->send_mutex);
     s->send_coroutine = qemu_coroutine_self();
-    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write, s);
+    aio_context = bdrv_get_aio_context(s->bs);
+    aio_set_fd_handler(aio_context, s->sock,
+                       nbd_reply_ready, nbd_restart_write, s);
     if (qiov) {
         if (!s->is_unix) {
             socket_set_cork(s->sock, 1);
@@ -126,7 +129,7 @@ static int nbd_co_send_request(NbdClientSession *s,
     } else {
         rc = nbd_send_request(s->sock, request);
     }
-    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL, s);
+    aio_set_fd_handler(aio_context, s->sock, nbd_reply_ready, NULL, s);
     s->send_coroutine = NULL;
     qemu_co_mutex_unlock(&s->send_mutex);
     return rc;
@@ -335,6 +338,19 @@ int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
 
 }
 
+void nbd_client_session_detach_aio_context(NbdClientSession *client)
+{
+    aio_set_fd_handler(bdrv_get_aio_context(client->bs), client->sock,
+                       NULL, NULL, NULL);
+}
+
+void nbd_client_session_attach_aio_context(NbdClientSession *client,
+                                           AioContext *new_context)
+{
+    aio_set_fd_handler(new_context, client->sock,
+                       nbd_reply_ready, NULL, client);
+}
+
 void nbd_client_session_close(NbdClientSession *client)
 {
     struct nbd_request request = {
@@ -381,7 +397,7 @@ int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
     /* Now that we're connected, set the socket to be non-blocking and
      * kick the reply mechanism.  */
     qemu_set_nonblock(sock);
-    qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL, client);
+    nbd_client_session_attach_aio_context(client, bdrv_get_aio_context(bs));
 
     logout("Established connection with NBD server\n");
     return 0;

block/nbd-client.h

@@ -47,4 +47,8 @@ int nbd_client_session_co_writev(NbdClientSession *client, int64_t sector_num,
 int nbd_client_session_co_readv(NbdClientSession *client, int64_t sector_num,
                                 int nb_sectors, QEMUIOVector *qiov);
 
+void nbd_client_session_detach_aio_context(NbdClientSession *client);
+void nbd_client_session_attach_aio_context(NbdClientSession *client,
+                                           AioContext *new_context);
+
 #endif /* NBD_CLIENT_H */

block/nbd.c

@@ -323,46 +323,67 @@ static int64_t nbd_getlength(BlockDriverState *bs)
     return s->client.size;
 }
 
+static void nbd_detach_aio_context(BlockDriverState *bs)
+{
+    BDRVNBDState *s = bs->opaque;
+
+    nbd_client_session_detach_aio_context(&s->client);
+}
+
+static void nbd_attach_aio_context(BlockDriverState *bs,
+                                   AioContext *new_context)
+{
+    BDRVNBDState *s = bs->opaque;
+
+    nbd_client_session_attach_aio_context(&s->client, new_context);
+}
+
 static BlockDriver bdrv_nbd = {
-    .format_name         = "nbd",
-    .protocol_name       = "nbd",
-    .instance_size       = sizeof(BDRVNBDState),
-    .bdrv_parse_filename = nbd_parse_filename,
-    .bdrv_file_open      = nbd_open,
-    .bdrv_co_readv       = nbd_co_readv,
-    .bdrv_co_writev      = nbd_co_writev,
-    .bdrv_close          = nbd_close,
-    .bdrv_co_flush_to_os = nbd_co_flush,
-    .bdrv_co_discard     = nbd_co_discard,
-    .bdrv_getlength      = nbd_getlength,
+    .format_name                = "nbd",
+    .protocol_name              = "nbd",
+    .instance_size              = sizeof(BDRVNBDState),
+    .bdrv_parse_filename        = nbd_parse_filename,
+    .bdrv_file_open             = nbd_open,
+    .bdrv_co_readv              = nbd_co_readv,
+    .bdrv_co_writev             = nbd_co_writev,
+    .bdrv_close                 = nbd_close,
+    .bdrv_co_flush_to_os        = nbd_co_flush,
+    .bdrv_co_discard            = nbd_co_discard,
+    .bdrv_getlength             = nbd_getlength,
+    .bdrv_detach_aio_context    = nbd_detach_aio_context,
+    .bdrv_attach_aio_context    = nbd_attach_aio_context,
 };
 
 static BlockDriver bdrv_nbd_tcp = {
-    .format_name         = "nbd",
-    .protocol_name       = "nbd+tcp",
-    .instance_size       = sizeof(BDRVNBDState),
-    .bdrv_parse_filename = nbd_parse_filename,
-    .bdrv_file_open      = nbd_open,
-    .bdrv_co_readv       = nbd_co_readv,
-    .bdrv_co_writev      = nbd_co_writev,
-    .bdrv_close          = nbd_close,
-    .bdrv_co_flush_to_os = nbd_co_flush,
-    .bdrv_co_discard     = nbd_co_discard,
-    .bdrv_getlength      = nbd_getlength,
+    .format_name                = "nbd",
+    .protocol_name              = "nbd+tcp",
+    .instance_size              = sizeof(BDRVNBDState),
+    .bdrv_parse_filename        = nbd_parse_filename,
+    .bdrv_file_open             = nbd_open,
+    .bdrv_co_readv              = nbd_co_readv,
+    .bdrv_co_writev             = nbd_co_writev,
+    .bdrv_close                 = nbd_close,
+    .bdrv_co_flush_to_os        = nbd_co_flush,
+    .bdrv_co_discard            = nbd_co_discard,
+    .bdrv_getlength             = nbd_getlength,
+    .bdrv_detach_aio_context    = nbd_detach_aio_context,
+    .bdrv_attach_aio_context    = nbd_attach_aio_context,
 };
 
 static BlockDriver bdrv_nbd_unix = {
-    .format_name         = "nbd",
-    .protocol_name       = "nbd+unix",
-    .instance_size       = sizeof(BDRVNBDState),
-    .bdrv_parse_filename = nbd_parse_filename,
-    .bdrv_file_open      = nbd_open,
-    .bdrv_co_readv       = nbd_co_readv,
-    .bdrv_co_writev      = nbd_co_writev,
-    .bdrv_close          = nbd_close,
-    .bdrv_co_flush_to_os = nbd_co_flush,
-    .bdrv_co_discard     = nbd_co_discard,
-    .bdrv_getlength      = nbd_getlength,
+    .format_name                = "nbd",
+    .protocol_name              = "nbd+unix",
+    .instance_size              = sizeof(BDRVNBDState),
+    .bdrv_parse_filename        = nbd_parse_filename,
+    .bdrv_file_open             = nbd_open,
+    .bdrv_co_readv              = nbd_co_readv,
+    .bdrv_co_writev             = nbd_co_writev,
+    .bdrv_close                 = nbd_close,
+    .bdrv_co_flush_to_os        = nbd_co_flush,
+    .bdrv_co_discard            = nbd_co_discard,
+    .bdrv_getlength             = nbd_getlength,
+    .bdrv_detach_aio_context    = nbd_detach_aio_context,
+    .bdrv_attach_aio_context    = nbd_attach_aio_context,
 };
 
 static void bdrv_nbd_init(void)

block/nfs.c

@@ -40,6 +40,7 @@ typedef struct NFSClient {
     struct nfsfh *fh;
     int events;
     bool has_zero_init;
+    AioContext *aio_context;
 } NFSClient;
 
 typedef struct NFSRPC {
@@ -49,6 +50,7 @@ typedef struct NFSRPC {
     struct stat *st;
     Coroutine *co;
     QEMUBH *bh;
+    NFSClient *client;
 } NFSRPC;
 
 static void nfs_process_read(void *arg);
@@ -58,10 +60,11 @@ static void nfs_set_events(NFSClient *client)
 {
     int ev = nfs_which_events(client->context);
     if (ev != client->events) {
-        qemu_aio_set_fd_handler(nfs_get_fd(client->context),
-                      (ev & POLLIN) ? nfs_process_read : NULL,
-                      (ev & POLLOUT) ? nfs_process_write : NULL,
-                      client);
+        aio_set_fd_handler(client->aio_context,
+                           nfs_get_fd(client->context),
+                           (ev & POLLIN) ? nfs_process_read : NULL,
+                           (ev & POLLOUT) ? nfs_process_write : NULL,
+                           client);
 
     }
     client->events = ev;
@@ -84,13 +87,15 @@ static void nfs_process_write(void *arg)
 static void nfs_co_init_task(NFSClient *client, NFSRPC *task)
 {
     *task = (NFSRPC) {
-        .co         = qemu_coroutine_self(),
+        .co             = qemu_coroutine_self(),
+        .client         = client,
     };
 }
 
 static void nfs_co_generic_bh_cb(void *opaque)
 {
     NFSRPC *task = opaque;
+    task->complete = 1;
     qemu_bh_delete(task->bh);
     qemu_coroutine_enter(task->co, NULL);
 }
@@ -100,7 +105,6 @@ nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
                   void *private_data)
 {
     NFSRPC *task = private_data;
-    task->complete = 1;
     task->ret = ret;
     if (task->ret > 0 && task->iov) {
         if (task->ret <= task->iov->size) {
@@ -116,8 +120,11 @@ nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
         error_report("NFS Error: %s", nfs_get_error(nfs));
     }
     if (task->co) {
-        task->bh = qemu_bh_new(nfs_co_generic_bh_cb, task);
+        task->bh = aio_bh_new(task->client->aio_context,
+                              nfs_co_generic_bh_cb, task);
         qemu_bh_schedule(task->bh);
+    } else {
+        task->complete = 1;
     }
 }
 
@@ -224,13 +231,34 @@ static QemuOptsList runtime_opts = {
     },
 };
 
+static void nfs_detach_aio_context(BlockDriverState *bs)
+{
+    NFSClient *client = bs->opaque;
+
+    aio_set_fd_handler(client->aio_context,
+                       nfs_get_fd(client->context),
+                       NULL, NULL, NULL);
+    client->events = 0;
+}
+
+static void nfs_attach_aio_context(BlockDriverState *bs,
+                                   AioContext *new_context)
+{
+    NFSClient *client = bs->opaque;
+
+    client->aio_context = new_context;
+    nfs_set_events(client);
+}
+
 static void nfs_client_close(NFSClient *client)
 {
     if (client->context) {
         if (client->fh) {
             nfs_close(client->context, client->fh);
         }
-        qemu_aio_set_fd_handler(nfs_get_fd(client->context), NULL, NULL, NULL);
+        aio_set_fd_handler(client->aio_context,
+                           nfs_get_fd(client->context),
+                           NULL, NULL, NULL);
         nfs_destroy_context(client->context);
     }
     memset(client, 0, sizeof(NFSClient));
@@ -345,6 +373,8 @@ static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
     QemuOpts *opts;
     Error *local_err = NULL;
 
+    client->aio_context = bdrv_get_aio_context(bs);
+
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
@@ -361,20 +391,16 @@ static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
     return 0;
 }
 
-static int nfs_file_create(const char *url, QEMUOptionParameter *options,
-                           Error **errp)
+static int nfs_file_create(const char *url, QemuOpts *opts, Error **errp)
 {
     int ret = 0;
     int64_t total_size = 0;
     NFSClient *client = g_malloc0(sizeof(NFSClient));
 
+    client->aio_context = qemu_get_aio_context();
+
     /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, "size")) {
-            total_size = options->value.n;
-        }
-        options++;
-    }
+    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
 
     ret = nfs_client_open(client, url, O_CREAT, errp);
     if (ret < 0) {
@@ -407,7 +433,7 @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
 
     while (!task.complete) {
         nfs_set_events(client);
-        qemu_aio_wait();
+        aio_poll(client->aio_context, true);
     }
 
     return (task.ret < 0 ? task.ret : st.st_blocks * st.st_blksize);
@@ -420,22 +446,25 @@ static int nfs_file_truncate(BlockDriverState *bs, int64_t offset)
 }
 
 static BlockDriver bdrv_nfs = {
-    .format_name     = "nfs",
-    .protocol_name   = "nfs",
+    .format_name                    = "nfs",
+    .protocol_name                  = "nfs",
 
-    .instance_size   = sizeof(NFSClient),
-    .bdrv_needs_filename = true,
-    .bdrv_has_zero_init = nfs_has_zero_init,
-    .bdrv_get_allocated_file_size = nfs_get_allocated_file_size,
-    .bdrv_truncate = nfs_file_truncate,
+    .instance_size                  = sizeof(NFSClient),
+    .bdrv_needs_filename            = true,
+    .bdrv_has_zero_init             = nfs_has_zero_init,
+    .bdrv_get_allocated_file_size   = nfs_get_allocated_file_size,
+    .bdrv_truncate                  = nfs_file_truncate,
 
-    .bdrv_file_open  = nfs_file_open,
-    .bdrv_close      = nfs_file_close,
-    .bdrv_create     = nfs_file_create,
+    .bdrv_file_open                 = nfs_file_open,
+    .bdrv_close                     = nfs_file_close,
+    .bdrv_create                    = nfs_file_create,
 
-    .bdrv_co_readv         = nfs_co_readv,
-    .bdrv_co_writev        = nfs_co_writev,
-    .bdrv_co_flush_to_disk = nfs_co_flush,
+    .bdrv_co_readv                  = nfs_co_readv,
+    .bdrv_co_writev                 = nfs_co_writev,
+    .bdrv_co_flush_to_disk          = nfs_co_flush,
+
+    .bdrv_detach_aio_context        = nfs_detach_aio_context,
+    .bdrv_attach_aio_context        = nfs_attach_aio_context,
 };
 
 static void nfs_block_init(void)

block/qcow.c

@@ -693,35 +693,29 @@ static void qcow_close(BlockDriverState *bs)
     error_free(s->migration_blocker);
 }
 
-static int qcow_create(const char *filename, QEMUOptionParameter *options,
-                       Error **errp)
+static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     int header_size, backing_filename_len, l1_size, shift, i;
     QCowHeader header;
     uint8_t *tmp;
     int64_t total_size = 0;
-    const char *backing_file = NULL;
+    char *backing_file = NULL;
     int flags = 0;
     Error *local_err = NULL;
     int ret;
     BlockDriverState *qcow_bs;
 
     /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            total_size = options->value.n / 512;
-        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
-            backing_file = options->value.s;
-        } else if (!strcmp(options->name, BLOCK_OPT_ENCRYPT)) {
-            flags |= options->value.n ? BLOCK_FLAG_ENCRYPT : 0;
-        }
-        options++;
+    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
+    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
+    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
+        flags |= BLOCK_FLAG_ENCRYPT;
     }
 
-    ret = bdrv_create_file(filename, options, &local_err);
+    ret = bdrv_create_file(filename, opts, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
-        return ret;
+        goto cleanup;
     }
 
     qcow_bs = NULL;
@@ -729,7 +723,7 @@ static int qcow_create(const char *filename, QEMUOptionParameter *options,
                     BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
-        return ret;
+        goto cleanup;
     }
 
     ret = bdrv_truncate(qcow_bs, 0);
@@ -800,6 +794,8 @@ static int qcow_create(const char *filename, QEMUOptionParameter *options,
     ret = 0;
 exit:
     bdrv_unref(qcow_bs);
+cleanup:
+    g_free(backing_file);
     return ret;
 }
 
@@ -912,24 +908,28 @@ static int qcow_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     return 0;
 }
 
-
-static QEMUOptionParameter qcow_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    {
-        .name = BLOCK_OPT_BACKING_FILE,
-        .type = OPT_STRING,
-        .help = "File name of a base image"
-    },
-    {
-        .name = BLOCK_OPT_ENCRYPT,
-        .type = OPT_FLAG,
-        .help = "Encrypt the image"
-    },
-    { NULL }
+static QemuOptsList qcow_create_opts = {
+    .name = "qcow-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(qcow_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        {
+            .name = BLOCK_OPT_BACKING_FILE,
+            .type = QEMU_OPT_STRING,
+            .help = "File name of a base image"
+        },
+        {
+            .name = BLOCK_OPT_ENCRYPT,
+            .type = QEMU_OPT_BOOL,
+            .help = "Encrypt the image",
+            .def_value_str = "off"
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_qcow = {
@@ -938,8 +938,8 @@ static BlockDriver bdrv_qcow = {
     .bdrv_probe		= qcow_probe,
     .bdrv_open		= qcow_open,
     .bdrv_close		= qcow_close,
-    .bdrv_reopen_prepare = qcow_reopen_prepare,
-    .bdrv_create	= qcow_create,
+    .bdrv_reopen_prepare    = qcow_reopen_prepare,
+    .bdrv_create            = qcow_create,
     .bdrv_has_zero_init     = bdrv_has_zero_init_1,
 
     .bdrv_co_readv          = qcow_co_readv,
@@ -951,7 +951,7 @@ static BlockDriver bdrv_qcow = {
     .bdrv_write_compressed  = qcow_write_compressed,
     .bdrv_get_info          = qcow_get_info,
 
-    .create_options = qcow_create_options,
+    .create_opts            = &qcow_create_opts,
 };
 
 static void bdrv_qcow_init(void)

block/qcow2-refcount.c

@@ -27,6 +27,7 @@
 #include "block/qcow2.h"
 #include "qemu/range.h"
 #include "qapi/qmp/types.h"
+#include "qapi-event.h"
 
 static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size);
 static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
@@ -1807,7 +1808,6 @@ int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
     } else if (ret > 0) {
         int metadata_ol_bitnr = ffs(ret) - 1;
         char *message;
-        QObject *data;
 
         assert(metadata_ol_bitnr < QCOW2_OL_MAX_BITNR);
 
@@ -1816,12 +1816,14 @@ int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
                 metadata_ol_names[metadata_ol_bitnr]);
         message = g_strdup_printf("Prevented %s overwrite",
                 metadata_ol_names[metadata_ol_bitnr]);
-        data = qobject_from_jsonf("{ 'device': %s, 'msg': %s, 'offset': %"
-                PRId64 ", 'size': %" PRId64 " }", bs->device_name, message,
-                offset, size);
-        monitor_protocol_event(QEVENT_BLOCK_IMAGE_CORRUPTED, data);
+        qapi_event_send_block_image_corrupted(bdrv_get_device_name(bs),
+                                              message,
+                                              true,
+                                              offset,
+                                              true,
+                                              size,
+                                              &error_abort);
         g_free(message);
-        qobject_decref(data);
 
         qcow2_mark_corrupt(bs);
         bs->drv = NULL; /* make BDS unusable */

block/qcow2.c

@@ -31,6 +31,7 @@
 #include "qapi/qmp/qerror.h"
 #include "qapi/qmp/qbool.h"
 #include "trace.h"
+#include "qemu/option_int.h"
 
 /*
   Differences with QCOW:
@@ -1594,7 +1595,7 @@ static int preallocate(BlockDriverState *bs)
 static int qcow2_create2(const char *filename, int64_t total_size,
                          const char *backing_file, const char *backing_format,
                          int flags, size_t cluster_size, int prealloc,
-                         QEMUOptionParameter *options, int version,
+                         QemuOpts *opts, int version,
                          Error **errp)
 {
     /* Calculate cluster_bits */
@@ -1626,7 +1627,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     Error *local_err = NULL;
     int ret;
 
-    ret = bdrv_create_file(filename, options, &local_err);
+    ret = bdrv_create_file(filename, opts, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         return ret;
@@ -1762,11 +1763,11 @@ out:
     return ret;
 }
 
-static int qcow2_create(const char *filename, QEMUOptionParameter *options,
-                        Error **errp)
+static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
 {
-    const char *backing_file = NULL;
-    const char *backing_fmt = NULL;
+    char *backing_file = NULL;
+    char *backing_fmt = NULL;
+    char *buf = NULL;
     uint64_t sectors = 0;
     int flags = 0;
     size_t cluster_size = DEFAULT_CLUSTER_SIZE;
@@ -1776,64 +1777,66 @@ static int qcow2_create(const char *filename, QEMUOptionParameter *options,
     int ret;
 
     /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            sectors = options->value.n / 512;
-        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
-            backing_file = options->value.s;
-        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FMT)) {
-            backing_fmt = options->value.s;
-        } else if (!strcmp(options->name, BLOCK_OPT_ENCRYPT)) {
-            flags |= options->value.n ? BLOCK_FLAG_ENCRYPT : 0;
-        } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
-            if (options->value.n) {
-                cluster_size = options->value.n;
-            }
-        } else if (!strcmp(options->name, BLOCK_OPT_PREALLOC)) {
-            if (!options->value.s || !strcmp(options->value.s, "off")) {
-                prealloc = 0;
-            } else if (!strcmp(options->value.s, "metadata")) {
-                prealloc = 1;
-            } else {
-                error_setg(errp, "Invalid preallocation mode: '%s'",
-                           options->value.s);
-                return -EINVAL;
-            }
-        } else if (!strcmp(options->name, BLOCK_OPT_COMPAT_LEVEL)) {
-            if (!options->value.s) {
-                /* keep the default */
-            } else if (!strcmp(options->value.s, "0.10")) {
-                version = 2;
-            } else if (!strcmp(options->value.s, "1.1")) {
-                version = 3;
-            } else {
-                error_setg(errp, "Invalid compatibility level: '%s'",
-                           options->value.s);
-                return -EINVAL;
-            }
-        } else if (!strcmp(options->name, BLOCK_OPT_LAZY_REFCOUNTS)) {
-            flags |= options->value.n ? BLOCK_FLAG_LAZY_REFCOUNTS : 0;
-        }
-        options++;
+    sectors = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
+    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
+    backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT);
+    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
+        flags |= BLOCK_FLAG_ENCRYPT;
+    }
+    cluster_size = qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE,
+                                         DEFAULT_CLUSTER_SIZE);
+    buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
+    if (!buf || !strcmp(buf, "off")) {
+        prealloc = 0;
+    } else if (!strcmp(buf, "metadata")) {
+        prealloc = 1;
+    } else {
+        error_setg(errp, "Invalid preallocation mode: '%s'", buf);
+        ret = -EINVAL;
+        goto finish;
+    }
+    g_free(buf);
+    buf = qemu_opt_get_del(opts, BLOCK_OPT_COMPAT_LEVEL);
+    if (!buf) {
+        /* keep the default */
+    } else if (!strcmp(buf, "0.10")) {
+        version = 2;
+    } else if (!strcmp(buf, "1.1")) {
+        version = 3;
+    } else {
+        error_setg(errp, "Invalid compatibility level: '%s'", buf);
+        ret = -EINVAL;
+        goto finish;
+    }
+
+    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_LAZY_REFCOUNTS, false)) {
+        flags |= BLOCK_FLAG_LAZY_REFCOUNTS;
     }
 
     if (backing_file && prealloc) {
         error_setg(errp, "Backing file and preallocation cannot be used at "
                    "the same time");
-        return -EINVAL;
+        ret = -EINVAL;
+        goto finish;
     }
 
     if (version < 3 && (flags & BLOCK_FLAG_LAZY_REFCOUNTS)) {
         error_setg(errp, "Lazy refcounts only supported with compatibility "
                    "level 1.1 and above (use compat=1.1 or greater)");
-        return -EINVAL;
+        ret = -EINVAL;
+        goto finish;
     }
 
     ret = qcow2_create2(filename, sectors, backing_file, backing_fmt, flags,
-                        cluster_size, prealloc, options, version, &local_err);
+                        cluster_size, prealloc, opts, version, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
     }
+
+finish:
+    g_free(backing_file);
+    g_free(backing_fmt);
+    g_free(buf);
     return ret;
 }
 
@@ -2198,64 +2201,72 @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version)
     return 0;
 }
 
-static int qcow2_amend_options(BlockDriverState *bs,
-                               QEMUOptionParameter *options)
+static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts)
 {
     BDRVQcowState *s = bs->opaque;
     int old_version = s->qcow_version, new_version = old_version;
     uint64_t new_size = 0;
     const char *backing_file = NULL, *backing_format = NULL;
     bool lazy_refcounts = s->use_lazy_refcounts;
+    const char *compat = NULL;
+    uint64_t cluster_size = s->cluster_size;
+    bool encrypt;
     int ret;
-    int i;
+    QemuOptDesc *desc = opts->list->desc;
 
-    for (i = 0; options[i].name; i++)
-    {
-        if (!options[i].assigned) {
+    while (desc && desc->name) {
+        if (!qemu_opt_find(opts, desc->name)) {
             /* only change explicitly defined options */
+            desc++;
             continue;
         }
 
-        if (!strcmp(options[i].name, "compat")) {
-            if (!options[i].value.s) {
+        if (!strcmp(desc->name, "compat")) {
+            compat = qemu_opt_get(opts, "compat");
+            if (!compat) {
                 /* preserve default */
-            } else if (!strcmp(options[i].value.s, "0.10")) {
+            } else if (!strcmp(compat, "0.10")) {
                 new_version = 2;
-            } else if (!strcmp(options[i].value.s, "1.1")) {
+            } else if (!strcmp(compat, "1.1")) {
                 new_version = 3;
             } else {
-                fprintf(stderr, "Unknown compatibility level %s.\n",
-                        options[i].value.s);
+                fprintf(stderr, "Unknown compatibility level %s.\n", compat);
                 return -EINVAL;
             }
-        } else if (!strcmp(options[i].name, "preallocation")) {
+        } else if (!strcmp(desc->name, "preallocation")) {
             fprintf(stderr, "Cannot change preallocation mode.\n");
             return -ENOTSUP;
-        } else if (!strcmp(options[i].name, "size")) {
-            new_size = options[i].value.n;
-        } else if (!strcmp(options[i].name, "backing_file")) {
-            backing_file = options[i].value.s;
-        } else if (!strcmp(options[i].name, "backing_fmt")) {
-            backing_format = options[i].value.s;
-        } else if (!strcmp(options[i].name, "encryption")) {
-            if ((options[i].value.n != !!s->crypt_method)) {
+        } else if (!strcmp(desc->name, "size")) {
+            new_size = qemu_opt_get_size(opts, "size", 0);
+        } else if (!strcmp(desc->name, "backing_file")) {
+            backing_file = qemu_opt_get(opts, "backing_file");
+        } else if (!strcmp(desc->name, "backing_fmt")) {
+            backing_format = qemu_opt_get(opts, "backing_fmt");
+        } else if (!strcmp(desc->name, "encryption")) {
+            encrypt = qemu_opt_get_bool(opts, "encryption", s->crypt_method);
+            if (encrypt != !!s->crypt_method) {
                 fprintf(stderr, "Changing the encryption flag is not "
                         "supported.\n");
                 return -ENOTSUP;
             }
-        } else if (!strcmp(options[i].name, "cluster_size")) {
-            if (options[i].value.n != s->cluster_size) {
+        } else if (!strcmp(desc->name, "cluster_size")) {
+            cluster_size = qemu_opt_get_size(opts, "cluster_size",
+                                             cluster_size);
+            if (cluster_size != s->cluster_size) {
                 fprintf(stderr, "Changing the cluster size is not "
                         "supported.\n");
                 return -ENOTSUP;
             }
-        } else if (!strcmp(options[i].name, "lazy_refcounts")) {
-            lazy_refcounts = options[i].value.n;
+        } else if (!strcmp(desc->name, "lazy_refcounts")) {
+            lazy_refcounts = qemu_opt_get_bool(opts, "lazy_refcounts",
+                                               lazy_refcounts);
         } else {
             /* if this assertion fails, this probably means a new option was
              * added without having it covered here */
             assert(false);
         }
+
+        desc++;
     }
 
     if (new_version != old_version) {
@@ -2324,49 +2335,55 @@ static int qcow2_amend_options(BlockDriverState *bs,
     return 0;
 }
 
-static QEMUOptionParameter qcow2_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    {
-        .name = BLOCK_OPT_COMPAT_LEVEL,
-        .type = OPT_STRING,
-        .help = "Compatibility level (0.10 or 1.1)"
-    },
-    {
-        .name = BLOCK_OPT_BACKING_FILE,
-        .type = OPT_STRING,
-        .help = "File name of a base image"
-    },
-    {
-        .name = BLOCK_OPT_BACKING_FMT,
-        .type = OPT_STRING,
-        .help = "Image format of the base image"
-    },
-    {
-        .name = BLOCK_OPT_ENCRYPT,
-        .type = OPT_FLAG,
-        .help = "Encrypt the image"
-    },
-    {
-        .name = BLOCK_OPT_CLUSTER_SIZE,
-        .type = OPT_SIZE,
-        .help = "qcow2 cluster size",
-        .value = { .n = DEFAULT_CLUSTER_SIZE },
-    },
-    {
-        .name = BLOCK_OPT_PREALLOC,
-        .type = OPT_STRING,
-        .help = "Preallocation mode (allowed values: off, metadata)"
-    },
-    {
-        .name = BLOCK_OPT_LAZY_REFCOUNTS,
-        .type = OPT_FLAG,
-        .help = "Postpone refcount updates",
-    },
-    { NULL }
+static QemuOptsList qcow2_create_opts = {
+    .name = "qcow2-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(qcow2_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        {
+            .name = BLOCK_OPT_COMPAT_LEVEL,
+            .type = QEMU_OPT_STRING,
+            .help = "Compatibility level (0.10 or 1.1)"
+        },
+        {
+            .name = BLOCK_OPT_BACKING_FILE,
+            .type = QEMU_OPT_STRING,
+            .help = "File name of a base image"
+        },
+        {
+            .name = BLOCK_OPT_BACKING_FMT,
+            .type = QEMU_OPT_STRING,
+            .help = "Image format of the base image"
+        },
+        {
+            .name = BLOCK_OPT_ENCRYPT,
+            .type = QEMU_OPT_BOOL,
+            .help = "Encrypt the image",
+            .def_value_str = "off"
+        },
+        {
+            .name = BLOCK_OPT_CLUSTER_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "qcow2 cluster size",
+            .def_value_str = stringify(DEFAULT_CLUSTER_SIZE)
+        },
+        {
+            .name = BLOCK_OPT_PREALLOC,
+            .type = QEMU_OPT_STRING,
+            .help = "Preallocation mode (allowed values: off, metadata)"
+        },
+        {
+            .name = BLOCK_OPT_LAZY_REFCOUNTS,
+            .type = QEMU_OPT_BOOL,
+            .help = "Postpone refcount updates",
+            .def_value_str = "off"
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_qcow2 = {
@@ -2394,8 +2411,8 @@ static BlockDriver bdrv_qcow2 = {
     .bdrv_snapshot_goto     = qcow2_snapshot_goto,
     .bdrv_snapshot_delete   = qcow2_snapshot_delete,
     .bdrv_snapshot_list     = qcow2_snapshot_list,
-    .bdrv_snapshot_load_tmp     = qcow2_snapshot_load_tmp,
-    .bdrv_get_info      = qcow2_get_info,
+    .bdrv_snapshot_load_tmp = qcow2_snapshot_load_tmp,
+    .bdrv_get_info          = qcow2_get_info,
     .bdrv_get_specific_info = qcow2_get_specific_info,
 
     .bdrv_save_vmstate    = qcow2_save_vmstate,
@@ -2406,9 +2423,9 @@ static BlockDriver bdrv_qcow2 = {
     .bdrv_refresh_limits        = qcow2_refresh_limits,
     .bdrv_invalidate_cache      = qcow2_invalidate_cache,
 
-    .create_options = qcow2_create_options,
-    .bdrv_check = qcow2_check,
-    .bdrv_amend_options = qcow2_amend_options,
+    .create_opts         = &qcow2_create_opts,
+    .bdrv_check          = qcow2_check,
+    .bdrv_amend_options  = qcow2_amend_options,
 };
 
 static void bdrv_qcow2_init(void)

block/qed-table.c

@@ -173,7 +173,7 @@ int qed_read_l1_table_sync(BDRVQEDState *s)
     qed_read_table(s, s->header.l1_table_offset,
                    s->l1_table, qed_sync_cb, &ret);
     while (ret == -EINPROGRESS) {
-        qemu_aio_wait();
+        aio_poll(bdrv_get_aio_context(s->bs), true);
     }
 
     return ret;
@@ -194,7 +194,7 @@ int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
 
     qed_write_l1_table(s, index, n, qed_sync_cb, &ret);
     while (ret == -EINPROGRESS) {
-        qemu_aio_wait();
+        aio_poll(bdrv_get_aio_context(s->bs), true);
     }
 
     return ret;
@@ -267,7 +267,7 @@ int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset
 
     qed_read_l2_table(s, request, offset, qed_sync_cb, &ret);
     while (ret == -EINPROGRESS) {
-        qemu_aio_wait();
+        aio_poll(bdrv_get_aio_context(s->bs), true);
     }
 
     return ret;
@@ -289,7 +289,7 @@ int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
 
     qed_write_l2_table(s, request, index, n, flush, qed_sync_cb, &ret);
     while (ret == -EINPROGRESS) {
-        qemu_aio_wait();
+        aio_poll(bdrv_get_aio_context(s->bs), true);
     }
 
     return ret;

block/qed.c

@@ -21,12 +21,13 @@
 static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
 {
     QEDAIOCB *acb = (QEDAIOCB *)blockacb;
+    AioContext *aio_context = bdrv_get_aio_context(blockacb->bs);
     bool finished = false;
 
     /* Wait for the request to finish */
     acb->finished = &finished;
     while (!finished) {
-        qemu_aio_wait();
+        aio_poll(aio_context, true);
     }
 }
 
@@ -373,6 +374,27 @@ static void bdrv_qed_rebind(BlockDriverState *bs)
     s->bs = bs;
 }
 
+static void bdrv_qed_detach_aio_context(BlockDriverState *bs)
+{
+    BDRVQEDState *s = bs->opaque;
+
+    qed_cancel_need_check_timer(s);
+    timer_free(s->need_check_timer);
+}
+
+static void bdrv_qed_attach_aio_context(BlockDriverState *bs,
+                                        AioContext *new_context)
+{
+    BDRVQEDState *s = bs->opaque;
+
+    s->need_check_timer = aio_timer_new(new_context,
+                                        QEMU_CLOCK_VIRTUAL, SCALE_NS,
+                                        qed_need_check_timer_cb, s);
+    if (s->header.features & QED_F_NEED_CHECK) {
+        qed_start_need_check_timer(s);
+    }
+}
+
 static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
                          Error **errp)
 {
@@ -496,8 +518,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
         }
     }
 
-    s->need_check_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
-                                            qed_need_check_timer_cb, s);
+    bdrv_qed_attach_aio_context(bs, bdrv_get_aio_context(bs));
 
 out:
     if (ret) {
@@ -528,8 +549,7 @@ static void bdrv_qed_close(BlockDriverState *bs)
 {
     BDRVQEDState *s = bs->opaque;
 
-    qed_cancel_need_check_timer(s);
-    timer_free(s->need_check_timer);
+    bdrv_qed_detach_aio_context(bs);
 
     /* Ensure writes reach stable storage */
     bdrv_flush(bs->file);
@@ -621,55 +641,53 @@ out:
     return ret;
 }
 
-static int bdrv_qed_create(const char *filename, QEMUOptionParameter *options,
-                           Error **errp)
+static int bdrv_qed_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     uint64_t image_size = 0;
     uint32_t cluster_size = QED_DEFAULT_CLUSTER_SIZE;
     uint32_t table_size = QED_DEFAULT_TABLE_SIZE;
-    const char *backing_file = NULL;
-    const char *backing_fmt = NULL;
+    char *backing_file = NULL;
+    char *backing_fmt = NULL;
+    int ret;
 
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            image_size = options->value.n;
-        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
-            backing_file = options->value.s;
-        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FMT)) {
-            backing_fmt = options->value.s;
-        } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
-            if (options->value.n) {
-                cluster_size = options->value.n;
-            }
-        } else if (!strcmp(options->name, BLOCK_OPT_TABLE_SIZE)) {
-            if (options->value.n) {
-                table_size = options->value.n;
-            }
-        }
-        options++;
-    }
+    image_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
+    backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT);
+    cluster_size = qemu_opt_get_size_del(opts,
+                                         BLOCK_OPT_CLUSTER_SIZE,
+                                         QED_DEFAULT_CLUSTER_SIZE);
+    table_size = qemu_opt_get_size_del(opts, BLOCK_OPT_TABLE_SIZE,
+                                       QED_DEFAULT_TABLE_SIZE);
 
     if (!qed_is_cluster_size_valid(cluster_size)) {
         error_setg(errp, "QED cluster size must be within range [%u, %u] "
                          "and power of 2",
                    QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE);
-        return -EINVAL;
+        ret = -EINVAL;
+        goto finish;
     }
     if (!qed_is_table_size_valid(table_size)) {
         error_setg(errp, "QED table size must be within range [%u, %u] "
                          "and power of 2",
                    QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE);
-        return -EINVAL;
+        ret = -EINVAL;
+        goto finish;
     }
     if (!qed_is_image_size_valid(image_size, cluster_size, table_size)) {
         error_setg(errp, "QED image size must be a non-zero multiple of "
                          "cluster size and less than %" PRIu64 " bytes",
                    qed_max_image_size(cluster_size, table_size));
-        return -EINVAL;
+        ret = -EINVAL;
+        goto finish;
     }
 
-    return qed_create(filename, cluster_size, image_size, table_size,
-                      backing_file, backing_fmt, errp);
+    ret = qed_create(filename, cluster_size, image_size, table_size,
+                     backing_file, backing_fmt, errp);
+
+finish:
+    g_free(backing_file);
+    g_free(backing_fmt);
+    return ret;
 }
 
 typedef struct {
@@ -919,7 +937,8 @@ static void qed_aio_complete(QEDAIOCB *acb, int ret)
 
     /* Arrange for a bh to invoke the completion function */
     acb->bh_ret = ret;
-    acb->bh = qemu_bh_new(qed_aio_complete_bh, acb);
+    acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
+                         qed_aio_complete_bh, acb);
     qemu_bh_schedule(acb->bh);
 
     /* Start next allocating write request waiting behind this one.  Note that
@@ -1595,36 +1614,44 @@ static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result,
     return qed_check(s, result, !!fix);
 }
 
-static QEMUOptionParameter qed_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size (in bytes)"
-    }, {
-        .name = BLOCK_OPT_BACKING_FILE,
-        .type = OPT_STRING,
-        .help = "File name of a base image"
-    }, {
-        .name = BLOCK_OPT_BACKING_FMT,
-        .type = OPT_STRING,
-        .help = "Image format of the base image"
-    }, {
-        .name = BLOCK_OPT_CLUSTER_SIZE,
-        .type = OPT_SIZE,
-        .help = "Cluster size (in bytes)",
-        .value = { .n = QED_DEFAULT_CLUSTER_SIZE },
-    }, {
-        .name = BLOCK_OPT_TABLE_SIZE,
-        .type = OPT_SIZE,
-        .help = "L1/L2 table size (in clusters)"
-    },
-    { /* end of list */ }
+static QemuOptsList qed_create_opts = {
+    .name = "qed-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(qed_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        {
+            .name = BLOCK_OPT_BACKING_FILE,
+            .type = QEMU_OPT_STRING,
+            .help = "File name of a base image"
+        },
+        {
+            .name = BLOCK_OPT_BACKING_FMT,
+            .type = QEMU_OPT_STRING,
+            .help = "Image format of the base image"
+        },
+        {
+            .name = BLOCK_OPT_CLUSTER_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Cluster size (in bytes)",
+            .def_value_str = stringify(QED_DEFAULT_CLUSTER_SIZE)
+        },
+        {
+            .name = BLOCK_OPT_TABLE_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "L1/L2 table size (in clusters)"
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_qed = {
     .format_name              = "qed",
     .instance_size            = sizeof(BDRVQEDState),
-    .create_options           = qed_create_options,
+    .create_opts              = &qed_create_opts,
 
     .bdrv_probe               = bdrv_qed_probe,
     .bdrv_rebind              = bdrv_qed_rebind,
@@ -1644,6 +1671,8 @@ static BlockDriver bdrv_qed = {
     .bdrv_change_backing_file = bdrv_qed_change_backing_file,
     .bdrv_invalidate_cache    = bdrv_qed_invalidate_cache,
     .bdrv_check               = bdrv_qed_check,
+    .bdrv_detach_aio_context  = bdrv_qed_detach_aio_context,
+    .bdrv_attach_aio_context  = bdrv_qed_attach_aio_context,
 };
 
 static void bdrv_qed_init(void)

block/qed.h

@@ -43,7 +43,7 @@
  *
  * All fields are little-endian on disk.
  */
-
+#define  QED_DEFAULT_CLUSTER_SIZE  65536
 enum {
     QED_MAGIC = 'Q' | 'E' << 8 | 'D' << 16 | '\0' << 24,
 
@@ -69,7 +69,6 @@ enum {
      */
     QED_MIN_CLUSTER_SIZE = 4 * 1024, /* in bytes */
     QED_MAX_CLUSTER_SIZE = 64 * 1024 * 1024,
-    QED_DEFAULT_CLUSTER_SIZE = 64 * 1024,
 
     /* Allocated clusters are tracked using a 2-level pagetable.  Table size is
      * a multiple of clusters so large maximum image sizes can be supported

block/quorum.c

@@ -17,6 +17,7 @@
 #include <gnutls/crypto.h>
 #include "block/block_int.h"
 #include "qapi/qmp/qjson.h"
+#include "qapi-event.h"
 
 #define HASH_LENGTH 32
 
@@ -198,32 +199,22 @@ static QuorumAIOCB *quorum_aio_get(BDRVQuorumState *s,
 
 static void quorum_report_bad(QuorumAIOCB *acb, char *node_name, int ret)
 {
-    QObject *data;
-    assert(node_name);
-    data = qobject_from_jsonf("{ 'node-name': %s"
-                              ", 'sector-num': %" PRId64
-                              ", 'sectors-count': %d }",
-                              node_name, acb->sector_num, acb->nb_sectors);
+    const char *msg = NULL;
     if (ret < 0) {
-        QDict *dict = qobject_to_qdict(data);
-        qdict_put(dict, "error", qstring_from_str(strerror(-ret)));
+        msg = strerror(-ret);
     }
-    monitor_protocol_event(QEVENT_QUORUM_REPORT_BAD, data);
-    qobject_decref(data);
+    qapi_event_send_quorum_report_bad(!!msg, msg, node_name,
+                                      acb->sector_num, acb->nb_sectors, &error_abort);
 }
 
 static void quorum_report_failure(QuorumAIOCB *acb)
 {
-    QObject *data;
     const char *reference = acb->common.bs->device_name[0] ?
                             acb->common.bs->device_name :
                             acb->common.bs->node_name;
-    data = qobject_from_jsonf("{ 'reference': %s"
-                              ", 'sector-num': %" PRId64
-                              ", 'sectors-count': %d }",
-                              reference, acb->sector_num, acb->nb_sectors);
-    monitor_protocol_event(QEVENT_QUORUM_FAILURE, data);
-    qobject_decref(data);
+
+    qapi_event_send_quorum_failure(reference, acb->sector_num,
+                                   acb->nb_sectors, &error_abort);
 }
 
 static int quorum_vote_error(QuorumAIOCB *acb);
@@ -848,25 +839,49 @@ static void quorum_close(BlockDriverState *bs)
     g_free(s->bs);
 }
 
+static void quorum_detach_aio_context(BlockDriverState *bs)
+{
+    BDRVQuorumState *s = bs->opaque;
+    int i;
+
+    for (i = 0; i < s->num_children; i++) {
+        bdrv_detach_aio_context(s->bs[i]);
+    }
+}
+
+static void quorum_attach_aio_context(BlockDriverState *bs,
+                                      AioContext *new_context)
+{
+    BDRVQuorumState *s = bs->opaque;
+    int i;
+
+    for (i = 0; i < s->num_children; i++) {
+        bdrv_attach_aio_context(s->bs[i], new_context);
+    }
+}
+
 static BlockDriver bdrv_quorum = {
-    .format_name        = "quorum",
-    .protocol_name      = "quorum",
+    .format_name                        = "quorum",
+    .protocol_name                      = "quorum",
 
-    .instance_size      = sizeof(BDRVQuorumState),
+    .instance_size                      = sizeof(BDRVQuorumState),
 
-    .bdrv_file_open     = quorum_open,
-    .bdrv_close         = quorum_close,
+    .bdrv_file_open                     = quorum_open,
+    .bdrv_close                         = quorum_close,
 
-    .bdrv_co_flush_to_disk = quorum_co_flush,
+    .bdrv_co_flush_to_disk              = quorum_co_flush,
 
-    .bdrv_getlength     = quorum_getlength,
+    .bdrv_getlength                     = quorum_getlength,
 
-    .bdrv_aio_readv     = quorum_aio_readv,
-    .bdrv_aio_writev    = quorum_aio_writev,
-    .bdrv_invalidate_cache = quorum_invalidate_cache,
+    .bdrv_aio_readv                     = quorum_aio_readv,
+    .bdrv_aio_writev                    = quorum_aio_writev,
+    .bdrv_invalidate_cache              = quorum_invalidate_cache,
 
-    .is_filter           = true,
-    .bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter,
+    .bdrv_detach_aio_context            = quorum_detach_aio_context,
+    .bdrv_attach_aio_context            = quorum_attach_aio_context,
+
+    .is_filter                          = true,
+    .bdrv_recurse_is_first_non_filter   = quorum_recurse_is_first_non_filter,
 };
 
 static void bdrv_quorum_init(void)

block/raw-aio.h

@@ -34,19 +34,27 @@
 /* linux-aio.c - Linux native implementation */
 #ifdef CONFIG_LINUX_AIO
 void *laio_init(void);
+void laio_cleanup(void *s);
 BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
         BlockDriverCompletionFunc *cb, void *opaque, int type);
+void laio_detach_aio_context(void *s, AioContext *old_context);
+void laio_attach_aio_context(void *s, AioContext *new_context);
 #endif
 
 #ifdef _WIN32
 typedef struct QEMUWin32AIOState QEMUWin32AIOState;
 QEMUWin32AIOState *win32_aio_init(void);
+void win32_aio_cleanup(QEMUWin32AIOState *aio);
 int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile);
 BlockDriverAIOCB *win32_aio_submit(BlockDriverState *bs,
         QEMUWin32AIOState *aio, HANDLE hfile,
         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
         BlockDriverCompletionFunc *cb, void *opaque, int type);
+void win32_aio_detach_aio_context(QEMUWin32AIOState *aio,
+                                  AioContext *old_context);
+void win32_aio_attach_aio_context(QEMUWin32AIOState *aio,
+                                  AioContext *new_context);
 #endif
 
 #endif /* QEMU_RAW_AIO_H */

block/raw-posix.c

@@ -307,6 +307,29 @@ static void raw_parse_flags(int bdrv_flags, int *open_flags)
     }
 }
 
+static void raw_detach_aio_context(BlockDriverState *bs)
+{
+#ifdef CONFIG_LINUX_AIO
+    BDRVRawState *s = bs->opaque;
+
+    if (s->use_aio) {
+        laio_detach_aio_context(s->aio_ctx, bdrv_get_aio_context(bs));
+    }
+#endif
+}
+
+static void raw_attach_aio_context(BlockDriverState *bs,
+                                   AioContext *new_context)
+{
+#ifdef CONFIG_LINUX_AIO
+    BDRVRawState *s = bs->opaque;
+
+    if (s->use_aio) {
+        laio_attach_aio_context(s->aio_ctx, new_context);
+    }
+#endif
+}
+
 #ifdef CONFIG_LINUX_AIO
 static int raw_set_aio(void **aio_ctx, int *use_aio, int bdrv_flags)
 {
@@ -447,6 +470,8 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
     }
 #endif
 
+    raw_attach_aio_context(bs, bdrv_get_aio_context(bs));
+
     ret = 0;
 fail:
     if (filename && (bdrv_flags & BDRV_O_TEMPORARY)) {
@@ -1059,6 +1084,14 @@ static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs,
 static void raw_close(BlockDriverState *bs)
 {
     BDRVRawState *s = bs->opaque;
+
+    raw_detach_aio_context(bs);
+
+#ifdef CONFIG_LINUX_AIO
+    if (s->use_aio) {
+        laio_cleanup(s->aio_ctx);
+    }
+#endif
     if (s->fd >= 0) {
         qemu_close(s->fd);
         s->fd = -1;
@@ -1240,8 +1273,7 @@ static int64_t raw_get_allocated_file_size(BlockDriverState *bs)
     return (int64_t)st.st_blocks * 512;
 }
 
-static int raw_create(const char *filename, QEMUOptionParameter *options,
-                      Error **errp)
+static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     int fd;
     int result = 0;
@@ -1250,12 +1282,8 @@ static int raw_create(const char *filename, QEMUOptionParameter *options,
     strstart(filename, "file:", &filename);
 
     /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            total_size = options->value.n / BDRV_SECTOR_SIZE;
-        }
-        options++;
-    }
+    total_size =
+        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
 
     fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
                    0644);
@@ -1440,13 +1468,17 @@ static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     return 0;
 }
 
-static QEMUOptionParameter raw_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    { NULL }
+static QemuOptsList raw_create_opts = {
+    .name = "raw-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(raw_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_file = {
@@ -1478,7 +1510,10 @@ static BlockDriver bdrv_file = {
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
 
-    .create_options = raw_create_options,
+    .bdrv_detach_aio_context = raw_detach_aio_context,
+    .bdrv_attach_aio_context = raw_attach_aio_context,
+
+    .create_opts = &raw_create_opts,
 };
 
 /***********************************************/
@@ -1799,7 +1834,7 @@ static coroutine_fn int hdev_co_write_zeroes(BlockDriverState *bs,
     return -ENOTSUP;
 }
 
-static int hdev_create(const char *filename, QEMUOptionParameter *options,
+static int hdev_create(const char *filename, QemuOpts *opts,
                        Error **errp)
 {
     int fd;
@@ -1820,12 +1855,8 @@ static int hdev_create(const char *filename, QEMUOptionParameter *options,
     (void)has_prefix;
 
     /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, "size")) {
-            total_size = options->value.n / BDRV_SECTOR_SIZE;
-        }
-        options++;
-    }
+    total_size =
+        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / BDRV_SECTOR_SIZE;
 
     fd = qemu_open(filename, O_WRONLY | O_BINARY);
     if (fd < 0) {
@@ -1862,8 +1893,8 @@ static BlockDriver bdrv_host_device = {
     .bdrv_reopen_prepare = raw_reopen_prepare,
     .bdrv_reopen_commit  = raw_reopen_commit,
     .bdrv_reopen_abort   = raw_reopen_abort,
-    .bdrv_create        = hdev_create,
-    .create_options     = raw_create_options,
+    .bdrv_create         = hdev_create,
+    .create_opts         = &raw_create_opts,
     .bdrv_co_write_zeroes = hdev_co_write_zeroes,
 
     .bdrv_aio_readv	= raw_aio_readv,
@@ -1878,6 +1909,9 @@ static BlockDriver bdrv_host_device = {
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
 
+    .bdrv_detach_aio_context = raw_detach_aio_context,
+    .bdrv_attach_aio_context = raw_attach_aio_context,
+
     /* generic scsi device */
 #ifdef __linux__
     .bdrv_ioctl         = hdev_ioctl,
@@ -2006,8 +2040,8 @@ static BlockDriver bdrv_host_floppy = {
     .bdrv_reopen_prepare = raw_reopen_prepare,
     .bdrv_reopen_commit  = raw_reopen_commit,
     .bdrv_reopen_abort   = raw_reopen_abort,
-    .bdrv_create        = hdev_create,
-    .create_options     = raw_create_options,
+    .bdrv_create         = hdev_create,
+    .create_opts         = &raw_create_opts,
 
     .bdrv_aio_readv     = raw_aio_readv,
     .bdrv_aio_writev    = raw_aio_writev,
@@ -2020,6 +2054,9 @@ static BlockDriver bdrv_host_floppy = {
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
 
+    .bdrv_detach_aio_context = raw_detach_aio_context,
+    .bdrv_attach_aio_context = raw_attach_aio_context,
+
     /* removable device support */
     .bdrv_is_inserted   = floppy_is_inserted,
     .bdrv_media_changed = floppy_media_changed,
@@ -2131,8 +2168,8 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_reopen_prepare = raw_reopen_prepare,
     .bdrv_reopen_commit  = raw_reopen_commit,
     .bdrv_reopen_abort   = raw_reopen_abort,
-    .bdrv_create        = hdev_create,
-    .create_options     = raw_create_options,
+    .bdrv_create         = hdev_create,
+    .create_opts         = &raw_create_opts,
 
     .bdrv_aio_readv     = raw_aio_readv,
     .bdrv_aio_writev    = raw_aio_writev,
@@ -2145,6 +2182,9 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
 
+    .bdrv_detach_aio_context = raw_detach_aio_context,
+    .bdrv_attach_aio_context = raw_attach_aio_context,
+
     /* removable device support */
     .bdrv_is_inserted   = cdrom_is_inserted,
     .bdrv_eject         = cdrom_eject,
@@ -2263,7 +2303,7 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_reopen_commit  = raw_reopen_commit,
     .bdrv_reopen_abort   = raw_reopen_abort,
     .bdrv_create        = hdev_create,
-    .create_options     = raw_create_options,
+    .create_opts        = &raw_create_opts,
 
     .bdrv_aio_readv     = raw_aio_readv,
     .bdrv_aio_writev    = raw_aio_writev,
@@ -2276,6 +2316,9 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
 
+    .bdrv_detach_aio_context = raw_detach_aio_context,
+    .bdrv_attach_aio_context = raw_attach_aio_context,
+
     /* removable device support */
     .bdrv_is_inserted   = cdrom_is_inserted,
     .bdrv_eject         = cdrom_eject,
@@ -2283,40 +2326,6 @@ static BlockDriver bdrv_host_cdrom = {
 };
 #endif /* __FreeBSD__ */
 
-#ifdef CONFIG_LINUX_AIO
-/**
- * Return the file descriptor for Linux AIO
- *
- * This function is a layering violation and should be removed when it becomes
- * possible to call the block layer outside the global mutex.  It allows the
- * caller to hijack the file descriptor so I/O can be performed outside the
- * block layer.
- */
-int raw_get_aio_fd(BlockDriverState *bs)
-{
-    BDRVRawState *s;
-
-    if (!bs->drv) {
-        return -ENOMEDIUM;
-    }
-
-    if (bs->drv == bdrv_find_format("raw")) {
-        bs = bs->file;
-    }
-
-    /* raw-posix has several protocols so just check for raw_aio_readv */
-    if (bs->drv->bdrv_aio_readv != raw_aio_readv) {
-        return -ENOTSUP;
-    }
-
-    s = bs->opaque;
-    if (!s->use_aio) {
-        return -ENOTSUP;
-    }
-    return s->fd;
-}
-#endif /* CONFIG_LINUX_AIO */
-
 static void bdrv_file_init(void)
 {
     /*

block/raw-win32.c

@@ -36,8 +36,6 @@
 #define FTYPE_CD     1
 #define FTYPE_HARDDISK 2
 
-static QEMUWin32AIOState *aio;
-
 typedef struct RawWin32AIOData {
     BlockDriverState *bs;
     HANDLE hfile;
@@ -202,6 +200,25 @@ static int set_sparse(int fd)
 				 NULL, 0, NULL, 0, &returned, NULL);
 }
 
+static void raw_detach_aio_context(BlockDriverState *bs)
+{
+    BDRVRawState *s = bs->opaque;
+
+    if (s->aio) {
+        win32_aio_detach_aio_context(s->aio, bdrv_get_aio_context(bs));
+    }
+}
+
+static void raw_attach_aio_context(BlockDriverState *bs,
+                                   AioContext *new_context)
+{
+    BDRVRawState *s = bs->opaque;
+
+    if (s->aio) {
+        win32_aio_attach_aio_context(s->aio, new_context);
+    }
+}
+
 static void raw_probe_alignment(BlockDriverState *bs)
 {
     BDRVRawState *s = bs->opaque;
@@ -300,15 +317,6 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
 
     raw_parse_flags(flags, &access_flags, &overlapped);
 
-    if ((flags & BDRV_O_NATIVE_AIO) && aio == NULL) {
-        aio = win32_aio_init();
-        if (aio == NULL) {
-            error_setg(errp, "Could not initialize AIO");
-            ret = -EINVAL;
-            goto fail;
-        }
-    }
-
     if (filename[0] && filename[1] == ':') {
         snprintf(s->drive_path, sizeof(s->drive_path), "%c:\\", filename[0]);
     } else if (filename[0] == '\\' && filename[1] == '\\') {
@@ -335,13 +343,23 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     if (flags & BDRV_O_NATIVE_AIO) {
-        ret = win32_aio_attach(aio, s->hfile);
+        s->aio = win32_aio_init();
+        if (s->aio == NULL) {
+            CloseHandle(s->hfile);
+            error_setg(errp, "Could not initialize AIO");
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        ret = win32_aio_attach(s->aio, s->hfile);
         if (ret < 0) {
+            win32_aio_cleanup(s->aio);
             CloseHandle(s->hfile);
             error_setg_errno(errp, -ret, "Could not enable AIO");
             goto fail;
         }
-        s->aio = aio;
+
+        win32_aio_attach_aio_context(s->aio, bdrv_get_aio_context(bs));
     }
 
     raw_probe_alignment(bs);
@@ -389,6 +407,13 @@ static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs,
 static void raw_close(BlockDriverState *bs)
 {
     BDRVRawState *s = bs->opaque;
+
+    if (s->aio) {
+        win32_aio_detach_aio_context(s->aio, bdrv_get_aio_context(bs));
+        win32_aio_cleanup(s->aio);
+        s->aio = NULL;
+    }
+
     CloseHandle(s->hfile);
     if (bs->open_flags & BDRV_O_TEMPORARY) {
         unlink(bs->filename);
@@ -478,8 +503,7 @@ static int64_t raw_get_allocated_file_size(BlockDriverState *bs)
     return st.st_size;
 }
 
-static int raw_create(const char *filename, QEMUOptionParameter *options,
-                      Error **errp)
+static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     int fd;
     int64_t total_size = 0;
@@ -487,12 +511,8 @@ static int raw_create(const char *filename, QEMUOptionParameter *options,
     strstart(filename, "file:", &filename);
 
     /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            total_size = options->value.n / 512;
-        }
-        options++;
-    }
+    total_size =
+        qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0) / 512;
 
     fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
                    0644);
@@ -506,13 +526,18 @@ static int raw_create(const char *filename, QEMUOptionParameter *options,
     return 0;
 }
 
-static QEMUOptionParameter raw_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    { NULL }
+
+static QemuOptsList raw_create_opts = {
+    .name = "raw-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(raw_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_file = {
@@ -521,9 +546,9 @@ static BlockDriver bdrv_file = {
     .instance_size	= sizeof(BDRVRawState),
     .bdrv_needs_filename = true,
     .bdrv_parse_filename = raw_parse_filename,
-    .bdrv_file_open	= raw_open,
-    .bdrv_close		= raw_close,
-    .bdrv_create	= raw_create,
+    .bdrv_file_open     = raw_open,
+    .bdrv_close         = raw_close,
+    .bdrv_create        = raw_create,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
 
     .bdrv_aio_readv     = raw_aio_readv,
@@ -535,7 +560,7 @@ static BlockDriver bdrv_file = {
     .bdrv_get_allocated_file_size
                         = raw_get_allocated_file_size,
 
-    .create_options = raw_create_options,
+    .create_opts        = &raw_create_opts,
 };
 
 /***********************************************/
@@ -684,6 +709,9 @@ static BlockDriver bdrv_host_device = {
     .bdrv_aio_writev    = raw_aio_writev,
     .bdrv_aio_flush     = raw_aio_flush,
 
+    .bdrv_detach_aio_context = raw_detach_aio_context,
+    .bdrv_attach_aio_context = raw_attach_aio_context,
+
     .bdrv_getlength      = raw_getlength,
     .has_variable_length = true,
 

block/raw_bsd.c

@@ -29,13 +29,17 @@
 #include "block/block_int.h"
 #include "qemu/option.h"
 
-static QEMUOptionParameter raw_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    { 0 }
+static QemuOptsList raw_create_opts = {
+    .name = "raw-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(raw_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        { /* end of list */ }
+    }
 };
 
 static int raw_reopen_prepare(BDRVReopenState *reopen_state,
@@ -139,13 +143,12 @@ static int raw_has_zero_init(BlockDriverState *bs)
     return bdrv_has_zero_init(bs->file);
 }
 
-static int raw_create(const char *filename, QEMUOptionParameter *options,
-                      Error **errp)
+static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     Error *local_err = NULL;
     int ret;
 
-    ret = bdrv_create_file(filename, options, &local_err);
+    ret = bdrv_create_file(filename, opts, &local_err);
     if (local_err) {
         error_propagate(errp, local_err);
     }
@@ -194,7 +197,7 @@ static BlockDriver bdrv_raw = {
     .bdrv_lock_medium     = &raw_lock_medium,
     .bdrv_ioctl           = &raw_ioctl,
     .bdrv_aio_ioctl       = &raw_aio_ioctl,
-    .create_options       = &raw_create_options[0],
+    .create_opts          = &raw_create_opts,
     .bdrv_has_zero_init   = &raw_has_zero_init
 };
 

block/rbd.c

@@ -289,8 +289,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
     return ret;
 }
 
-static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options,
-                           Error **errp)
+static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     Error *local_err = NULL;
     int64_t bytes = 0;
@@ -315,24 +314,18 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options,
     }
 
     /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            bytes = options->value.n;
-        } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
-            if (options->value.n) {
-                objsize = options->value.n;
-                if ((objsize - 1) & objsize) {    /* not a power of 2? */
-                    error_setg(errp, "obj size needs to be power of 2");
-                    return -EINVAL;
-                }
-                if (objsize < 4096) {
-                    error_setg(errp, "obj size too small");
-                    return -EINVAL;
-                }
-                obj_order = ffs(objsize) - 1;
-            }
+    bytes = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    objsize = qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE, 0);
+    if (objsize) {
+        if ((objsize - 1) & objsize) {    /* not a power of 2? */
+            error_setg(errp, "obj size needs to be power of 2");
+            return -EINVAL;
         }
-        options++;
+        if (objsize < 4096) {
+            error_setg(errp, "obj size too small");
+            return -EINVAL;
+        }
+        obj_order = ffs(objsize) - 1;
     }
 
     clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
@@ -555,7 +548,7 @@ static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
     acb->cancelled = 1;
 
     while (acb->status == -EINPROGRESS) {
-        qemu_aio_wait();
+        aio_poll(bdrv_get_aio_context(acb->common.bs), true);
     }
 
     qemu_aio_release(acb);
@@ -588,7 +581,8 @@ static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
     rcb->ret = rbd_aio_get_return_value(c);
     rbd_aio_release(c);
 
-    acb->bh = qemu_bh_new(rbd_finish_bh, rcb);
+    acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
+                         rbd_finish_bh, rcb);
     qemu_bh_schedule(acb->bh);
 }
 
@@ -684,13 +678,16 @@ static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
     }
 
     if (r < 0) {
-        goto failed;
+        goto failed_completion;
     }
 
     return &acb->common;
 
+failed_completion:
+    rbd_aio_release(c);
 failed:
     g_free(rcb);
+    qemu_vfree(acb->bounce);
     qemu_aio_release(acb);
     return NULL;
 }
@@ -907,18 +904,22 @@ static BlockDriverAIOCB* qemu_rbd_aio_discard(BlockDriverState *bs,
 }
 #endif
 
-static QEMUOptionParameter qemu_rbd_create_options[] = {
-    {
-     .name = BLOCK_OPT_SIZE,
-     .type = OPT_SIZE,
-     .help = "Virtual disk size"
-    },
-    {
-     .name = BLOCK_OPT_CLUSTER_SIZE,
-     .type = OPT_SIZE,
-     .help = "RBD object size"
-    },
-    {NULL}
+static QemuOptsList qemu_rbd_create_opts = {
+    .name = "rbd-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(qemu_rbd_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        {
+            .name = BLOCK_OPT_CLUSTER_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "RBD object size"
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_rbd = {
@@ -930,7 +931,7 @@ static BlockDriver bdrv_rbd = {
     .bdrv_create        = qemu_rbd_create,
     .bdrv_has_zero_init = bdrv_has_zero_init_1,
     .bdrv_get_info      = qemu_rbd_getinfo,
-    .create_options     = qemu_rbd_create_options,
+    .create_opts        = &qemu_rbd_create_opts,
     .bdrv_getlength     = qemu_rbd_getlength,
     .bdrv_truncate      = qemu_rbd_truncate,
     .protocol_name      = "rbd",

block/sheepdog.c

@@ -200,6 +200,8 @@ typedef struct SheepdogInode {
     uint32_t data_vdi_id[MAX_DATA_OBJS];
 } SheepdogInode;
 
+#define SD_INODE_HEADER_SIZE offsetof(SheepdogInode, data_vdi_id)
+
 /*
  * 64 bit FNV-1a non-zero initial basis
  */
@@ -282,6 +284,7 @@ typedef struct AIOReq {
     unsigned int data_len;
     uint8_t flags;
     uint32_t id;
+    bool create;
 
     QLIST_ENTRY(AIOReq) aio_siblings;
 } AIOReq;
@@ -314,6 +317,7 @@ struct SheepdogAIOCB {
 
 typedef struct BDRVSheepdogState {
     BlockDriverState *bs;
+    AioContext *aio_context;
 
     SheepdogInode inode;
 
@@ -404,7 +408,7 @@ static const char * sd_strerror(int err)
 
 static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb,
                                     uint64_t oid, unsigned int data_len,
-                                    uint64_t offset, uint8_t flags,
+                                    uint64_t offset, uint8_t flags, bool create,
                                     uint64_t base_oid, unsigned int iov_offset)
 {
     AIOReq *aio_req;
@@ -418,6 +422,7 @@ static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb,
     aio_req->data_len = data_len;
     aio_req->flags = flags;
     aio_req->id = s->aioreq_seq_num++;
+    aio_req->create = create;
 
     acb->nr_pending++;
     return aio_req;
@@ -496,7 +501,7 @@ static void sd_aio_cancel(BlockDriverAIOCB *blockacb)
             sd_finish_aiocb(acb);
             return;
         }
-        qemu_aio_wait();
+        aio_poll(s->aio_context, true);
     }
 }
 
@@ -578,6 +583,7 @@ static void restart_co_req(void *opaque)
 
 typedef struct SheepdogReqCo {
     int sockfd;
+    AioContext *aio_context;
     SheepdogReq *hdr;
     void *data;
     unsigned int *wlen;
@@ -598,14 +604,14 @@ static coroutine_fn void do_co_req(void *opaque)
     unsigned int *rlen = srco->rlen;
 
     co = qemu_coroutine_self();
-    qemu_aio_set_fd_handler(sockfd, NULL, restart_co_req, co);
+    aio_set_fd_handler(srco->aio_context, sockfd, NULL, restart_co_req, co);
 
     ret = send_co_req(sockfd, hdr, data, wlen);
     if (ret < 0) {
         goto out;
     }
 
-    qemu_aio_set_fd_handler(sockfd, restart_co_req, NULL, co);
+    aio_set_fd_handler(srco->aio_context, sockfd, restart_co_req, NULL, co);
 
     ret = qemu_co_recv(sockfd, hdr, sizeof(*hdr));
     if (ret != sizeof(*hdr)) {
@@ -630,18 +636,19 @@ static coroutine_fn void do_co_req(void *opaque)
 out:
     /* there is at most one request for this sockfd, so it is safe to
      * set each handler to NULL. */
-    qemu_aio_set_fd_handler(sockfd, NULL, NULL, NULL);
+    aio_set_fd_handler(srco->aio_context, sockfd, NULL, NULL, NULL);
 
     srco->ret = ret;
     srco->finished = true;
 }
 
-static int do_req(int sockfd, SheepdogReq *hdr, void *data,
-                  unsigned int *wlen, unsigned int *rlen)
+static int do_req(int sockfd, AioContext *aio_context, SheepdogReq *hdr,
+                  void *data, unsigned int *wlen, unsigned int *rlen)
 {
     Coroutine *co;
     SheepdogReqCo srco = {
         .sockfd = sockfd,
+        .aio_context = aio_context,
         .hdr = hdr,
         .data = data,
         .wlen = wlen,
@@ -656,7 +663,7 @@ static int do_req(int sockfd, SheepdogReq *hdr, void *data,
         co = qemu_coroutine_create(do_co_req);
         qemu_coroutine_enter(co, &srco);
         while (!srco.finished) {
-            qemu_aio_wait();
+            aio_poll(aio_context, true);
         }
     }
 
@@ -664,8 +671,8 @@ static int do_req(int sockfd, SheepdogReq *hdr, void *data,
 }
 
 static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
-                           struct iovec *iov, int niov, bool create,
-                           enum AIOCBState aiocb_type);
+                                         struct iovec *iov, int niov,
+                                         enum AIOCBState aiocb_type);
 static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req);
 static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag);
 static int get_sheep_fd(BDRVSheepdogState *s, Error **errp);
@@ -698,7 +705,7 @@ static void coroutine_fn send_pending_req(BDRVSheepdogState *s, uint64_t oid)
         /* move aio_req from pending list to inflight one */
         QLIST_REMOVE(aio_req, aio_siblings);
         QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
-        add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov, false,
+        add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
                         acb->aiocb_type);
     }
 }
@@ -709,7 +716,7 @@ static coroutine_fn void reconnect_to_sdog(void *opaque)
     BDRVSheepdogState *s = opaque;
     AIOReq *aio_req, *next;
 
-    qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL);
+    aio_set_fd_handler(s->aio_context, s->fd, NULL, NULL, NULL);
     close(s->fd);
     s->fd = -1;
 
@@ -797,7 +804,7 @@ static void coroutine_fn aio_read_response(void *opaque)
         }
         idx = data_oid_to_idx(aio_req->oid);
 
-        if (s->inode.data_vdi_id[idx] != s->inode.vdi_id) {
+        if (aio_req->create) {
             /*
              * If the object is newly created one, we need to update
              * the vdi object (metadata object).  min_dirty_data_idx
@@ -922,7 +929,7 @@ static int get_sheep_fd(BDRVSheepdogState *s, Error **errp)
         return fd;
     }
 
-    qemu_aio_set_fd_handler(fd, co_read_response, NULL, s);
+    aio_set_fd_handler(s->aio_context, fd, co_read_response, NULL, s);
     return fd;
 }
 
@@ -1092,7 +1099,7 @@ static int find_vdi_name(BDRVSheepdogState *s, const char *filename,
     hdr.snapid = snapid;
     hdr.flags = SD_FLAG_CMD_WRITE;
 
-    ret = do_req(fd, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
+    ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
     if (ret) {
         error_setg_errno(errp, -ret, "cannot get vdi info");
         goto out;
@@ -1117,8 +1124,8 @@ out:
 }
 
 static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
-                           struct iovec *iov, int niov, bool create,
-                           enum AIOCBState aiocb_type)
+                                         struct iovec *iov, int niov,
+                                         enum AIOCBState aiocb_type)
 {
     int nr_copies = s->inode.nr_copies;
     SheepdogObjReq hdr;
@@ -1129,6 +1136,7 @@ static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
     uint64_t offset = aio_req->offset;
     uint8_t flags = aio_req->flags;
     uint64_t old_oid = aio_req->base_oid;
+    bool create = aio_req->create;
 
     if (!nr_copies) {
         error_report("bug");
@@ -1173,7 +1181,8 @@ static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
 
     qemu_co_mutex_lock(&s->lock);
     s->co_send = qemu_coroutine_self();
-    qemu_aio_set_fd_handler(s->fd, co_read_response, co_write_request, s);
+    aio_set_fd_handler(s->aio_context, s->fd,
+                       co_read_response, co_write_request, s);
     socket_set_cork(s->fd, 1);
 
     /* send a header */
@@ -1191,12 +1200,13 @@ static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
     }
 out:
     socket_set_cork(s->fd, 0);
-    qemu_aio_set_fd_handler(s->fd, co_read_response, NULL, s);
+    aio_set_fd_handler(s->aio_context, s->fd, co_read_response, NULL, s);
     s->co_send = NULL;
     qemu_co_mutex_unlock(&s->lock);
 }
 
-static int read_write_object(int fd, char *buf, uint64_t oid, uint8_t copies,
+static int read_write_object(int fd, AioContext *aio_context, char *buf,
+                             uint64_t oid, uint8_t copies,
                              unsigned int datalen, uint64_t offset,
                              bool write, bool create, uint32_t cache_flags)
 {
@@ -1229,7 +1239,7 @@ static int read_write_object(int fd, char *buf, uint64_t oid, uint8_t copies,
     hdr.offset = offset;
     hdr.copies = copies;
 
-    ret = do_req(fd, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
+    ret = do_req(fd, aio_context, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
     if (ret) {
         error_report("failed to send a request to the sheep");
         return ret;
@@ -1244,19 +1254,23 @@ static int read_write_object(int fd, char *buf, uint64_t oid, uint8_t copies,
     }
 }
 
-static int read_object(int fd, char *buf, uint64_t oid, uint8_t copies,
+static int read_object(int fd, AioContext *aio_context, char *buf,
+                       uint64_t oid, uint8_t copies,
                        unsigned int datalen, uint64_t offset,
                        uint32_t cache_flags)
 {
-    return read_write_object(fd, buf, oid, copies, datalen, offset, false,
+    return read_write_object(fd, aio_context, buf, oid, copies,
+                             datalen, offset, false,
                              false, cache_flags);
 }
 
-static int write_object(int fd, char *buf, uint64_t oid, uint8_t copies,
+static int write_object(int fd, AioContext *aio_context, char *buf,
+                        uint64_t oid, uint8_t copies,
                         unsigned int datalen, uint64_t offset, bool create,
                         uint32_t cache_flags)
 {
-    return read_write_object(fd, buf, oid, copies, datalen, offset, true,
+    return read_write_object(fd, aio_context, buf, oid, copies,
+                             datalen, offset, true,
                              create, cache_flags);
 }
 
@@ -1275,7 +1289,7 @@ static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag)
         return -EIO;
     }
 
-    inode = g_malloc(sizeof(s->inode));
+    inode = g_malloc(SD_INODE_HEADER_SIZE);
 
     ret = find_vdi_name(s, s->name, snapid, tag, &vid, false, &local_err);
     if (ret) {
@@ -1284,14 +1298,15 @@ static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag)
         goto out;
     }
 
-    ret = read_object(fd, (char *)inode, vid_to_vdi_oid(vid),
-                      s->inode.nr_copies, sizeof(*inode), 0, s->cache_flags);
+    ret = read_object(fd, s->aio_context, (char *)inode, vid_to_vdi_oid(vid),
+                      s->inode.nr_copies, SD_INODE_HEADER_SIZE, 0,
+                      s->cache_flags);
     if (ret < 0) {
         goto out;
     }
 
     if (inode->vdi_id != s->inode.vdi_id) {
-        memcpy(&s->inode, inode, sizeof(s->inode));
+        memcpy(&s->inode, inode, SD_INODE_HEADER_SIZE);
     }
 
 out:
@@ -1315,6 +1330,7 @@ static bool check_simultaneous_create(BDRVSheepdogState *s, AIOReq *aio_req)
             DPRINTF("simultaneous create to %" PRIx64 "\n", aio_req->oid);
             aio_req->flags = 0;
             aio_req->base_oid = 0;
+            aio_req->create = false;
             QLIST_REMOVE(aio_req, aio_siblings);
             QLIST_INSERT_HEAD(&s->pending_aio_head, aio_req, aio_siblings);
             return true;
@@ -1327,7 +1343,8 @@ static bool check_simultaneous_create(BDRVSheepdogState *s, AIOReq *aio_req)
 static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req)
 {
     SheepdogAIOCB *acb = aio_req->aiocb;
-    bool create = false;
+
+    aio_req->create = false;
 
     /* check whether this request becomes a CoW one */
     if (acb->aiocb_type == AIOCB_WRITE_UDATA && is_data_obj(aio_req->oid)) {
@@ -1345,20 +1362,36 @@ static void coroutine_fn resend_aioreq(BDRVSheepdogState *s, AIOReq *aio_req)
             aio_req->base_oid = vid_to_data_oid(s->inode.data_vdi_id[idx], idx);
             aio_req->flags |= SD_FLAG_CMD_COW;
         }
-        create = true;
+        aio_req->create = true;
     }
 out:
     if (is_data_obj(aio_req->oid)) {
-        add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov, create,
+        add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
                         acb->aiocb_type);
     } else {
         struct iovec iov;
         iov.iov_base = &s->inode;
         iov.iov_len = sizeof(s->inode);
-        add_aio_request(s, aio_req, &iov, 1, false, AIOCB_WRITE_UDATA);
+        add_aio_request(s, aio_req, &iov, 1, AIOCB_WRITE_UDATA);
     }
 }
 
+static void sd_detach_aio_context(BlockDriverState *bs)
+{
+    BDRVSheepdogState *s = bs->opaque;
+
+    aio_set_fd_handler(s->aio_context, s->fd, NULL, NULL, NULL);
+}
+
+static void sd_attach_aio_context(BlockDriverState *bs,
+                                  AioContext *new_context)
+{
+    BDRVSheepdogState *s = bs->opaque;
+
+    s->aio_context = new_context;
+    aio_set_fd_handler(new_context, s->fd, co_read_response, NULL, s);
+}
+
 /* TODO Convert to fine grained options */
 static QemuOptsList runtime_opts = {
     .name = "sheepdog",
@@ -1387,6 +1420,7 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
     const char *filename;
 
     s->bs = bs;
+    s->aio_context = bdrv_get_aio_context(bs);
 
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
@@ -1448,8 +1482,8 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     buf = g_malloc(SD_INODE_SIZE);
-    ret = read_object(fd, buf, vid_to_vdi_oid(vid), 0, SD_INODE_SIZE, 0,
-                      s->cache_flags);
+    ret = read_object(fd, s->aio_context, buf, vid_to_vdi_oid(vid),
+                      0, SD_INODE_SIZE, 0, s->cache_flags);
 
     closesocket(fd);
 
@@ -1469,7 +1503,7 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
     g_free(buf);
     return 0;
 out:
-    qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL);
+    aio_set_fd_handler(bdrv_get_aio_context(bs), s->fd, NULL, NULL, NULL);
     if (s->fd >= 0) {
         closesocket(s->fd);
     }
@@ -1512,7 +1546,7 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot,
     hdr.copy_policy = s->inode.copy_policy;
     hdr.copies = s->inode.nr_copies;
 
-    ret = do_req(fd, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
+    ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr, buf, &wlen, &rlen);
 
     closesocket(fd);
 
@@ -1636,12 +1670,13 @@ static int parse_redundancy(BDRVSheepdogState *s, const char *opt)
     return 0;
 }
 
-static int sd_create(const char *filename, QEMUOptionParameter *options,
+static int sd_create(const char *filename, QemuOpts *opts,
                      Error **errp)
 {
     int ret = 0;
     uint32_t vid = 0;
     char *backing_file = NULL;
+    char *buf = NULL;
     BDRVSheepdogState *s;
     char tag[SD_MAX_VDI_TAG_LEN];
     uint32_t snapid;
@@ -1660,33 +1695,27 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
         goto out;
     }
 
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            s->inode.vdi_size = options->value.n;
-        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
-            backing_file = options->value.s;
-        } else if (!strcmp(options->name, BLOCK_OPT_PREALLOC)) {
-            if (!options->value.s || !strcmp(options->value.s, "off")) {
-                prealloc = false;
-            } else if (!strcmp(options->value.s, "full")) {
-                prealloc = true;
-            } else {
-                error_setg(errp, "Invalid preallocation mode: '%s'",
-                           options->value.s);
-                ret = -EINVAL;
-                goto out;
-            }
-        } else if (!strcmp(options->name, BLOCK_OPT_REDUNDANCY)) {
-            if (options->value.s) {
-                ret = parse_redundancy(s, options->value.s);
-                if (ret < 0) {
-                    error_setg(errp, "Invalid redundancy mode: '%s'",
-                               options->value.s);
-                    goto out;
-                }
-            }
+    s->inode.vdi_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
+    buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
+    if (!buf || !strcmp(buf, "off")) {
+        prealloc = false;
+    } else if (!strcmp(buf, "full")) {
+        prealloc = true;
+    } else {
+        error_setg(errp, "Invalid preallocation mode: '%s'", buf);
+        ret = -EINVAL;
+        goto out;
+    }
+
+    g_free(buf);
+    buf = qemu_opt_get_del(opts, BLOCK_OPT_REDUNDANCY);
+    if (buf) {
+        ret = parse_redundancy(s, buf);
+        if (ret < 0) {
+            error_setg(errp, "Invalid redundancy mode: '%s'", buf);
+            goto out;
         }
-        options++;
     }
 
     if (s->inode.vdi_size > SD_MAX_VDI_SIZE) {
@@ -1727,6 +1756,7 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
         bdrv_unref(bs);
     }
 
+    s->aio_context = qemu_get_aio_context();
     ret = do_sd_create(s, &vid, 0, errp);
     if (ret) {
         goto out;
@@ -1736,6 +1766,8 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
         ret = sd_prealloc(filename, errp);
     }
 out:
+    g_free(backing_file);
+    g_free(buf);
     g_free(s);
     return ret;
 }
@@ -1766,7 +1798,8 @@ static void sd_close(BlockDriverState *bs)
     hdr.data_length = wlen;
     hdr.flags = SD_FLAG_CMD_WRITE;
 
-    ret = do_req(fd, (SheepdogReq *)&hdr, s->name, &wlen, &rlen);
+    ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr,
+                 s->name, &wlen, &rlen);
 
     closesocket(fd);
 
@@ -1775,7 +1808,7 @@ static void sd_close(BlockDriverState *bs)
         error_report("%s, %s", sd_strerror(rsp->result), s->name);
     }
 
-    qemu_aio_set_fd_handler(s->fd, NULL, NULL, NULL);
+    aio_set_fd_handler(bdrv_get_aio_context(bs), s->fd, NULL, NULL, NULL);
     closesocket(s->fd);
     g_free(s->host_spec);
 }
@@ -1812,8 +1845,9 @@ static int sd_truncate(BlockDriverState *bs, int64_t offset)
     /* we don't need to update entire object */
     datalen = SD_INODE_SIZE - sizeof(s->inode.data_vdi_id);
     s->inode.vdi_size = offset;
-    ret = write_object(fd, (char *)&s->inode, vid_to_vdi_oid(s->inode.vdi_id),
-                       s->inode.nr_copies, datalen, 0, false, s->cache_flags);
+    ret = write_object(fd, s->aio_context, (char *)&s->inode,
+                       vid_to_vdi_oid(s->inode.vdi_id), s->inode.nr_copies,
+                       datalen, 0, false, s->cache_flags);
     close(fd);
 
     if (ret < 0) {
@@ -1849,9 +1883,9 @@ static void coroutine_fn sd_write_done(SheepdogAIOCB *acb)
         iov.iov_base = &s->inode;
         iov.iov_len = sizeof(s->inode);
         aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id),
-                                data_len, offset, 0, 0, offset);
+                                data_len, offset, 0, false, 0, offset);
         QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
-        add_aio_request(s, aio_req, &iov, 1, false, AIOCB_WRITE_UDATA);
+        add_aio_request(s, aio_req, &iov, 1, AIOCB_WRITE_UDATA);
 
         acb->aio_done_func = sd_finish_aiocb;
         acb->aiocb_type = AIOCB_WRITE_UDATA;
@@ -1882,7 +1916,8 @@ static bool sd_delete(BDRVSheepdogState *s)
         return false;
     }
 
-    ret = do_req(fd, (SheepdogReq *)&hdr, s->name, &wlen, &rlen);
+    ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr,
+                 s->name, &wlen, &rlen);
     closesocket(fd);
     if (ret) {
         return false;
@@ -1939,8 +1974,8 @@ static int sd_create_branch(BDRVSheepdogState *s)
         goto out;
     }
 
-    ret = read_object(fd, buf, vid_to_vdi_oid(vid), s->inode.nr_copies,
-                      SD_INODE_SIZE, 0, s->cache_flags);
+    ret = read_object(fd, s->aio_context, buf, vid_to_vdi_oid(vid),
+                      s->inode.nr_copies, SD_INODE_SIZE, 0, s->cache_flags);
 
     closesocket(fd);
 
@@ -2049,7 +2084,8 @@ static int coroutine_fn sd_co_rw_vector(void *p)
             DPRINTF("new oid %" PRIx64 "\n", oid);
         }
 
-        aio_req = alloc_aio_req(s, acb, oid, len, offset, flags, old_oid, done);
+        aio_req = alloc_aio_req(s, acb, oid, len, offset, flags, create,
+                                old_oid, done);
         QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
 
         if (create) {
@@ -2058,7 +2094,7 @@ static int coroutine_fn sd_co_rw_vector(void *p)
             }
         }
 
-        add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov, create,
+        add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
                         acb->aiocb_type);
     done:
         offset = 0;
@@ -2138,9 +2174,9 @@ static int coroutine_fn sd_co_flush_to_disk(BlockDriverState *bs)
     acb->aio_done_func = sd_finish_aiocb;
 
     aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id),
-                            0, 0, 0, 0, 0);
+                            0, 0, 0, false, 0, 0);
     QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
-    add_aio_request(s, aio_req, NULL, 0, false, acb->aiocb_type);
+    add_aio_request(s, aio_req, NULL, 0, acb->aiocb_type);
 
     qemu_coroutine_yield();
     return acb->ret;
@@ -2187,8 +2223,9 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
         goto cleanup;
     }
 
-    ret = write_object(fd, (char *)&s->inode, vid_to_vdi_oid(s->inode.vdi_id),
-                       s->inode.nr_copies, datalen, 0, false, s->cache_flags);
+    ret = write_object(fd, s->aio_context, (char *)&s->inode,
+                       vid_to_vdi_oid(s->inode.vdi_id), s->inode.nr_copies,
+                       datalen, 0, false, s->cache_flags);
     if (ret < 0) {
         error_report("failed to write snapshot's inode.");
         goto cleanup;
@@ -2203,8 +2240,9 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
         goto cleanup;
     }
 
-    ret = read_object(fd, (char *)inode, vid_to_vdi_oid(new_vid),
-                      s->inode.nr_copies, datalen, 0, s->cache_flags);
+    ret = read_object(fd, s->aio_context, (char *)inode,
+                      vid_to_vdi_oid(new_vid), s->inode.nr_copies, datalen, 0,
+                      s->cache_flags);
 
     if (ret < 0) {
         error_report("failed to read new inode info. %s", strerror(errno));
@@ -2311,7 +2349,8 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
     req.opcode = SD_OP_READ_VDIS;
     req.data_length = max;
 
-    ret = do_req(fd, (SheepdogReq *)&req, vdi_inuse, &wlen, &rlen);
+    ret = do_req(fd, s->aio_context, (SheepdogReq *)&req,
+                 vdi_inuse, &wlen, &rlen);
 
     closesocket(fd);
     if (ret) {
@@ -2338,7 +2377,8 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
         }
 
         /* we don't need to read entire object */
-        ret = read_object(fd, (char *)&inode, vid_to_vdi_oid(vid),
+        ret = read_object(fd, s->aio_context, (char *)&inode,
+                          vid_to_vdi_oid(vid),
                           0, SD_INODE_SIZE - sizeof(inode.data_vdi_id), 0,
                           s->cache_flags);
 
@@ -2403,11 +2443,11 @@ static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data,
 
         create = (offset == 0);
         if (load) {
-            ret = read_object(fd, (char *)data, vmstate_oid,
+            ret = read_object(fd, s->aio_context, (char *)data, vmstate_oid,
                               s->inode.nr_copies, data_len, offset,
                               s->cache_flags);
         } else {
-            ret = write_object(fd, (char *)data, vmstate_oid,
+            ret = write_object(fd, s->aio_context, (char *)data, vmstate_oid,
                                s->inode.nr_copies, data_len, offset, create,
                                s->cache_flags);
         }
@@ -2529,28 +2569,32 @@ static int64_t sd_get_allocated_file_size(BlockDriverState *bs)
     return size;
 }
 
-static QEMUOptionParameter sd_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    {
-        .name = BLOCK_OPT_BACKING_FILE,
-        .type = OPT_STRING,
-        .help = "File name of a base image"
-    },
-    {
-        .name = BLOCK_OPT_PREALLOC,
-        .type = OPT_STRING,
-        .help = "Preallocation mode (allowed values: off, full)"
-    },
-    {
-        .name = BLOCK_OPT_REDUNDANCY,
-        .type = OPT_STRING,
-        .help = "Redundancy of the image"
-    },
-    { NULL }
+static QemuOptsList sd_create_opts = {
+    .name = "sheepdog-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(sd_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        {
+            .name = BLOCK_OPT_BACKING_FILE,
+            .type = QEMU_OPT_STRING,
+            .help = "File name of a base image"
+        },
+        {
+            .name = BLOCK_OPT_PREALLOC,
+            .type = QEMU_OPT_STRING,
+            .help = "Preallocation mode (allowed values: off, full)"
+        },
+        {
+            .name = BLOCK_OPT_REDUNDANCY,
+            .type = QEMU_OPT_STRING,
+            .help = "Redundancy of the image"
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_sheepdog = {
@@ -2580,7 +2624,10 @@ static BlockDriver bdrv_sheepdog = {
     .bdrv_save_vmstate  = sd_save_vmstate,
     .bdrv_load_vmstate  = sd_load_vmstate,
 
-    .create_options = sd_create_options,
+    .bdrv_detach_aio_context = sd_detach_aio_context,
+    .bdrv_attach_aio_context = sd_attach_aio_context,
+
+    .create_opts    = &sd_create_opts,
 };
 
 static BlockDriver bdrv_sheepdog_tcp = {
@@ -2610,7 +2657,10 @@ static BlockDriver bdrv_sheepdog_tcp = {
     .bdrv_save_vmstate  = sd_save_vmstate,
     .bdrv_load_vmstate  = sd_load_vmstate,
 
-    .create_options = sd_create_options,
+    .bdrv_detach_aio_context = sd_detach_aio_context,
+    .bdrv_attach_aio_context = sd_attach_aio_context,
+
+    .create_opts    = &sd_create_opts,
 };
 
 static BlockDriver bdrv_sheepdog_unix = {
@@ -2640,7 +2690,10 @@ static BlockDriver bdrv_sheepdog_unix = {
     .bdrv_save_vmstate  = sd_save_vmstate,
     .bdrv_load_vmstate  = sd_load_vmstate,
 
-    .create_options = sd_create_options,
+    .bdrv_detach_aio_context = sd_detach_aio_context,
+    .bdrv_attach_aio_context = sd_attach_aio_context,
+
+    .create_opts    = &sd_create_opts,
 };
 
 static void bdrv_sheepdog_init(void)

block/ssh.c

@@ -675,17 +675,20 @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
     return ret;
 }
 
-static QEMUOptionParameter ssh_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    { NULL }
+static QemuOptsList ssh_create_opts = {
+    .name = "ssh-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(ssh_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        { /* end of list */ }
+    }
 };
 
-static int ssh_create(const char *filename, QEMUOptionParameter *options,
-                      Error **errp)
+static int ssh_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     int r, ret;
     int64_t total_size = 0;
@@ -697,12 +700,7 @@ static int ssh_create(const char *filename, QEMUOptionParameter *options,
     ssh_state_init(&s);
 
     /* Get desired file size. */
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            total_size = options->value.n;
-        }
-        options++;
-    }
+    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
     DPRINTF("total_size=%" PRIi64, total_size);
 
     uri_options = qdict_new();
@@ -773,7 +771,7 @@ static void restart_coroutine(void *opaque)
     qemu_coroutine_enter(co, NULL);
 }
 
-static coroutine_fn void set_fd_handler(BDRVSSHState *s)
+static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs)
 {
     int r;
     IOHandler *rd_handler = NULL, *wr_handler = NULL;
@@ -791,24 +789,26 @@ static coroutine_fn void set_fd_handler(BDRVSSHState *s)
     DPRINTF("s->sock=%d rd_handler=%p wr_handler=%p", s->sock,
             rd_handler, wr_handler);
 
-    qemu_aio_set_fd_handler(s->sock, rd_handler, wr_handler, co);
+    aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock,
+                       rd_handler, wr_handler, co);
 }
 
-static coroutine_fn void clear_fd_handler(BDRVSSHState *s)
+static coroutine_fn void clear_fd_handler(BDRVSSHState *s,
+                                          BlockDriverState *bs)
 {
     DPRINTF("s->sock=%d", s->sock);
-    qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL);
+    aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, NULL, NULL, NULL);
 }
 
 /* A non-blocking call returned EAGAIN, so yield, ensuring the
  * handlers are set up so that we'll be rescheduled when there is an
  * interesting event on the socket.
  */
-static coroutine_fn void co_yield(BDRVSSHState *s)
+static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs)
 {
-    set_fd_handler(s);
+    set_fd_handler(s, bs);
     qemu_coroutine_yield();
-    clear_fd_handler(s);
+    clear_fd_handler(s, bs);
 }
 
 /* SFTP has a function `libssh2_sftp_seek64' which seeks to a position
@@ -838,7 +838,7 @@ static void ssh_seek(BDRVSSHState *s, int64_t offset, int flags)
     }
 }
 
-static coroutine_fn int ssh_read(BDRVSSHState *s,
+static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
                                  int64_t offset, size_t size,
                                  QEMUIOVector *qiov)
 {
@@ -871,7 +871,7 @@ static coroutine_fn int ssh_read(BDRVSSHState *s,
         DPRINTF("sftp_read returned %zd", r);
 
         if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
-            co_yield(s);
+            co_yield(s, bs);
             goto again;
         }
         if (r < 0) {
@@ -906,14 +906,14 @@ static coroutine_fn int ssh_co_readv(BlockDriverState *bs,
     int ret;
 
     qemu_co_mutex_lock(&s->lock);
-    ret = ssh_read(s, sector_num * BDRV_SECTOR_SIZE,
+    ret = ssh_read(s, bs, sector_num * BDRV_SECTOR_SIZE,
                    nb_sectors * BDRV_SECTOR_SIZE, qiov);
     qemu_co_mutex_unlock(&s->lock);
 
     return ret;
 }
 
-static int ssh_write(BDRVSSHState *s,
+static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
                      int64_t offset, size_t size,
                      QEMUIOVector *qiov)
 {
@@ -941,7 +941,7 @@ static int ssh_write(BDRVSSHState *s,
         DPRINTF("sftp_write returned %zd", r);
 
         if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
-            co_yield(s);
+            co_yield(s, bs);
             goto again;
         }
         if (r < 0) {
@@ -960,7 +960,7 @@ static int ssh_write(BDRVSSHState *s,
          */
         if (r == 0) {
             ssh_seek(s, offset + written, SSH_SEEK_WRITE|SSH_SEEK_FORCE);
-            co_yield(s);
+            co_yield(s, bs);
             goto again;
         }
 
@@ -988,7 +988,7 @@ static coroutine_fn int ssh_co_writev(BlockDriverState *bs,
     int ret;
 
     qemu_co_mutex_lock(&s->lock);
-    ret = ssh_write(s, sector_num * BDRV_SECTOR_SIZE,
+    ret = ssh_write(s, bs, sector_num * BDRV_SECTOR_SIZE,
                     nb_sectors * BDRV_SECTOR_SIZE, qiov);
     qemu_co_mutex_unlock(&s->lock);
 
@@ -1009,7 +1009,7 @@ static void unsafe_flush_warning(BDRVSSHState *s, const char *what)
 
 #ifdef HAS_LIBSSH2_SFTP_FSYNC
 
-static coroutine_fn int ssh_flush(BDRVSSHState *s)
+static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs)
 {
     int r;
 
@@ -1017,7 +1017,7 @@ static coroutine_fn int ssh_flush(BDRVSSHState *s)
  again:
     r = libssh2_sftp_fsync(s->sftp_handle);
     if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
-        co_yield(s);
+        co_yield(s, bs);
         goto again;
     }
     if (r == LIBSSH2_ERROR_SFTP_PROTOCOL &&
@@ -1039,7 +1039,7 @@ static coroutine_fn int ssh_co_flush(BlockDriverState *bs)
     int ret;
 
     qemu_co_mutex_lock(&s->lock);
-    ret = ssh_flush(s);
+    ret = ssh_flush(s, bs);
     qemu_co_mutex_unlock(&s->lock);
 
     return ret;
@@ -1082,7 +1082,7 @@ static BlockDriver bdrv_ssh = {
     .bdrv_co_writev               = ssh_co_writev,
     .bdrv_getlength               = ssh_getlength,
     .bdrv_co_flush_to_disk        = ssh_co_flush,
-    .create_options               = ssh_create_options,
+    .create_opts                  = &ssh_create_opts,
 };
 
 static void bdrv_ssh_init(void)

block/stream.c

@@ -159,14 +159,14 @@ wait:
             BlockErrorAction action =
                 block_job_error_action(&s->common, s->common.bs, s->on_error,
                                        true, -ret);
-            if (action == BDRV_ACTION_STOP) {
+            if (action == BLOCK_ERROR_ACTION_STOP) {
                 n = 0;
                 continue;
             }
             if (error == 0) {
                 error = ret;
             }
-            if (action == BDRV_ACTION_REPORT) {
+            if (action == BLOCK_ERROR_ACTION_REPORT) {
                 break;
             }
         }

block/vdi.c

@@ -239,7 +239,6 @@ static void vdi_header_to_le(VdiHeader *header)
     cpu_to_le32s(&header->block_extra);
     cpu_to_le32s(&header->blocks_in_image);
     cpu_to_le32s(&header->blocks_allocated);
-    cpu_to_le32s(&header->blocks_allocated);
     uuid_convert(header->uuid_image);
     uuid_convert(header->uuid_last_snap);
     uuid_convert(header->uuid_link);
@@ -673,8 +672,7 @@ static int vdi_co_write(BlockDriverState *bs,
     return ret;
 }
 
-static int vdi_create(const char *filename, QEMUOptionParameter *options,
-                      Error **errp)
+static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     int fd;
     int result = 0;
@@ -689,25 +687,18 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options,
     logout("\n");
 
     /* Read out options. */
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            bytes = options->value.n;
+    bytes = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
 #if defined(CONFIG_VDI_BLOCK_SIZE)
-        } else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
-            if (options->value.n) {
-                /* TODO: Additional checks (SECTOR_SIZE * 2^n, ...). */
-                block_size = options->value.n;
-            }
+    /* TODO: Additional checks (SECTOR_SIZE * 2^n, ...). */
+    block_size = qemu_opt_get_size_del(opts,
+                                       BLOCK_OPT_CLUSTER_SIZE,
+                                       DEFAULT_CLUSTER_SIZE);
 #endif
 #if defined(CONFIG_VDI_STATIC_IMAGE)
-        } else if (!strcmp(options->name, BLOCK_OPT_STATIC)) {
-            if (options->value.n) {
-                image_type = VDI_TYPE_STATIC;
-            }
-#endif
-        }
-        options++;
+    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_STATIC, false)) {
+        image_type = VDI_TYPE_STATIC;
     }
+#endif
 
     if (bytes > VDI_DISK_SIZE_MAX) {
         result = -ENOTSUP;
@@ -802,29 +793,34 @@ static void vdi_close(BlockDriverState *bs)
     error_free(s->migration_blocker);
 }
 
-static QEMUOptionParameter vdi_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
+static QemuOptsList vdi_create_opts = {
+    .name = "vdi-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(vdi_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
 #if defined(CONFIG_VDI_BLOCK_SIZE)
-    {
-        .name = BLOCK_OPT_CLUSTER_SIZE,
-        .type = OPT_SIZE,
-        .help = "VDI cluster (block) size",
-        .value = { .n = DEFAULT_CLUSTER_SIZE },
-    },
+        {
+            .name = BLOCK_OPT_CLUSTER_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "VDI cluster (block) size",
+            .def_value_str = stringify(DEFAULT_CLUSTER_SIZE)
+        },
 #endif
 #if defined(CONFIG_VDI_STATIC_IMAGE)
-    {
-        .name = BLOCK_OPT_STATIC,
-        .type = OPT_FLAG,
-        .help = "VDI static (pre-allocated) image"
-    },
+        {
+            .name = BLOCK_OPT_STATIC,
+            .type = QEMU_OPT_BOOL,
+            .help = "VDI static (pre-allocated) image",
+            .def_value_str = "off"
+        },
 #endif
-    /* TODO: An additional option to set UUID values might be useful. */
-    { NULL }
+        /* TODO: An additional option to set UUID values might be useful. */
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_vdi = {
@@ -846,7 +842,7 @@ static BlockDriver bdrv_vdi = {
 
     .bdrv_get_info = vdi_get_info,
 
-    .create_options = vdi_create_options,
+    .create_opts = &vdi_create_opts,
     .bdrv_check = vdi_check,
 };
 

block/vhdx.c

@@ -1723,8 +1723,7 @@ exit:
  *    .---- ~ ----------- ~ ------------ ~ ---------------- ~ -----------.
  *   1MB
  */
-static int vhdx_create(const char *filename, QEMUOptionParameter *options,
-                       Error **errp)
+static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     int ret = 0;
     uint64_t image_size = (uint64_t) 2 * GiB;
@@ -1737,24 +1736,15 @@ static int vhdx_create(const char *filename, QEMUOptionParameter *options,
     gunichar2 *creator = NULL;
     glong creator_items;
     BlockDriverState *bs;
-    const char *type = NULL;
+    char *type = NULL;
     VHDXImageType image_type;
     Error *local_err = NULL;
 
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            image_size = options->value.n;
-        } else if (!strcmp(options->name, VHDX_BLOCK_OPT_LOG_SIZE)) {
-            log_size = options->value.n;
-        } else if (!strcmp(options->name, VHDX_BLOCK_OPT_BLOCK_SIZE)) {
-            block_size = options->value.n;
-        } else if (!strcmp(options->name, BLOCK_OPT_SUBFMT)) {
-            type = options->value.s;
-        } else if (!strcmp(options->name, VHDX_BLOCK_OPT_ZERO)) {
-            use_zero_blocks = options->value.n != 0;
-        }
-        options++;
-    }
+    image_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    log_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_LOG_SIZE, 0);
+    block_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_BLOCK_SIZE, 0);
+    type = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
+    use_zero_blocks = qemu_opt_get_bool_del(opts, VHDX_BLOCK_OPT_ZERO, false);
 
     if (image_size > VHDX_MAX_IMAGE_SIZE) {
         error_setg_errno(errp, EINVAL, "Image size too large; max of 64TB");
@@ -1763,7 +1753,7 @@ static int vhdx_create(const char *filename, QEMUOptionParameter *options,
     }
 
     if (type == NULL) {
-        type = "dynamic";
+        type = g_strdup("dynamic");
     }
 
     if (!strcmp(type, "dynamic")) {
@@ -1803,7 +1793,7 @@ static int vhdx_create(const char *filename, QEMUOptionParameter *options,
     block_size = block_size > VHDX_BLOCK_SIZE_MAX ? VHDX_BLOCK_SIZE_MAX :
                                                     block_size;
 
-    ret = bdrv_create_file(filename, options, &local_err);
+    ret = bdrv_create_file(filename, opts, &local_err);
     if (ret < 0) {
         error_propagate(errp, local_err);
         goto exit;
@@ -1863,6 +1853,7 @@ static int vhdx_create(const char *filename, QEMUOptionParameter *options,
 delete_and_exit:
     bdrv_unref(bs);
 exit:
+    g_free(type);
     g_free(creator);
     return ret;
 }
@@ -1885,37 +1876,41 @@ static int vhdx_check(BlockDriverState *bs, BdrvCheckResult *result,
     return 0;
 }
 
-static QEMUOptionParameter vhdx_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size; max of 64TB."
-    },
-    {
-        .name = VHDX_BLOCK_OPT_LOG_SIZE,
-        .type = OPT_SIZE,
-        .value.n = 1 * MiB,
-        .help = "Log size; min 1MB."
-    },
-    {
-        .name = VHDX_BLOCK_OPT_BLOCK_SIZE,
-        .type = OPT_SIZE,
-        .value.n = 0,
-        .help = "Block Size; min 1MB, max 256MB. " \
-                "0 means auto-calculate based on image size."
-    },
-    {
-        .name = BLOCK_OPT_SUBFMT,
-        .type = OPT_STRING,
-        .help = "VHDX format type, can be either 'dynamic' or 'fixed'. "\
-                "Default is 'dynamic'."
-    },
-    {
-        .name = VHDX_BLOCK_OPT_ZERO,
-        .type = OPT_FLAG,
-        .help = "Force use of payload blocks of type 'ZERO'.  Non-standard."
-    },
-    { NULL }
+static QemuOptsList vhdx_create_opts = {
+    .name = "vhdx-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(vhdx_create_opts.head),
+    .desc = {
+        {
+           .name = BLOCK_OPT_SIZE,
+           .type = QEMU_OPT_SIZE,
+           .help = "Virtual disk size; max of 64TB."
+       },
+       {
+           .name = VHDX_BLOCK_OPT_LOG_SIZE,
+           .type = QEMU_OPT_SIZE,
+           .def_value_str = stringify(DEFAULT_LOG_SIZE),
+           .help = "Log size; min 1MB."
+       },
+       {
+           .name = VHDX_BLOCK_OPT_BLOCK_SIZE,
+           .type = QEMU_OPT_SIZE,
+           .def_value_str = stringify(0),
+           .help = "Block Size; min 1MB, max 256MB. " \
+                   "0 means auto-calculate based on image size."
+       },
+       {
+           .name = BLOCK_OPT_SUBFMT,
+           .type = QEMU_OPT_STRING,
+           .help = "VHDX format type, can be either 'dynamic' or 'fixed'. "\
+                   "Default is 'dynamic'."
+       },
+       {
+           .name = VHDX_BLOCK_OPT_ZERO,
+           .type = QEMU_OPT_BOOL,
+           .help = "Force use of payload blocks of type 'ZERO'.  Non-standard."
+       },
+       { NULL }
+    }
 };
 
 static BlockDriver bdrv_vhdx = {
@@ -1931,7 +1926,7 @@ static BlockDriver bdrv_vhdx = {
     .bdrv_get_info          = vhdx_get_info,
     .bdrv_check             = vhdx_check,
 
-    .create_options         = vhdx_create_options,
+    .create_opts            = &vhdx_create_opts,
 };
 
 static void bdrv_vhdx_init(void)

block/vhdx.h

@@ -23,6 +23,7 @@
 #define GiB            (MiB * 1024)
 #define TiB ((uint64_t) GiB * 1024)
 
+#define DEFAULT_LOG_SIZE 1048576 /* 1MiB */
 /* Structures and fields present in the VHDX file */
 
 /* The header section has the following blocks,

block/vmdk.c

@@ -1695,17 +1695,16 @@ static int filename_decompose(const char *filename, char *path, char *prefix,
     return VMDK_OK;
 }
 
-static int vmdk_create(const char *filename, QEMUOptionParameter *options,
-                       Error **errp)
+static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     int idx = 0;
     BlockDriverState *new_bs = NULL;
     Error *local_err = NULL;
     char *desc = NULL;
     int64_t total_size = 0, filesize;
-    const char *adapter_type = NULL;
-    const char *backing_file = NULL;
-    const char *fmt = NULL;
+    char *adapter_type = NULL;
+    char *backing_file = NULL;
+    char *fmt = NULL;
     int flags = 0;
     int ret = 0;
     bool flat, split, compress;
@@ -1745,24 +1744,19 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
         goto exit;
     }
     /* Read out options */
-    while (options && options->name) {
-        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
-            total_size = options->value.n;
-        } else if (!strcmp(options->name, BLOCK_OPT_ADAPTER_TYPE)) {
-            adapter_type = options->value.s;
-        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
-            backing_file = options->value.s;
-        } else if (!strcmp(options->name, BLOCK_OPT_COMPAT6)) {
-            flags |= options->value.n ? BLOCK_FLAG_COMPAT6 : 0;
-        } else if (!strcmp(options->name, BLOCK_OPT_SUBFMT)) {
-            fmt = options->value.s;
-        } else if (!strcmp(options->name, BLOCK_OPT_ZEROED_GRAIN)) {
-            zeroed_grain |= options->value.n;
-        }
-        options++;
+    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    adapter_type = qemu_opt_get_del(opts, BLOCK_OPT_ADAPTER_TYPE);
+    backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
+    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_COMPAT6, false)) {
+        flags |= BLOCK_FLAG_COMPAT6;
     }
+    fmt = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
+    if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ZEROED_GRAIN, false)) {
+        zeroed_grain = true;
+    }
+
     if (!adapter_type) {
-        adapter_type = "ide";
+        adapter_type = g_strdup("ide");
     } else if (strcmp(adapter_type, "ide") &&
                strcmp(adapter_type, "buslogic") &&
                strcmp(adapter_type, "lsilogic") &&
@@ -1778,7 +1772,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
     }
     if (!fmt) {
         /* Default format to monolithicSparse */
-        fmt = "monolithicSparse";
+        fmt = g_strdup("monolithicSparse");
     } else if (strcmp(fmt, "monolithicFlat") &&
                strcmp(fmt, "monolithicSparse") &&
                strcmp(fmt, "twoGbMaxExtentSparse") &&
@@ -1879,7 +1873,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
     if (!split && !flat) {
         desc_offset = 0x200;
     } else {
-        ret = bdrv_create_file(filename, options, &local_err);
+        ret = bdrv_create_file(filename, opts, &local_err);
         if (ret < 0) {
             error_propagate(errp, local_err);
             goto exit;
@@ -1909,6 +1903,9 @@ exit:
     if (new_bs) {
         bdrv_unref(new_bs);
     }
+    g_free(adapter_type);
+    g_free(backing_file);
+    g_free(fmt);
     g_free(desc);
     g_string_free(ext_desc_lines, true);
     return ret;
@@ -2096,41 +2093,68 @@ static int vmdk_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     return 0;
 }
 
-static QEMUOptionParameter vmdk_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    {
-        .name = BLOCK_OPT_ADAPTER_TYPE,
-        .type = OPT_STRING,
-        .help = "Virtual adapter type, can be one of "
-                "ide (default), lsilogic, buslogic or legacyESX"
-    },
-    {
-        .name = BLOCK_OPT_BACKING_FILE,
-        .type = OPT_STRING,
-        .help = "File name of a base image"
-    },
-    {
-        .name = BLOCK_OPT_COMPAT6,
-        .type = OPT_FLAG,
-        .help = "VMDK version 6 image"
-    },
-    {
-        .name = BLOCK_OPT_SUBFMT,
-        .type = OPT_STRING,
-        .help =
-            "VMDK flat extent format, can be one of "
-            "{monolithicSparse (default) | monolithicFlat | twoGbMaxExtentSparse | twoGbMaxExtentFlat | streamOptimized} "
-    },
-    {
-        .name = BLOCK_OPT_ZEROED_GRAIN,
-        .type = OPT_FLAG,
-        .help = "Enable efficient zero writes using the zeroed-grain GTE feature"
-    },
-    { NULL }
+static void vmdk_detach_aio_context(BlockDriverState *bs)
+{
+    BDRVVmdkState *s = bs->opaque;
+    int i;
+
+    for (i = 0; i < s->num_extents; i++) {
+        bdrv_detach_aio_context(s->extents[i].file);
+    }
+}
+
+static void vmdk_attach_aio_context(BlockDriverState *bs,
+                                    AioContext *new_context)
+{
+    BDRVVmdkState *s = bs->opaque;
+    int i;
+
+    for (i = 0; i < s->num_extents; i++) {
+        bdrv_attach_aio_context(s->extents[i].file, new_context);
+    }
+}
+
+static QemuOptsList vmdk_create_opts = {
+    .name = "vmdk-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(vmdk_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        {
+            .name = BLOCK_OPT_ADAPTER_TYPE,
+            .type = QEMU_OPT_STRING,
+            .help = "Virtual adapter type, can be one of "
+                    "ide (default), lsilogic, buslogic or legacyESX"
+        },
+        {
+            .name = BLOCK_OPT_BACKING_FILE,
+            .type = QEMU_OPT_STRING,
+            .help = "File name of a base image"
+        },
+        {
+            .name = BLOCK_OPT_COMPAT6,
+            .type = QEMU_OPT_BOOL,
+            .help = "VMDK version 6 image",
+            .def_value_str = "off"
+        },
+        {
+            .name = BLOCK_OPT_SUBFMT,
+            .type = QEMU_OPT_STRING,
+            .help =
+                "VMDK flat extent format, can be one of "
+                "{monolithicSparse (default) | monolithicFlat | twoGbMaxExtentSparse | twoGbMaxExtentFlat | streamOptimized} "
+        },
+        {
+            .name = BLOCK_OPT_ZEROED_GRAIN,
+            .type = QEMU_OPT_BOOL,
+            .help = "Enable efficient zero writes "
+                    "using the zeroed-grain GTE feature"
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_vmdk = {
@@ -2153,8 +2177,10 @@ static BlockDriver bdrv_vmdk = {
     .bdrv_get_specific_info       = vmdk_get_specific_info,
     .bdrv_refresh_limits          = vmdk_refresh_limits,
     .bdrv_get_info                = vmdk_get_info,
+    .bdrv_detach_aio_context      = vmdk_detach_aio_context,
+    .bdrv_attach_aio_context      = vmdk_attach_aio_context,
 
-    .create_options               = vmdk_create_options,
+    .create_opts                  = &vmdk_create_opts,
 };
 
 static void bdrv_vmdk_init(void)

block/vpc.c

@@ -738,12 +738,11 @@ static int create_fixed_disk(int fd, uint8_t *buf, int64_t total_size)
     return ret;
 }
 
-static int vpc_create(const char *filename, QEMUOptionParameter *options,
-                      Error **errp)
+static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
 {
     uint8_t buf[1024];
     VHDFooter *footer = (VHDFooter *) buf;
-    QEMUOptionParameter *disk_type_param;
+    char *disk_type_param;
     int fd, i;
     uint16_t cyls = 0;
     uint8_t heads = 0;
@@ -754,16 +753,16 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options,
     int ret = -EIO;
 
     /* Read out options */
-    total_size = get_option_parameter(options, BLOCK_OPT_SIZE)->value.n;
-
-    disk_type_param = get_option_parameter(options, BLOCK_OPT_SUBFMT);
-    if (disk_type_param && disk_type_param->value.s) {
-        if (!strcmp(disk_type_param->value.s, "dynamic")) {
+    total_size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0);
+    disk_type_param = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
+    if (disk_type_param) {
+        if (!strcmp(disk_type_param, "dynamic")) {
             disk_type = VHD_DYNAMIC;
-        } else if (!strcmp(disk_type_param->value.s, "fixed")) {
+        } else if (!strcmp(disk_type_param, "fixed")) {
             disk_type = VHD_FIXED;
         } else {
-            return -EINVAL;
+            ret = -EINVAL;
+            goto out;
         }
     } else {
         disk_type = VHD_DYNAMIC;
@@ -772,7 +771,8 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options,
     /* Create the file */
     fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
     if (fd < 0) {
-        return -EIO;
+        ret = -EIO;
+        goto out;
     }
 
     /*
@@ -837,8 +837,10 @@ static int vpc_create(const char *filename, QEMUOptionParameter *options,
         ret = create_fixed_disk(fd, buf, total_size);
     }
 
- fail:
+fail:
     qemu_close(fd);
+out:
+    g_free(disk_type_param);
     return ret;
 }
 
@@ -866,20 +868,24 @@ static void vpc_close(BlockDriverState *bs)
     error_free(s->migration_blocker);
 }
 
-static QEMUOptionParameter vpc_create_options[] = {
-    {
-        .name = BLOCK_OPT_SIZE,
-        .type = OPT_SIZE,
-        .help = "Virtual disk size"
-    },
-    {
-        .name = BLOCK_OPT_SUBFMT,
-        .type = OPT_STRING,
-        .help =
-            "Type of virtual hard disk format. Supported formats are "
-            "{dynamic (default) | fixed} "
-    },
-    { NULL }
+static QemuOptsList vpc_create_opts = {
+    .name = "vpc-create-opts",
+    .head = QTAILQ_HEAD_INITIALIZER(vpc_create_opts.head),
+    .desc = {
+        {
+            .name = BLOCK_OPT_SIZE,
+            .type = QEMU_OPT_SIZE,
+            .help = "Virtual disk size"
+        },
+        {
+            .name = BLOCK_OPT_SUBFMT,
+            .type = QEMU_OPT_STRING,
+            .help =
+                "Type of virtual hard disk format. Supported formats are "
+                "{dynamic (default) | fixed} "
+        },
+        { /* end of list */ }
+    }
 };
 
 static BlockDriver bdrv_vpc = {
@@ -897,7 +903,7 @@ static BlockDriver bdrv_vpc = {
 
     .bdrv_get_info          = vpc_get_info,
 
-    .create_options         = vpc_create_options,
+    .create_opts            = &vpc_create_opts,
     .bdrv_has_zero_init     = vpc_has_zero_init,
 };
 

block/vvfat.c

@@ -2910,8 +2910,8 @@ static BlockDriver vvfat_write_target = {
 
 static int enable_write_target(BDRVVVFATState *s, Error **errp)
 {
-    BlockDriver *bdrv_qcow;
-    QEMUOptionParameter *options;
+    BlockDriver *bdrv_qcow = NULL;
+    QemuOpts *opts = NULL;
     int ret;
     int size = sector2cluster(s, s->sector_count);
     s->used_clusters = calloc(size, 1);
@@ -2926,12 +2926,12 @@ static int enable_write_target(BDRVVVFATState *s, Error **errp)
     }
 
     bdrv_qcow = bdrv_find_format("qcow");
-    options = parse_option_parameters("", bdrv_qcow->create_options, NULL);
-    set_option_parameter_int(options, BLOCK_OPT_SIZE, s->sector_count * 512);
-    set_option_parameter(options, BLOCK_OPT_BACKING_FILE, "fat:");
+    opts = qemu_opts_create(bdrv_qcow->create_opts, NULL, 0, &error_abort);
+    qemu_opt_set_number(opts, BLOCK_OPT_SIZE, s->sector_count * 512);
+    qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, "fat:");
 
-    ret = bdrv_create(bdrv_qcow, s->qcow_filename, options, errp);
-    free_option_parameters(options);
+    ret = bdrv_create(bdrv_qcow, s->qcow_filename, opts, errp);
+    qemu_opts_del(opts);
     if (ret < 0) {
         goto err;
     }

block/win32-aio.c

@@ -40,6 +40,7 @@ struct QEMUWin32AIOState {
     HANDLE hIOCP;
     EventNotifier e;
     int count;
+    bool is_aio_context_attached;
 };
 
 typedef struct QEMUWin32AIOCB {
@@ -114,7 +115,7 @@ static void win32_aio_cancel(BlockDriverAIOCB *blockacb)
      * wait for completion.
      */
     while (!HasOverlappedIoCompleted(&waiocb->ov)) {
-        qemu_aio_wait();
+        aio_poll(bdrv_get_aio_context(blockacb->bs), true);
     }
 }
 
@@ -180,6 +181,20 @@ int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile)
     }
 }
 
+void win32_aio_detach_aio_context(QEMUWin32AIOState *aio,
+                                  AioContext *old_context)
+{
+    aio_set_event_notifier(old_context, &aio->e, NULL);
+    aio->is_aio_context_attached = false;
+}
+
+void win32_aio_attach_aio_context(QEMUWin32AIOState *aio,
+                                  AioContext *new_context)
+{
+    aio->is_aio_context_attached = true;
+    aio_set_event_notifier(new_context, &aio->e, win32_aio_completion_cb);
+}
+
 QEMUWin32AIOState *win32_aio_init(void)
 {
     QEMUWin32AIOState *s;
@@ -194,8 +209,6 @@ QEMUWin32AIOState *win32_aio_init(void)
         goto out_close_efd;
     }
 
-    qemu_aio_set_event_notifier(&s->e, win32_aio_completion_cb);
-
     return s;
 
 out_close_efd:
@@ -204,3 +217,11 @@ out_free_state:
     g_free(s);
     return NULL;
 }
+
+void win32_aio_cleanup(QEMUWin32AIOState *aio)
+{
+    assert(!aio->is_aio_context_attached);
+    CloseHandle(aio->hIOCP);
+    event_notifier_cleanup(&aio->e);
+    g_free(aio);
+}

blockdev.c

@@ -106,7 +106,7 @@ void blockdev_auto_del(BlockDriverState *bs)
     DriveInfo *dinfo = drive_get_by_blockdev(bs);
 
     if (dinfo && dinfo->auto_del) {
-        drive_put_ref(dinfo);
+        drive_del(dinfo);
     }
 }
 
@@ -213,7 +213,7 @@ static void bdrv_format_print(void *opaque, const char *name)
     error_printf(" %s", name);
 }
 
-static void drive_uninit(DriveInfo *dinfo)
+void drive_del(DriveInfo *dinfo)
 {
     if (dinfo->opts) {
         qemu_opts_del(dinfo->opts);
@@ -226,19 +226,6 @@ static void drive_uninit(DriveInfo *dinfo)
     g_free(dinfo);
 }
 
-void drive_put_ref(DriveInfo *dinfo)
-{
-    assert(dinfo->refcount);
-    if (--dinfo->refcount == 0) {
-        drive_uninit(dinfo);
-    }
-}
-
-void drive_get_ref(DriveInfo *dinfo)
-{
-    dinfo->refcount++;
-}
-
 typedef struct {
     QEMUBH *bh;
     BlockDriverState *bs;
@@ -329,7 +316,6 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
                                 Error **errp)
 {
     const char *buf;
-    const char *serial;
     int ro = 0;
     int bdrv_flags = 0;
     int on_read_error, on_write_error;
@@ -371,8 +357,6 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     ro = qemu_opt_get_bool(opts, "read-only", 0);
     copy_on_read = qemu_opt_get_bool(opts, "copy-on-read", false);
 
-    serial = qemu_opt_get(opts, "serial");
-
     if ((buf = qemu_opt_get(opts, "discard")) != NULL) {
         if (bdrv_parse_discard_flags(buf, &bdrv_flags) != 0) {
             error_setg(errp, "invalid discard option");
@@ -500,10 +484,6 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     dinfo->bdrv->open_flags = snapshot ? BDRV_O_SNAPSHOT : 0;
     dinfo->bdrv->read_only = ro;
     dinfo->bdrv->detect_zeroes = detect_zeroes;
-    dinfo->refcount = 1;
-    if (serial != NULL) {
-        dinfo->serial = g_strdup(serial);
-    }
     QTAILQ_INSERT_TAIL(&drives, dinfo, next);
 
     bdrv_set_on_error(dinfo->bdrv, on_read_error, on_write_error);
@@ -629,6 +609,10 @@ QemuOptsList qemu_legacy_drive_opts = {
             .name = "addr",
             .type = QEMU_OPT_STRING,
             .help = "pci address (virtio only)",
+        },{
+            .name = "serial",
+            .type = QEMU_OPT_STRING,
+            .help = "disk serial number",
         },{
             .name = "file",
             .type = QEMU_OPT_STRING,
@@ -658,7 +642,7 @@ QemuOptsList qemu_legacy_drive_opts = {
     },
 };
 
-DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
+DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type)
 {
     const char *value;
     DriveInfo *dinfo = NULL;
@@ -672,6 +656,7 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
     const char *werror, *rerror;
     bool read_only = false;
     bool copy_on_read;
+    const char *serial;
     const char *filename;
     Error *local_err = NULL;
 
@@ -875,6 +860,9 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
         goto fail;
     }
 
+    /* Serial number */
+    serial = qemu_opt_get(legacy_opts, "serial");
+
     /* no id supplied -> create one */
     if (qemu_opts_id(all_opts) == NULL) {
         char *new_id;
@@ -965,6 +953,8 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
     dinfo->unit = unit_id;
     dinfo->devaddr = devaddr;
 
+    dinfo->serial = g_strdup(serial);
+
     switch(type) {
     case IF_IDE:
     case IF_SCSI:
@@ -1703,6 +1693,7 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
 {
     ThrottleConfig cfg;
     BlockDriverState *bs;
+    AioContext *aio_context;
 
     bs = bdrv_find(device);
     if (!bs) {
@@ -1746,6 +1737,9 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
         return;
     }
 
+    aio_context = bdrv_get_aio_context(bs);
+    aio_context_acquire(aio_context);
+
     if (!bs->io_limits_enabled && throttle_enabled(&cfg)) {
         bdrv_io_limits_enable(bs);
     } else if (bs->io_limits_enabled && !throttle_enabled(&cfg)) {
@@ -1755,6 +1749,8 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
     if (bs->io_limits_enabled) {
         bdrv_set_io_limits(bs, &cfg);
     }
+
+    aio_context_release(aio_context);
 }
 
 int do_drive_del(Monitor *mon, const QDict *qdict, QObject **ret_data)
@@ -1791,7 +1787,7 @@ int do_drive_del(Monitor *mon, const QDict *qdict, QObject **ret_data)
         bdrv_set_on_error(bs, BLOCKDEV_ON_ERROR_REPORT,
                           BLOCKDEV_ON_ERROR_REPORT);
     } else {
-        drive_uninit(drive_get_by_blockdev(bs));
+        drive_del(drive_get_by_blockdev(bs));
     }
 
     return 0;
@@ -1851,23 +1847,21 @@ void qmp_block_resize(bool has_device, const char *device,
 static void block_job_cb(void *opaque, int ret)
 {
     BlockDriverState *bs = opaque;
-    QObject *obj;
+    const char *msg = NULL;
 
     trace_block_job_cb(bs, bs->job, ret);
 
     assert(bs->job);
-    obj = qobject_from_block_job(bs->job);
+
     if (ret < 0) {
-        QDict *dict = qobject_to_qdict(obj);
-        qdict_put(dict, "error", qstring_from_str(strerror(-ret)));
+        msg = strerror(-ret);
     }
 
     if (block_job_is_cancelled(bs->job)) {
-        monitor_protocol_event(QEVENT_BLOCK_JOB_CANCELLED, obj);
+        block_job_event_cancelled(bs->job);
     } else {
-        monitor_protocol_event(QEVENT_BLOCK_JOB_COMPLETED, obj);
+        block_job_event_completed(bs->job, msg);
     }
-    qobject_decref(obj);
 
     bdrv_put_ref_bh_schedule(bs);
 }
@@ -2334,9 +2328,9 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
         goto fail;
     }
 
-    /* TODO Sort it out in raw-posix and drive_init: Reject aio=native with
+    /* TODO Sort it out in raw-posix and drive_new(): Reject aio=native with
      * cache.direct=false instead of silently switching to aio=threads, except
-     * if called from drive_init.
+     * when called from drive_new().
      *
      * For now, simply forbidding the combination for all drivers will do. */
     if (options->has_aio && options->aio == BLOCKDEV_AIO_OPTIONS_NATIVE) {
@@ -2368,7 +2362,7 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
     }
 
     if (bdrv_key_required(dinfo->bdrv)) {
-        drive_uninit(dinfo);
+        drive_del(dinfo);
         error_setg(errp, "blockdev-add doesn't support encrypted devices");
         goto fail;
     }
@@ -2431,10 +2425,6 @@ QemuOptsList qemu_common_drive_opts = {
             .name = "format",
             .type = QEMU_OPT_STRING,
             .help = "disk format (raw, qcow2, ...)",
-        },{
-            .name = "serial",
-            .type = QEMU_OPT_STRING,
-            .help = "disk serial number",
         },{
             .name = "rerror",
             .type = QEMU_OPT_STRING,

blockjob.c

@@ -26,7 +26,6 @@
 #include "config-host.h"
 #include "qemu-common.h"
 #include "trace.h"
-#include "monitor/monitor.h"
 #include "block/block.h"
 #include "block/blockjob.h"
 #include "block/block_int.h"
@@ -34,6 +33,7 @@
 #include "block/coroutine.h"
 #include "qmp-commands.h"
 #include "qemu/timer.h"
+#include "qapi-event.h"
 
 void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
                        int64_t speed, BlockDriverCompletionFunc *cb,
@@ -232,26 +232,31 @@ static void block_job_iostatus_set_err(BlockJob *job, int error)
     }
 }
 
-
-QObject *qobject_from_block_job(BlockJob *job)
+void block_job_event_cancelled(BlockJob *job)
 {
-    return qobject_from_jsonf("{ 'type': %s,"
-                              "'device': %s,"
-                              "'len': %" PRId64 ","
-                              "'offset': %" PRId64 ","
-                              "'speed': %" PRId64 " }",
-                              BlockJobType_lookup[job->driver->job_type],
-                              bdrv_get_device_name(job->bs),
-                              job->len,
-                              job->offset,
-                              job->speed);
+    qapi_event_send_block_job_cancelled(job->driver->job_type,
+                                        bdrv_get_device_name(job->bs),
+                                        job->len,
+                                        job->offset,
+                                        job->speed,
+                                        &error_abort);
 }
 
-void block_job_ready(BlockJob *job)
+void block_job_event_completed(BlockJob *job, const char *msg)
 {
-    QObject *data = qobject_from_block_job(job);
-    monitor_protocol_event(QEVENT_BLOCK_JOB_READY, data);
-    qobject_decref(data);
+    qapi_event_send_block_job_completed(job->driver->job_type,
+                                        bdrv_get_device_name(job->bs),
+                                        job->len,
+                                        job->offset,
+                                        job->speed,
+                                        !!msg,
+                                        msg,
+                                        &error_abort);
+}
+
+void block_job_event_ready(BlockJob *job)
+{
+    qapi_event_send_block_job_ready(bdrv_get_device_name(job->bs), &error_abort);
 }
 
 BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
@@ -262,22 +267,26 @@ BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
 
     switch (on_err) {
     case BLOCKDEV_ON_ERROR_ENOSPC:
-        action = (error == ENOSPC) ? BDRV_ACTION_STOP : BDRV_ACTION_REPORT;
+        action = (error == ENOSPC) ?
+                 BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
         break;
     case BLOCKDEV_ON_ERROR_STOP:
-        action = BDRV_ACTION_STOP;
+        action = BLOCK_ERROR_ACTION_STOP;
         break;
     case BLOCKDEV_ON_ERROR_REPORT:
-        action = BDRV_ACTION_REPORT;
+        action = BLOCK_ERROR_ACTION_REPORT;
         break;
     case BLOCKDEV_ON_ERROR_IGNORE:
-        action = BDRV_ACTION_IGNORE;
+        action = BLOCK_ERROR_ACTION_IGNORE;
         break;
     default:
         abort();
     }
-    bdrv_emit_qmp_error_event(job->bs, QEVENT_BLOCK_JOB_ERROR, action, is_read);
-    if (action == BDRV_ACTION_STOP) {
+    qapi_event_send_block_job_error(bdrv_get_device_name(bs),
+                                    is_read ? IO_OPERATION_TYPE_READ :
+                                    IO_OPERATION_TYPE_WRITE,
+                                    action, &error_abort);
+    if (action == BLOCK_ERROR_ACTION_STOP) {
         block_job_pause(job);
         block_job_iostatus_set_err(job, error);
         if (bs != job->bs) {

bsd-user/freebsd/strace.list

@@ -1,7 +1,37 @@
-{ TARGET_FREEBSD_NR___getcwd, "__getcwd", NULL, NULL, NULL },
+/*
+ *  FreeBSD strace list
+ *
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+{ TARGET_FREEBSD_NR___acl_aclcheck_fd, "__acl_aclcheck_fd", "%s(%d, %d, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR___acl_aclcheck_file, "__acl_aclcheck_file", "%s(\"%s\", %d, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR___acl_aclcheck_link, "__acl_aclcheck_link", "%s(\"%s\", %d, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR___acl_delete_fd, "__acl_delete_fd", "%s(%d, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR___acl_delete_file, "__acl_delete_file", "%s(\"%s\", %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR___acl_delete_link, "__acl_delete_link", "%s(\"%s\", %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR___acl_get_fd, "__acl_get_fd", "%s(%d, %d, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR___acl_get_file, "__acl_get_file", "%s(\"%s\", %d, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR___acl_get_link, "__acl_get_link", "%s(\"%s\", %d, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR___acl_set_fd, "__acl_set_fd", "%s(%d, %d, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR___acl_set_file, "__acl_set_file", "%s(\"%s\", %d, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR___acl_set_link, "__acl_set_link", "%s(\"%s\", %d, %#x)", NULL, NULL },
 { TARGET_FREEBSD_NR___semctl, "__semctl", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR___syscall, "__syscall", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR___sysctl, "__sysctl", NULL, NULL, NULL },
+{ TARGET_FREEBSD_NR___sysctl, "__sysctl", NULL, print_sysctl, NULL },
+{ TARGET_FREEBSD_NR__umtx_op, "_umtx_op", "%s(%#x, %d, %d, %#x, %#x)", NULL, NULL },
 { TARGET_FREEBSD_NR_accept, "accept", "%s(%d,%#x,%#x)", NULL, NULL },
 { TARGET_FREEBSD_NR_access, "access", "%s(\"%s\",%#o)", NULL, NULL },
 { TARGET_FREEBSD_NR_acct, "acct", NULL, NULL, NULL },
@@ -20,24 +50,41 @@
 { TARGET_FREEBSD_NR_connect, "connect", "%s(%d,%#x,%d)", NULL, NULL },
 { TARGET_FREEBSD_NR_dup, "dup", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_dup2, "dup2", NULL, NULL, NULL },
+{ TARGET_FREEBSD_NR_eaccess, "eaccess", "%s(\"%s\",%#x)", NULL, NULL },
 { TARGET_FREEBSD_NR_execve, "execve", NULL, print_execve, NULL },
 { TARGET_FREEBSD_NR_exit, "exit", "%s(%d)\n", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattrctl, "extattrctl", "%s(\"%s\", %d, \"%s\", %d, \"%s\"", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_delete_fd, "extattr_delete_fd", "%s(%d, %d, \"%s\")", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_delete_file, "extattr_delete_file", "%s(\"%s\", %d, \"%s\")", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_delete_link, "extattr_delete_link", "%s(\"%s\", %d, \"%s\")", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_get_fd, "extattr_get_fd", "%s(%d, %d, \"%s\", %#x, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_get_file, "extattr_get_file", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_get_file, "extattr_get_link", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_list_fd, "extattr_list_fd", "%s(%d, %d, %#x, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_list_file, "extattr_list_file", "%s(\"%s\", %d, %#x, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_list_link, "extattr_list_link", "%s(\"%s\", %d, %#x, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_set_fd, "extattr_set_fd", "%s(%d, %d, \"%s\", %#x, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_set_file, "extattr_set_file", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_extattr_set_link, "extattr_set_link", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
 { TARGET_FREEBSD_NR_fchdir, "fchdir", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_fchflags, "fchflags", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_fchmod, "fchmod", "%s(%d,%#o)", NULL, NULL },
-{ TARGET_FREEBSD_NR_fchown, "fchown", "%s(\"%s\",%d,%d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_fchown, "fchown", "%s(%d,%d,%d)", NULL, NULL },
 { TARGET_FREEBSD_NR_fcntl, "fcntl", NULL, NULL, NULL },
+{ TARGET_FREEBSD_NR_fexecve, "fexecve", NULL, print_execve, NULL },
 { TARGET_FREEBSD_NR_fhopen, "fhopen", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_fhstat, "fhstat", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_fhstatfs, "fhstatfs", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_flock, "flock", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_fork, "fork", "%s()", NULL, NULL },
 { TARGET_FREEBSD_NR_fpathconf, "fpathconf", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR_fstat, "fstat", "%s(%d,%p)", NULL, NULL },
-{ TARGET_FREEBSD_NR_fstatfs, "fstatfs", "%s(%d,%p)", NULL, NULL },
+{ TARGET_FREEBSD_NR_fstat, "fstat", "%s(%d,%#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR_fstatat, "fstatat", "%s(%d,\"%s\", %#x, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_fstatfs, "fstatfs", "%s(%d,%#x)", NULL, NULL },
 { TARGET_FREEBSD_NR_fsync, "fsync", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_ftruncate, "ftruncate", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_futimes, "futimes", NULL, NULL, NULL },
+{ TARGET_FREEBSD_NR_getcontext, "getcontext", "%s(%#x)", NULL, NULL },
 { TARGET_FREEBSD_NR_getdirentries, "getdirentries", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_freebsd6_mmap, "freebsd6_mmap", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_getegid, "getegid", "%s()", NULL, NULL },
@@ -63,7 +110,7 @@
 { TARGET_FREEBSD_NR_getsockopt, "getsockopt", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_gettimeofday, "gettimeofday", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_getuid, "getuid", "%s()", NULL, NULL },
-{ TARGET_FREEBSD_NR_ioctl, "ioctl", NULL, NULL, NULL },
+{ TARGET_FREEBSD_NR_ioctl, "ioctl", NULL, print_ioctl, NULL },
 { TARGET_FREEBSD_NR_issetugid, "issetugid", "%s()", NULL, NULL },
 { TARGET_FREEBSD_NR_kevent, "kevent", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_kill, "kill", NULL, NULL, NULL },
@@ -72,6 +119,7 @@
 { TARGET_FREEBSD_NR_lchown, "lchown", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_link, "link", "%s(\"%s\",\"%s\")", NULL, NULL },
 { TARGET_FREEBSD_NR_listen, "listen", NULL, NULL, NULL },
+{ TARGET_FREEBSD_NR_lpathconf, "lpathconf", "%s(\"%s\", %d)", NULL, NULL },
 { TARGET_FREEBSD_NR_lseek, "lseek", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_lstat, "lstat", "%s(\"%s\",%p)", NULL, NULL },
 { TARGET_FREEBSD_NR_madvise, "madvise", NULL, NULL, NULL },
@@ -96,7 +144,8 @@
 { TARGET_FREEBSD_NR_nanosleep, "nanosleep", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_nfssvc, "nfssvc", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_open, "open", "%s(\"%s\",%#x,%#o)", NULL, NULL },
-{ TARGET_FREEBSD_NR_pathconf, "pathconf", NULL, NULL, NULL },
+{ TARGET_FREEBSD_NR_openat, "openat", "%s(%d, \"%s\",%#x,%#o)", NULL, NULL },
+{ TARGET_FREEBSD_NR_pathconf, "pathconf", "%s(\"%s\", %d)", NULL, NULL },
 { TARGET_FREEBSD_NR_pipe, "pipe", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_poll, "poll", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_pread, "pread", NULL, NULL, NULL },
@@ -116,6 +165,7 @@
 { TARGET_FREEBSD_NR_revoke, "revoke", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_rfork, "rfork", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_rmdir, "rmdir", NULL, NULL, NULL },
+{ TARGET_FREEBSD_NR_rtprio_thread, "rtprio_thread", "%s(%d, %d, %p)", NULL, NULL },
 { TARGET_FREEBSD_NR_sbrk, "sbrk", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sched_yield, "sched_yield", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_select, "select", NULL, NULL, NULL },
@@ -123,6 +173,7 @@
 { TARGET_FREEBSD_NR_semop, "semop", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sendmsg, "sendmsg", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sendto, "sendto", NULL, NULL, NULL },
+{ TARGET_FREEBSD_NR_setcontext, "setcontext", "%s(%#x)", NULL, NULL },
 { TARGET_FREEBSD_NR_setegid, "setegid", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_seteuid, "seteuid", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_setgid, "setgid", NULL, NULL, NULL },
@@ -151,7 +202,7 @@
 { TARGET_FREEBSD_NR_sigprocmask, "sigprocmask", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sigreturn, "sigreturn", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sigsuspend, "sigsuspend", NULL, NULL, NULL },
-{ TARGET_FREEBSD_NR_socket, "socket", NULL, NULL, NULL },
+{ TARGET_FREEBSD_NR_socket, "socket", "%s(%d,%d,%d)", NULL, NULL },
 { TARGET_FREEBSD_NR_socketpair, "socketpair", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sstk, "sstk", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_stat, "stat", "%s(\"%s\",%p)", NULL, NULL },
@@ -160,6 +211,15 @@
 { TARGET_FREEBSD_NR_sync, "sync", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_sysarch, "sysarch", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_syscall, "syscall", NULL, NULL, NULL },
+{ TARGET_FREEBSD_NR_thr_create, "thr_create", "%s(%#x, %#x, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_thr_exit, "thr_exit", "%s(%#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR_thr_kill, "thr_kill", "%s(%d, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR_thr_kill2, "thr_kill2", "%s(%d, %d, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_thr_new, "thr_new", "%s(%#x, %d)", NULL, NULL },
+{ TARGET_FREEBSD_NR_thr_self, "thr_self", "%s(%#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR_thr_set_name, "thr_set_name", "%s(%d, \"%s\")", NULL, NULL },
+{ TARGET_FREEBSD_NR_thr_suspend, "thr_suspend", "%s(%d, %#x)", NULL, NULL },
+{ TARGET_FREEBSD_NR_thr_wake, "thr_wake", "%s(%d)", NULL, NULL },
 { TARGET_FREEBSD_NR_truncate, "truncate", NULL, NULL, NULL },
 { TARGET_FREEBSD_NR_umask, "umask", "%s(%#o)", NULL, NULL },
 { TARGET_FREEBSD_NR_unlink, "unlink", "%s(\"%s\")", NULL, NULL },

bsd-user/freebsd/syscall_nr.h

@@ -1,373 +1,450 @@
 /*
  * System call numbers.
  *
- * $FreeBSD: src/sys/sys/syscall.h,v 1.224 2008/08/24 21:23:08 rwatson Exp $
- * created from FreeBSD: head/sys/kern/syscalls.master 182123 2008-08-24 21:20:35Z rwatson
+ * created from FreeBSD: releng/9.1/sys/kern/syscalls.master 229723
+ * 2012-01-06 19:29:16Z jhb
  */
 
-#define TARGET_FREEBSD_NR_syscall     0
-#define TARGET_FREEBSD_NR_exit        1
-#define TARGET_FREEBSD_NR_fork        2
-#define TARGET_FREEBSD_NR_read        3
-#define TARGET_FREEBSD_NR_write       4
-#define TARGET_FREEBSD_NR_open        5
-#define TARGET_FREEBSD_NR_close       6
-#define TARGET_FREEBSD_NR_wait4       7
-#define TARGET_FREEBSD_NR_link        9
-#define TARGET_FREEBSD_NR_unlink      10
-#define TARGET_FREEBSD_NR_chdir       12
-#define TARGET_FREEBSD_NR_fchdir      13
-#define TARGET_FREEBSD_NR_mknod       14
-#define TARGET_FREEBSD_NR_chmod       15
-#define TARGET_FREEBSD_NR_chown       16
-#define TARGET_FREEBSD_NR_break       17
-#define TARGET_FREEBSD_NR_freebsd4_getfsstat  18
-#define TARGET_FREEBSD_NR_getpid      20
-#define TARGET_FREEBSD_NR_mount       21
-#define TARGET_FREEBSD_NR_unmount     22
-#define TARGET_FREEBSD_NR_setuid      23
-#define TARGET_FREEBSD_NR_getuid      24
-#define TARGET_FREEBSD_NR_geteuid     25
-#define TARGET_FREEBSD_NR_ptrace      26
-#define TARGET_FREEBSD_NR_recvmsg     27
-#define TARGET_FREEBSD_NR_sendmsg     28
-#define TARGET_FREEBSD_NR_recvfrom    29
-#define TARGET_FREEBSD_NR_accept      30
-#define TARGET_FREEBSD_NR_getpeername 31
-#define TARGET_FREEBSD_NR_getsockname 32
-#define TARGET_FREEBSD_NR_access      33
-#define TARGET_FREEBSD_NR_chflags     34
-#define TARGET_FREEBSD_NR_fchflags    35
-#define TARGET_FREEBSD_NR_sync        36
-#define TARGET_FREEBSD_NR_kill        37
-#define TARGET_FREEBSD_NR_getppid     39
-#define TARGET_FREEBSD_NR_dup 41
-#define TARGET_FREEBSD_NR_pipe        42
-#define TARGET_FREEBSD_NR_getegid     43
-#define TARGET_FREEBSD_NR_profil      44
-#define TARGET_FREEBSD_NR_ktrace      45
-#define TARGET_FREEBSD_NR_getgid      47
-#define TARGET_FREEBSD_NR_getlogin    49
-#define TARGET_FREEBSD_NR_setlogin    50
-#define TARGET_FREEBSD_NR_acct        51
-#define TARGET_FREEBSD_NR_sigaltstack 53
-#define TARGET_FREEBSD_NR_ioctl       54
-#define TARGET_FREEBSD_NR_reboot      55
-#define TARGET_FREEBSD_NR_revoke      56
-#define TARGET_FREEBSD_NR_symlink     57
-#define TARGET_FREEBSD_NR_readlink    58
-#define TARGET_FREEBSD_NR_execve      59
-#define TARGET_FREEBSD_NR_umask       60
-#define TARGET_FREEBSD_NR_chroot      61
-#define TARGET_FREEBSD_NR_msync       65
-#define TARGET_FREEBSD_NR_vfork       66
-#define TARGET_FREEBSD_NR_sbrk        69
-#define TARGET_FREEBSD_NR_sstk        70
-#define TARGET_FREEBSD_NR_vadvise     72
-#define TARGET_FREEBSD_NR_munmap      73
-#define TARGET_FREEBSD_NR_mprotect    74
-#define TARGET_FREEBSD_NR_madvise     75
-#define TARGET_FREEBSD_NR_mincore     78
-#define TARGET_FREEBSD_NR_getgroups   79
-#define TARGET_FREEBSD_NR_setgroups   80
-#define TARGET_FREEBSD_NR_getpgrp     81
-#define TARGET_FREEBSD_NR_setpgid     82
-#define TARGET_FREEBSD_NR_setitimer   83
-#define TARGET_FREEBSD_NR_swapon      85
-#define TARGET_FREEBSD_NR_getitimer   86
-#define TARGET_FREEBSD_NR_getdtablesize       89
-#define TARGET_FREEBSD_NR_dup2        90
-#define TARGET_FREEBSD_NR_fcntl       92
-#define TARGET_FREEBSD_NR_select      93
-#define TARGET_FREEBSD_NR_fsync       95
-#define TARGET_FREEBSD_NR_setpriority 96
-#define TARGET_FREEBSD_NR_socket      97
-#define TARGET_FREEBSD_NR_connect     98
-#define TARGET_FREEBSD_NR_getpriority 100
-#define TARGET_FREEBSD_NR_bind        104
-#define TARGET_FREEBSD_NR_setsockopt  105
-#define TARGET_FREEBSD_NR_listen      106
-#define TARGET_FREEBSD_NR_gettimeofday        116
-#define TARGET_FREEBSD_NR_getrusage   117
-#define TARGET_FREEBSD_NR_getsockopt  118
-#define TARGET_FREEBSD_NR_readv       120
-#define TARGET_FREEBSD_NR_writev      121
-#define TARGET_FREEBSD_NR_settimeofday        122
-#define TARGET_FREEBSD_NR_fchown      123
-#define TARGET_FREEBSD_NR_fchmod      124
-#define TARGET_FREEBSD_NR_setreuid    126
-#define TARGET_FREEBSD_NR_setregid    127
-#define TARGET_FREEBSD_NR_rename      128
-#define TARGET_FREEBSD_NR_flock       131
-#define TARGET_FREEBSD_NR_mkfifo      132
-#define TARGET_FREEBSD_NR_sendto      133
-#define TARGET_FREEBSD_NR_shutdown    134
-#define TARGET_FREEBSD_NR_socketpair  135
-#define TARGET_FREEBSD_NR_mkdir       136
-#define TARGET_FREEBSD_NR_rmdir       137
-#define TARGET_FREEBSD_NR_utimes      138
-#define TARGET_FREEBSD_NR_adjtime     140
-#define TARGET_FREEBSD_NR_setsid      147
-#define TARGET_FREEBSD_NR_quotactl    148
-#define TARGET_FREEBSD_NR_nlm_syscall 154
-#define TARGET_FREEBSD_NR_nfssvc      155
-#define TARGET_FREEBSD_NR_freebsd4_statfs     157
-#define TARGET_FREEBSD_NR_freebsd4_fstatfs    158
-#define TARGET_FREEBSD_NR_lgetfh      160
-#define TARGET_FREEBSD_NR_getfh       161
-#define TARGET_FREEBSD_NR_getdomainname       162
-#define TARGET_FREEBSD_NR_setdomainname       163
-#define TARGET_FREEBSD_NR_uname       164
-#define TARGET_FREEBSD_NR_sysarch     165
-#define TARGET_FREEBSD_NR_rtprio      166
-#define TARGET_FREEBSD_NR_semsys      169
-#define TARGET_FREEBSD_NR_msgsys      170
-#define TARGET_FREEBSD_NR_shmsys      171
-#define TARGET_FREEBSD_NR_freebsd6_pread      173
-#define TARGET_FREEBSD_NR_freebsd6_pwrite     174
-#define TARGET_FREEBSD_NR_setfib      175
-#define TARGET_FREEBSD_NR_ntp_adjtime 176
-#define TARGET_FREEBSD_NR_setgid      181
-#define TARGET_FREEBSD_NR_setegid     182
-#define TARGET_FREEBSD_NR_seteuid     183
-#define TARGET_FREEBSD_NR_stat        188
-#define TARGET_FREEBSD_NR_fstat       189
-#define TARGET_FREEBSD_NR_lstat       190
-#define TARGET_FREEBSD_NR_pathconf    191
-#define TARGET_FREEBSD_NR_fpathconf   192
-#define TARGET_FREEBSD_NR_getrlimit   194
-#define TARGET_FREEBSD_NR_setrlimit   195
-#define TARGET_FREEBSD_NR_getdirentries       196
-#define TARGET_FREEBSD_NR_freebsd6_mmap       197
-#define TARGET_FREEBSD_NR___syscall   198
-#define TARGET_FREEBSD_NR_freebsd6_lseek      199
-#define TARGET_FREEBSD_NR_freebsd6_truncate   200
-#define TARGET_FREEBSD_NR_freebsd6_ftruncate  201
-#define TARGET_FREEBSD_NR___sysctl    202
-#define TARGET_FREEBSD_NR_mlock       203
-#define TARGET_FREEBSD_NR_munlock     204
-#define TARGET_FREEBSD_NR_undelete    205
-#define TARGET_FREEBSD_NR_futimes     206
-#define TARGET_FREEBSD_NR_getpgid     207
-#define TARGET_FREEBSD_NR_poll        209
-#define TARGET_FREEBSD_NR___semctl    220
-#define TARGET_FREEBSD_NR_semget      221
-#define TARGET_FREEBSD_NR_semop       222
-#define TARGET_FREEBSD_NR_msgctl      224
-#define TARGET_FREEBSD_NR_msgget      225
-#define TARGET_FREEBSD_NR_msgsnd      226
-#define TARGET_FREEBSD_NR_msgrcv      227
-#define TARGET_FREEBSD_NR_shmat       228
-#define TARGET_FREEBSD_NR_shmctl      229
-#define TARGET_FREEBSD_NR_shmdt       230
-#define TARGET_FREEBSD_NR_shmget      231
-#define TARGET_FREEBSD_NR_clock_gettime       232
-#define TARGET_FREEBSD_NR_clock_settime       233
-#define TARGET_FREEBSD_NR_clock_getres        234
-#define TARGET_FREEBSD_NR_ktimer_create       235
-#define TARGET_FREEBSD_NR_ktimer_delete       236
-#define TARGET_FREEBSD_NR_ktimer_settime      237
-#define TARGET_FREEBSD_NR_ktimer_gettime      238
-#define TARGET_FREEBSD_NR_ktimer_getoverrun   239
-#define TARGET_FREEBSD_NR_nanosleep   240
-#define TARGET_FREEBSD_NR_ntp_gettime 248
-#define TARGET_FREEBSD_NR_minherit    250
-#define TARGET_FREEBSD_NR_rfork       251
-#define TARGET_FREEBSD_NR_openbsd_poll        252
-#define TARGET_FREEBSD_NR_issetugid   253
-#define TARGET_FREEBSD_NR_lchown      254
-#define TARGET_FREEBSD_NR_aio_read    255
-#define TARGET_FREEBSD_NR_aio_write   256
-#define TARGET_FREEBSD_NR_lio_listio  257
-#define TARGET_FREEBSD_NR_getdents    272
-#define TARGET_FREEBSD_NR_lchmod      274
-#define TARGET_FREEBSD_NR_netbsd_lchown       275
-#define TARGET_FREEBSD_NR_lutimes     276
-#define TARGET_FREEBSD_NR_netbsd_msync        277
-#define TARGET_FREEBSD_NR_nstat       278
-#define TARGET_FREEBSD_NR_nfstat      279
-#define TARGET_FREEBSD_NR_nlstat      280
-#define TARGET_FREEBSD_NR_preadv      289
-#define TARGET_FREEBSD_NR_pwritev     290
-#define TARGET_FREEBSD_NR_freebsd4_fhstatfs   297
-#define TARGET_FREEBSD_NR_fhopen      298
-#define TARGET_FREEBSD_NR_fhstat      299
-#define TARGET_FREEBSD_NR_modnext     300
-#define TARGET_FREEBSD_NR_modstat     301
-#define TARGET_FREEBSD_NR_modfnext    302
-#define TARGET_FREEBSD_NR_modfind     303
-#define TARGET_FREEBSD_NR_kldload     304
-#define TARGET_FREEBSD_NR_kldunload   305
-#define TARGET_FREEBSD_NR_kldfind     306
-#define TARGET_FREEBSD_NR_kldnext     307
-#define TARGET_FREEBSD_NR_kldstat     308
-#define TARGET_FREEBSD_NR_kldfirstmod 309
-#define TARGET_FREEBSD_NR_getsid      310
-#define TARGET_FREEBSD_NR_setresuid   311
-#define TARGET_FREEBSD_NR_setresgid   312
-#define TARGET_FREEBSD_NR_aio_return  314
-#define TARGET_FREEBSD_NR_aio_suspend 315
-#define TARGET_FREEBSD_NR_aio_cancel  316
-#define TARGET_FREEBSD_NR_aio_error   317
-#define TARGET_FREEBSD_NR_oaio_read   318
-#define TARGET_FREEBSD_NR_oaio_write  319
-#define TARGET_FREEBSD_NR_olio_listio 320
-#define TARGET_FREEBSD_NR_yield       321
-#define TARGET_FREEBSD_NR_mlockall    324
-#define TARGET_FREEBSD_NR_munlockall  325
-#define TARGET_FREEBSD_NR___getcwd    326
-#define TARGET_FREEBSD_NR_sched_setparam      327
-#define TARGET_FREEBSD_NR_sched_getparam      328
-#define TARGET_FREEBSD_NR_sched_setscheduler  329
-#define TARGET_FREEBSD_NR_sched_getscheduler  330
-#define TARGET_FREEBSD_NR_sched_yield 331
-#define TARGET_FREEBSD_NR_sched_get_priority_max      332
-#define TARGET_FREEBSD_NR_sched_get_priority_min      333
-#define TARGET_FREEBSD_NR_sched_rr_get_interval       334
-#define TARGET_FREEBSD_NR_utrace      335
-#define TARGET_FREEBSD_NR_freebsd4_sendfile   336
-#define TARGET_FREEBSD_NR_kldsym      337
-#define TARGET_FREEBSD_NR_jail        338
-#define TARGET_FREEBSD_NR_sigprocmask 340
-#define TARGET_FREEBSD_NR_sigsuspend  341
-#define TARGET_FREEBSD_NR_freebsd4_sigaction  342
-#define TARGET_FREEBSD_NR_sigpending  343
-#define TARGET_FREEBSD_NR_freebsd4_sigreturn  344
-#define TARGET_FREEBSD_NR_sigtimedwait        345
-#define TARGET_FREEBSD_NR_sigwaitinfo 346
-#define TARGET_FREEBSD_NR___acl_get_file      347
-#define TARGET_FREEBSD_NR___acl_set_file      348
-#define TARGET_FREEBSD_NR___acl_get_fd        349
-#define TARGET_FREEBSD_NR___acl_set_fd        350
-#define TARGET_FREEBSD_NR___acl_delete_file   351
-#define TARGET_FREEBSD_NR___acl_delete_fd     352
-#define TARGET_FREEBSD_NR___acl_aclcheck_file 353
-#define TARGET_FREEBSD_NR___acl_aclcheck_fd   354
-#define TARGET_FREEBSD_NR_extattrctl  355
-#define TARGET_FREEBSD_NR_extattr_set_file    356
-#define TARGET_FREEBSD_NR_extattr_get_file    357
-#define TARGET_FREEBSD_NR_extattr_delete_file 358
-#define TARGET_FREEBSD_NR_aio_waitcomplete    359
-#define TARGET_FREEBSD_NR_getresuid   360
-#define TARGET_FREEBSD_NR_getresgid   361
-#define TARGET_FREEBSD_NR_kqueue      362
-#define TARGET_FREEBSD_NR_kevent      363
-#define TARGET_FREEBSD_NR_extattr_set_fd      371
-#define TARGET_FREEBSD_NR_extattr_get_fd      372
-#define TARGET_FREEBSD_NR_extattr_delete_fd   373
-#define TARGET_FREEBSD_NR___setugid   374
-#define TARGET_FREEBSD_NR_nfsclnt     375
-#define TARGET_FREEBSD_NR_eaccess     376
-#define TARGET_FREEBSD_NR_nmount      378
-#define TARGET_FREEBSD_NR___mac_get_proc      384
-#define TARGET_FREEBSD_NR___mac_set_proc      385
-#define TARGET_FREEBSD_NR___mac_get_fd        386
-#define TARGET_FREEBSD_NR___mac_get_file      387
-#define TARGET_FREEBSD_NR___mac_set_fd        388
-#define TARGET_FREEBSD_NR___mac_set_file      389
-#define TARGET_FREEBSD_NR_kenv        390
-#define TARGET_FREEBSD_NR_lchflags    391
-#define TARGET_FREEBSD_NR_uuidgen     392
-#define TARGET_FREEBSD_NR_sendfile    393
-#define TARGET_FREEBSD_NR_mac_syscall 394
-#define TARGET_FREEBSD_NR_getfsstat   395
-#define TARGET_FREEBSD_NR_statfs      396
-#define TARGET_FREEBSD_NR_fstatfs     397
-#define TARGET_FREEBSD_NR_fhstatfs    398
-#define TARGET_FREEBSD_NR_ksem_close  400
-#define TARGET_FREEBSD_NR_ksem_post   401
-#define TARGET_FREEBSD_NR_ksem_wait   402
-#define TARGET_FREEBSD_NR_ksem_trywait        403
-#define TARGET_FREEBSD_NR_ksem_init   404
-#define TARGET_FREEBSD_NR_ksem_open   405
-#define TARGET_FREEBSD_NR_ksem_unlink 406
-#define TARGET_FREEBSD_NR_ksem_getvalue       407
-#define TARGET_FREEBSD_NR_ksem_destroy        408
-#define TARGET_FREEBSD_NR___mac_get_pid       409
-#define TARGET_FREEBSD_NR___mac_get_link      410
-#define TARGET_FREEBSD_NR___mac_set_link      411
-#define TARGET_FREEBSD_NR_extattr_set_link    412
-#define TARGET_FREEBSD_NR_extattr_get_link    413
-#define TARGET_FREEBSD_NR_extattr_delete_link 414
-#define TARGET_FREEBSD_NR___mac_execve        415
-#define TARGET_FREEBSD_NR_sigaction   416
-#define TARGET_FREEBSD_NR_sigreturn   417
-#define TARGET_FREEBSD_NR_getcontext  421
-#define TARGET_FREEBSD_NR_setcontext  422
-#define TARGET_FREEBSD_NR_swapcontext 423
-#define TARGET_FREEBSD_NR_swapoff     424
-#define TARGET_FREEBSD_NR___acl_get_link      425
-#define TARGET_FREEBSD_NR___acl_set_link      426
-#define TARGET_FREEBSD_NR___acl_delete_link   427
-#define TARGET_FREEBSD_NR___acl_aclcheck_link 428
-#define TARGET_FREEBSD_NR_sigwait     429
-#define TARGET_FREEBSD_NR_thr_create  430
-#define TARGET_FREEBSD_NR_thr_exit    431
-#define TARGET_FREEBSD_NR_thr_self    432
-#define TARGET_FREEBSD_NR_thr_kill    433
-#define TARGET_FREEBSD_NR__umtx_lock  434
-#define TARGET_FREEBSD_NR__umtx_unlock        435
-#define TARGET_FREEBSD_NR_jail_attach 436
-#define TARGET_FREEBSD_NR_extattr_list_fd     437
-#define TARGET_FREEBSD_NR_extattr_list_file   438
-#define TARGET_FREEBSD_NR_extattr_list_link   439
-#define TARGET_FREEBSD_NR_ksem_timedwait      441
-#define TARGET_FREEBSD_NR_thr_suspend 442
-#define TARGET_FREEBSD_NR_thr_wake    443
-#define TARGET_FREEBSD_NR_kldunloadf  444
-#define TARGET_FREEBSD_NR_audit       445
-#define TARGET_FREEBSD_NR_auditon     446
-#define TARGET_FREEBSD_NR_getauid     447
-#define TARGET_FREEBSD_NR_setauid     448
-#define TARGET_FREEBSD_NR_getaudit    449
-#define TARGET_FREEBSD_NR_setaudit    450
-#define TARGET_FREEBSD_NR_getaudit_addr       451
-#define TARGET_FREEBSD_NR_setaudit_addr       452
-#define TARGET_FREEBSD_NR_auditctl    453
-#define TARGET_FREEBSD_NR__umtx_op    454
-#define TARGET_FREEBSD_NR_thr_new     455
-#define TARGET_FREEBSD_NR_sigqueue    456
-#define TARGET_FREEBSD_NR_kmq_open    457
-#define TARGET_FREEBSD_NR_kmq_setattr 458
-#define TARGET_FREEBSD_NR_kmq_timedreceive    459
-#define TARGET_FREEBSD_NR_kmq_timedsend       460
-#define TARGET_FREEBSD_NR_kmq_notify  461
-#define TARGET_FREEBSD_NR_kmq_unlink  462
-#define TARGET_FREEBSD_NR_abort2      463
-#define TARGET_FREEBSD_NR_thr_set_name        464
-#define TARGET_FREEBSD_NR_aio_fsync   465
-#define TARGET_FREEBSD_NR_rtprio_thread       466
-#define TARGET_FREEBSD_NR_sctp_peeloff        471
-#define TARGET_FREEBSD_NR_sctp_generic_sendmsg        472
-#define TARGET_FREEBSD_NR_sctp_generic_sendmsg_iov    473
-#define TARGET_FREEBSD_NR_sctp_generic_recvmsg        474
-#define TARGET_FREEBSD_NR_pread       475
-#define TARGET_FREEBSD_NR_pwrite      476
-#define TARGET_FREEBSD_NR_mmap        477
-#define TARGET_FREEBSD_NR_lseek       478
-#define TARGET_FREEBSD_NR_truncate    479
-#define TARGET_FREEBSD_NR_ftruncate   480
-#define TARGET_FREEBSD_NR_thr_kill2   481
-#define TARGET_FREEBSD_NR_shm_open    482
-#define TARGET_FREEBSD_NR_shm_unlink  483
-#define TARGET_FREEBSD_NR_cpuset      484
-#define TARGET_FREEBSD_NR_cpuset_setid        485
-#define TARGET_FREEBSD_NR_cpuset_getid        486
-#define TARGET_FREEBSD_NR_cpuset_getaffinity  487
-#define TARGET_FREEBSD_NR_cpuset_setaffinity  488
-#define TARGET_FREEBSD_NR_faccessat   489
-#define TARGET_FREEBSD_NR_fchmodat    490
-#define TARGET_FREEBSD_NR_fchownat    491
-#define TARGET_FREEBSD_NR_fexecve     492
-#define TARGET_FREEBSD_NR_fstatat     493
-#define TARGET_FREEBSD_NR_futimesat   494
-#define TARGET_FREEBSD_NR_linkat      495
-#define TARGET_FREEBSD_NR_mkdirat     496
-#define TARGET_FREEBSD_NR_mkfifoat    497
-#define TARGET_FREEBSD_NR_mknodat     498
-#define TARGET_FREEBSD_NR_openat      499
-#define TARGET_FREEBSD_NR_readlinkat  500
-#define TARGET_FREEBSD_NR_renameat    501
-#define TARGET_FREEBSD_NR_symlinkat   502
-#define TARGET_FREEBSD_NR_unlinkat    503
-#define TARGET_FREEBSD_NR_posix_openpt        504
+#define TARGET_FREEBSD_NR_syscall   0
+#define TARGET_FREEBSD_NR_exit  1
+#define TARGET_FREEBSD_NR_fork  2
+#define TARGET_FREEBSD_NR_read  3
+#define TARGET_FREEBSD_NR_write 4
+#define TARGET_FREEBSD_NR_open  5
+#define TARGET_FREEBSD_NR_close 6
+#define TARGET_FREEBSD_NR_wait4 7
+                /* 8 is old creat */
+#define TARGET_FREEBSD_NR_link  9
+#define TARGET_FREEBSD_NR_unlink    10
+                /* 11 is obsolete execv */
+#define TARGET_FREEBSD_NR_chdir 12
+#define TARGET_FREEBSD_NR_fchdir    13
+#define TARGET_FREEBSD_NR_mknod 14
+#define TARGET_FREEBSD_NR_chmod 15
+#define TARGET_FREEBSD_NR_chown 16
+#define TARGET_FREEBSD_NR_break 17
+#define TARGET_FREEBSD_NR_freebsd4_getfsstat    18
+                /* 19 is old lseek */
+#define TARGET_FREEBSD_NR_getpid    20
+#define TARGET_FREEBSD_NR_mount 21
+#define TARGET_FREEBSD_NR_unmount   22
+#define TARGET_FREEBSD_NR_setuid    23
+#define TARGET_FREEBSD_NR_getuid    24
+#define TARGET_FREEBSD_NR_geteuid   25
+#define TARGET_FREEBSD_NR_ptrace    26
+#define TARGET_FREEBSD_NR_recvmsg   27
+#define TARGET_FREEBSD_NR_sendmsg   28
+#define TARGET_FREEBSD_NR_recvfrom  29
+#define TARGET_FREEBSD_NR_accept    30
+#define TARGET_FREEBSD_NR_getpeername   31
+#define TARGET_FREEBSD_NR_getsockname   32
+#define TARGET_FREEBSD_NR_access    33
+#define TARGET_FREEBSD_NR_chflags   34
+#define TARGET_FREEBSD_NR_fchflags  35
+#define TARGET_FREEBSD_NR_sync  36
+#define TARGET_FREEBSD_NR_kill  37
+                /* 38 is old stat */
+#define TARGET_FREEBSD_NR_getppid   39
+                /* 40 is old lstat */
+#define TARGET_FREEBSD_NR_dup   41
+#define TARGET_FREEBSD_NR_pipe  42
+#define TARGET_FREEBSD_NR_getegid   43
+#define TARGET_FREEBSD_NR_profil    44
+#define TARGET_FREEBSD_NR_ktrace    45
+                /* 46 is old sigaction */
+#define TARGET_FREEBSD_NR_getgid    47
+                /* 48 is old sigprocmask */
+#define TARGET_FREEBSD_NR_getlogin  49
+#define TARGET_FREEBSD_NR_setlogin  50
+#define TARGET_FREEBSD_NR_acct  51
+                /* 52 is old sigpending */
+#define TARGET_FREEBSD_NR_sigaltstack   53
+#define TARGET_FREEBSD_NR_ioctl 54
+#define TARGET_FREEBSD_NR_reboot    55
+#define TARGET_FREEBSD_NR_revoke    56
+#define TARGET_FREEBSD_NR_symlink   57
+#define TARGET_FREEBSD_NR_readlink  58
+#define TARGET_FREEBSD_NR_execve    59
+#define TARGET_FREEBSD_NR_umask 60
+#define TARGET_FREEBSD_NR_chroot    61
+                /* 62 is old fstat */
+                /* 63 is old getkerninfo */
+                /* 64 is old getpagesize */
+#define TARGET_FREEBSD_NR_msync 65
+#define TARGET_FREEBSD_NR_vfork 66
+                /* 67 is obsolete vread */
+                /* 68 is obsolete vwrite */
+#define TARGET_FREEBSD_NR_sbrk  69
+#define TARGET_FREEBSD_NR_sstk  70
+                /* 71 is old mmap */
+#define TARGET_FREEBSD_NR_vadvise   72
+#define TARGET_FREEBSD_NR_munmap    73
+#define TARGET_FREEBSD_NR_mprotect  74
+#define TARGET_FREEBSD_NR_madvise   75
+                /* 76 is obsolete vhangup */
+                /* 77 is obsolete vlimit */
+#define TARGET_FREEBSD_NR_mincore   78
+#define TARGET_FREEBSD_NR_getgroups 79
+#define TARGET_FREEBSD_NR_setgroups 80
+#define TARGET_FREEBSD_NR_getpgrp   81
+#define TARGET_FREEBSD_NR_setpgid   82
+#define TARGET_FREEBSD_NR_setitimer 83
+                /* 84 is old wait */
+#define TARGET_FREEBSD_NR_swapon    85
+#define TARGET_FREEBSD_NR_getitimer 86
+                /* 87 is old gethostname */
+                /* 88 is old sethostname */
+#define TARGET_FREEBSD_NR_getdtablesize 89
+#define TARGET_FREEBSD_NR_dup2  90
+#define TARGET_FREEBSD_NR_fcntl 92
+#define TARGET_FREEBSD_NR_select    93
+#define TARGET_FREEBSD_NR_fsync 95
+#define TARGET_FREEBSD_NR_setpriority   96
+#define TARGET_FREEBSD_NR_socket    97
+#define TARGET_FREEBSD_NR_connect   98
+                /* 99 is old accept */
+#define TARGET_FREEBSD_NR_getpriority   100
+                /* 101 is old send */
+                /* 102 is old recv */
+                /* 103 is old sigreturn */
+#define TARGET_FREEBSD_NR_bind  104
+#define TARGET_FREEBSD_NR_setsockopt    105
+#define TARGET_FREEBSD_NR_listen    106
+                /* 107 is obsolete vtimes */
+                /* 108 is old sigvec */
+                /* 109 is old sigblock */
+                /* 110 is old sigsetmask */
+                /* 111 is old sigsuspend */
+                /* 112 is old sigstack */
+                /* 113 is old recvmsg */
+                /* 114 is old sendmsg */
+                /* 115 is obsolete vtrace */
+#define TARGET_FREEBSD_NR_gettimeofday  116
+#define TARGET_FREEBSD_NR_getrusage 117
+#define TARGET_FREEBSD_NR_getsockopt    118
+#define TARGET_FREEBSD_NR_readv 120
+#define TARGET_FREEBSD_NR_writev    121
+#define TARGET_FREEBSD_NR_settimeofday  122
+#define TARGET_FREEBSD_NR_fchown    123
+#define TARGET_FREEBSD_NR_fchmod    124
+                /* 125 is old recvfrom */
+#define TARGET_FREEBSD_NR_setreuid  126
+#define TARGET_FREEBSD_NR_setregid  127
+#define TARGET_FREEBSD_NR_rename    128
+                /* 129 is old truncate */
+                /* 130 is old ftruncate */
+#define TARGET_FREEBSD_NR_flock 131
+#define TARGET_FREEBSD_NR_mkfifo    132
+#define TARGET_FREEBSD_NR_sendto    133
+#define TARGET_FREEBSD_NR_shutdown  134
+#define TARGET_FREEBSD_NR_socketpair    135
+#define TARGET_FREEBSD_NR_mkdir 136
+#define TARGET_FREEBSD_NR_rmdir 137
+#define TARGET_FREEBSD_NR_utimes    138
+                /* 139 is obsolete 4.2 sigreturn */
+#define TARGET_FREEBSD_NR_adjtime   140
+                /* 141 is old getpeername */
+                /* 142 is old gethostid */
+                /* 143 is old sethostid */
+                /* 144 is old getrlimit */
+                /* 145 is old setrlimit */
+                /* 146 is old killpg */
+#define TARGET_FREEBSD_NR_killpg    146 /* COMPAT */
+#define TARGET_FREEBSD_NR_setsid    147
+#define TARGET_FREEBSD_NR_quotactl  148
+                /* 149 is old quota */
+                /* 150 is old getsockname */
+#define TARGET_FREEBSD_NR_nlm_syscall   154
+#define TARGET_FREEBSD_NR_nfssvc    155
+                /* 156 is old getdirentries */
+#define TARGET_FREEBSD_NR_freebsd4_statfs   157
+#define TARGET_FREEBSD_NR_freebsd4_fstatfs  158
+#define TARGET_FREEBSD_NR_lgetfh    160
+#define TARGET_FREEBSD_NR_getfh 161
+#define TARGET_FREEBSD_NR_freebsd4_getdomainname    162
+#define TARGET_FREEBSD_NR_freebsd4_setdomainname    163
+#define TARGET_FREEBSD_NR_freebsd4_uname    164
+#define TARGET_FREEBSD_NR_sysarch   165
+#define TARGET_FREEBSD_NR_rtprio    166
+#define TARGET_FREEBSD_NR_semsys    169
+#define TARGET_FREEBSD_NR_msgsys    170
+#define TARGET_FREEBSD_NR_shmsys    171
+#define TARGET_FREEBSD_NR_freebsd6_pread    173
+#define TARGET_FREEBSD_NR_freebsd6_pwrite   174
+#define TARGET_FREEBSD_NR_setfib    175
+#define TARGET_FREEBSD_NR_ntp_adjtime   176
+#define TARGET_FREEBSD_NR_setgid    181
+#define TARGET_FREEBSD_NR_setegid   182
+#define TARGET_FREEBSD_NR_seteuid   183
+#define TARGET_FREEBSD_NR_stat  188
+#define TARGET_FREEBSD_NR_fstat 189
+#define TARGET_FREEBSD_NR_lstat 190
+#define TARGET_FREEBSD_NR_pathconf  191
+#define TARGET_FREEBSD_NR_fpathconf 192
+#define TARGET_FREEBSD_NR_getrlimit 194
+#define TARGET_FREEBSD_NR_setrlimit 195
+#define TARGET_FREEBSD_NR_getdirentries 196
+#define TARGET_FREEBSD_NR_freebsd6_mmap 197
+#define TARGET_FREEBSD_NR___syscall 198
+#define TARGET_FREEBSD_NR_freebsd6_lseek    199
+#define TARGET_FREEBSD_NR_freebsd6_truncate 200
+#define TARGET_FREEBSD_NR_freebsd6_ftruncate    201
+#define TARGET_FREEBSD_NR___sysctl  202
+#define TARGET_FREEBSD_NR_mlock 203
+#define TARGET_FREEBSD_NR_munlock   204
+#define TARGET_FREEBSD_NR_undelete  205
+#define TARGET_FREEBSD_NR_futimes   206
+#define TARGET_FREEBSD_NR_getpgid   207
+#define TARGET_FREEBSD_NR_poll  209
+#define TARGET_FREEBSD_NR_freebsd7___semctl 220
+#define TARGET_FREEBSD_NR_semget    221
+#define TARGET_FREEBSD_NR_semop 222
+#define TARGET_FREEBSD_NR_freebsd7_msgctl   224
+#define TARGET_FREEBSD_NR_msgget    225
+#define TARGET_FREEBSD_NR_msgsnd    226
+#define TARGET_FREEBSD_NR_msgrcv    227
+#define TARGET_FREEBSD_NR_shmat 228
+#define TARGET_FREEBSD_NR_freebsd7_shmctl   229
+#define TARGET_FREEBSD_NR_shmdt 230
+#define TARGET_FREEBSD_NR_shmget    231
+#define TARGET_FREEBSD_NR_clock_gettime 232
+#define TARGET_FREEBSD_NR_clock_settime 233
+#define TARGET_FREEBSD_NR_clock_getres  234
+#define TARGET_FREEBSD_NR_ktimer_create 235
+#define TARGET_FREEBSD_NR_ktimer_delete 236
+#define TARGET_FREEBSD_NR_ktimer_settime    237
+#define TARGET_FREEBSD_NR_ktimer_gettime    238
+#define TARGET_FREEBSD_NR_ktimer_getoverrun 239
+#define TARGET_FREEBSD_NR_nanosleep 240
+#define TARGET_FREEBSD_NR_ntp_gettime   248
+#define TARGET_FREEBSD_NR_minherit  250
+#define TARGET_FREEBSD_NR_rfork 251
+#define TARGET_FREEBSD_NR_openbsd_poll  252
+#define TARGET_FREEBSD_NR_issetugid 253
+#define TARGET_FREEBSD_NR_lchown    254
+#define TARGET_FREEBSD_NR_aio_read  255
+#define TARGET_FREEBSD_NR_aio_write 256
+#define TARGET_FREEBSD_NR_lio_listio    257
+#define TARGET_FREEBSD_NR_getdents  272
+#define TARGET_FREEBSD_NR_lchmod    274
+#define TARGET_FREEBSD_NR_netbsd_lchown 275
+#define TARGET_FREEBSD_NR_lutimes   276
+#define TARGET_FREEBSD_NR_netbsd_msync  277
+#define TARGET_FREEBSD_NR_nstat 278
+#define TARGET_FREEBSD_NR_nfstat    279
+#define TARGET_FREEBSD_NR_nlstat    280
+#define TARGET_FREEBSD_NR_preadv    289
+#define TARGET_FREEBSD_NR_pwritev   290
+#define TARGET_FREEBSD_NR_freebsd4_fhstatfs 297
+#define TARGET_FREEBSD_NR_fhopen    298
+#define TARGET_FREEBSD_NR_fhstat    299
+#define TARGET_FREEBSD_NR_modnext   300
+#define TARGET_FREEBSD_NR_modstat   301
+#define TARGET_FREEBSD_NR_modfnext  302
+#define TARGET_FREEBSD_NR_modfind   303
+#define TARGET_FREEBSD_NR_kldload   304
+#define TARGET_FREEBSD_NR_kldunload 305
+#define TARGET_FREEBSD_NR_kldfind   306
+#define TARGET_FREEBSD_NR_kldnext   307
+#define TARGET_FREEBSD_NR_kldstat   308
+#define TARGET_FREEBSD_NR_kldfirstmod   309
+#define TARGET_FREEBSD_NR_getsid    310
+#define TARGET_FREEBSD_NR_setresuid 311
+#define TARGET_FREEBSD_NR_setresgid 312
+                /* 313 is obsolete signanosleep */
+#define TARGET_FREEBSD_NR_aio_return    314
+#define TARGET_FREEBSD_NR_aio_suspend   315
+#define TARGET_FREEBSD_NR_aio_cancel    316
+#define TARGET_FREEBSD_NR_aio_error 317
+#define TARGET_FREEBSD_NR_oaio_read 318
+#define TARGET_FREEBSD_NR_oaio_write    319
+#define TARGET_FREEBSD_NR_olio_listio   320
+#define TARGET_FREEBSD_NR_yield 321
+                /* 322 is obsolete thr_sleep */
+                /* 323 is obsolete thr_wakeup */
+#define TARGET_FREEBSD_NR_mlockall  324
+#define TARGET_FREEBSD_NR_munlockall    325
+#define TARGET_FREEBSD_NR___getcwd  326
+#define TARGET_FREEBSD_NR_sched_setparam    327
+#define TARGET_FREEBSD_NR_sched_getparam    328
+#define TARGET_FREEBSD_NR_sched_setscheduler    329
+#define TARGET_FREEBSD_NR_sched_getscheduler    330
+#define TARGET_FREEBSD_NR_sched_yield   331
+#define TARGET_FREEBSD_NR_sched_get_priority_max    332
+#define TARGET_FREEBSD_NR_sched_get_priority_min    333
+#define TARGET_FREEBSD_NR_sched_rr_get_interval 334
+#define TARGET_FREEBSD_NR_utrace    335
+#define TARGET_FREEBSD_NR_freebsd4_sendfile 336
+#define TARGET_FREEBSD_NR_kldsym    337
+#define TARGET_FREEBSD_NR_jail  338
+#define TARGET_FREEBSD_NR_nnpfs_syscall 339
+#define TARGET_FREEBSD_NR_sigprocmask   340
+#define TARGET_FREEBSD_NR_sigsuspend    341
+#define TARGET_FREEBSD_NR_freebsd4_sigaction    342
+#define TARGET_FREEBSD_NR_sigpending    343
+#define TARGET_FREEBSD_NR_freebsd4_sigreturn    344
+#define TARGET_FREEBSD_NR_sigtimedwait  345
+#define TARGET_FREEBSD_NR_sigwaitinfo   346
+#define TARGET_FREEBSD_NR___acl_get_file    347
+#define TARGET_FREEBSD_NR___acl_set_file    348
+#define TARGET_FREEBSD_NR___acl_get_fd  349
+#define TARGET_FREEBSD_NR___acl_set_fd  350
+#define TARGET_FREEBSD_NR___acl_delete_file 351
+#define TARGET_FREEBSD_NR___acl_delete_fd   352
+#define TARGET_FREEBSD_NR___acl_aclcheck_file   353
+#define TARGET_FREEBSD_NR___acl_aclcheck_fd 354
+#define TARGET_FREEBSD_NR_extattrctl    355
+#define TARGET_FREEBSD_NR_extattr_set_file  356
+#define TARGET_FREEBSD_NR_extattr_get_file  357
+#define TARGET_FREEBSD_NR_extattr_delete_file   358
+#define TARGET_FREEBSD_NR_aio_waitcomplete  359
+#define TARGET_FREEBSD_NR_getresuid 360
+#define TARGET_FREEBSD_NR_getresgid 361
+#define TARGET_FREEBSD_NR_kqueue    362
+#define TARGET_FREEBSD_NR_kevent    363
+#define TARGET_FREEBSD_NR_extattr_set_fd    371
+#define TARGET_FREEBSD_NR_extattr_get_fd    372
+#define TARGET_FREEBSD_NR_extattr_delete_fd 373
+#define TARGET_FREEBSD_NR___setugid 374
+#define TARGET_FREEBSD_NR_eaccess   376
+#define TARGET_FREEBSD_NR_afs3_syscall  377
+#define TARGET_FREEBSD_NR_nmount    378
+#define TARGET_FREEBSD_NR___mac_get_proc    384
+#define TARGET_FREEBSD_NR___mac_set_proc    385
+#define TARGET_FREEBSD_NR___mac_get_fd  386
+#define TARGET_FREEBSD_NR___mac_get_file    387
+#define TARGET_FREEBSD_NR___mac_set_fd  388
+#define TARGET_FREEBSD_NR___mac_set_file    389
+#define TARGET_FREEBSD_NR_kenv  390
+#define TARGET_FREEBSD_NR_lchflags  391
+#define TARGET_FREEBSD_NR_uuidgen   392
+#define TARGET_FREEBSD_NR_sendfile  393
+#define TARGET_FREEBSD_NR_mac_syscall   394
+#define TARGET_FREEBSD_NR_getfsstat 395
+#define TARGET_FREEBSD_NR_statfs    396
+#define TARGET_FREEBSD_NR_fstatfs   397
+#define TARGET_FREEBSD_NR_fhstatfs  398
+#define TARGET_FREEBSD_NR_ksem_close    400
+#define TARGET_FREEBSD_NR_ksem_post 401
+#define TARGET_FREEBSD_NR_ksem_wait 402
+#define TARGET_FREEBSD_NR_ksem_trywait  403
+#define TARGET_FREEBSD_NR_ksem_init 404
+#define TARGET_FREEBSD_NR_ksem_open 405
+#define TARGET_FREEBSD_NR_ksem_unlink   406
+#define TARGET_FREEBSD_NR_ksem_getvalue 407
+#define TARGET_FREEBSD_NR_ksem_destroy  408
+#define TARGET_FREEBSD_NR___mac_get_pid 409
+#define TARGET_FREEBSD_NR___mac_get_link    410
+#define TARGET_FREEBSD_NR___mac_set_link    411
+#define TARGET_FREEBSD_NR_extattr_set_link  412
+#define TARGET_FREEBSD_NR_extattr_get_link  413
+#define TARGET_FREEBSD_NR_extattr_delete_link   414
+#define TARGET_FREEBSD_NR___mac_execve  415
+#define TARGET_FREEBSD_NR_sigaction 416
+#define TARGET_FREEBSD_NR_sigreturn 417
+#define TARGET_FREEBSD_NR_getcontext    421
+#define TARGET_FREEBSD_NR_setcontext    422
+#define TARGET_FREEBSD_NR_swapcontext   423
+#define TARGET_FREEBSD_NR_swapoff   424
+#define TARGET_FREEBSD_NR___acl_get_link    425
+#define TARGET_FREEBSD_NR___acl_set_link    426
+#define TARGET_FREEBSD_NR___acl_delete_link 427
+#define TARGET_FREEBSD_NR___acl_aclcheck_link   428
+#define TARGET_FREEBSD_NR_sigwait   429
+#define TARGET_FREEBSD_NR_thr_create    430
+#define TARGET_FREEBSD_NR_thr_exit  431
+#define TARGET_FREEBSD_NR_thr_self  432
+#define TARGET_FREEBSD_NR_thr_kill  433
+#define TARGET_FREEBSD_NR__umtx_lock    434
+#define TARGET_FREEBSD_NR__umtx_unlock  435
+#define TARGET_FREEBSD_NR_jail_attach   436
+#define TARGET_FREEBSD_NR_extattr_list_fd   437
+#define TARGET_FREEBSD_NR_extattr_list_file 438
+#define TARGET_FREEBSD_NR_extattr_list_link 439
+#define TARGET_FREEBSD_NR_ksem_timedwait    441
+#define TARGET_FREEBSD_NR_thr_suspend   442
+#define TARGET_FREEBSD_NR_thr_wake  443
+#define TARGET_FREEBSD_NR_kldunloadf    444
+#define TARGET_FREEBSD_NR_audit 445
+#define TARGET_FREEBSD_NR_auditon   446
+#define TARGET_FREEBSD_NR_getauid   447
+#define TARGET_FREEBSD_NR_setauid   448
+#define TARGET_FREEBSD_NR_getaudit  449
+#define TARGET_FREEBSD_NR_setaudit  450
+#define TARGET_FREEBSD_NR_getaudit_addr 451
+#define TARGET_FREEBSD_NR_setaudit_addr 452
+#define TARGET_FREEBSD_NR_auditctl  453
+#define TARGET_FREEBSD_NR__umtx_op  454
+#define TARGET_FREEBSD_NR_thr_new   455
+#define TARGET_FREEBSD_NR_sigqueue  456
+#define TARGET_FREEBSD_NR_kmq_open  457
+#define TARGET_FREEBSD_NR_kmq_setattr   458
+#define TARGET_FREEBSD_NR_kmq_timedreceive  459
+#define TARGET_FREEBSD_NR_kmq_timedsend 460
+#define TARGET_FREEBSD_NR_kmq_notify    461
+#define TARGET_FREEBSD_NR_kmq_unlink    462
+#define TARGET_FREEBSD_NR_abort2    463
+#define TARGET_FREEBSD_NR_thr_set_name  464
+#define TARGET_FREEBSD_NR_aio_fsync 465
+#define TARGET_FREEBSD_NR_rtprio_thread 466
+#define TARGET_FREEBSD_NR_sctp_peeloff  471
+#define TARGET_FREEBSD_NR_sctp_generic_sendmsg  472
+#define TARGET_FREEBSD_NR_sctp_generic_sendmsg_iov  473
+#define TARGET_FREEBSD_NR_sctp_generic_recvmsg  474
+#define TARGET_FREEBSD_NR_pread 475
+#define TARGET_FREEBSD_NR_pwrite    476
+#define TARGET_FREEBSD_NR_mmap  477
+#define TARGET_FREEBSD_NR_lseek 478
+#define TARGET_FREEBSD_NR_truncate  479
+#define TARGET_FREEBSD_NR_ftruncate 480
+#define TARGET_FREEBSD_NR_thr_kill2 481
+#define TARGET_FREEBSD_NR_shm_open  482
+#define TARGET_FREEBSD_NR_shm_unlink    483
+#define TARGET_FREEBSD_NR_cpuset    484
+#define TARGET_FREEBSD_NR_cpuset_setid  485
+#define TARGET_FREEBSD_NR_cpuset_getid  486
+#define TARGET_FREEBSD_NR_cpuset_getaffinity    487
+#define TARGET_FREEBSD_NR_cpuset_setaffinity    488
+#define TARGET_FREEBSD_NR_faccessat 489
+#define TARGET_FREEBSD_NR_fchmodat  490
+#define TARGET_FREEBSD_NR_fchownat  491
+#define TARGET_FREEBSD_NR_fexecve   492
+#define TARGET_FREEBSD_NR_fstatat   493
+#define TARGET_FREEBSD_NR_futimesat 494
+#define TARGET_FREEBSD_NR_linkat    495
+#define TARGET_FREEBSD_NR_mkdirat   496
+#define TARGET_FREEBSD_NR_mkfifoat  497
+#define TARGET_FREEBSD_NR_mknodat   498
+#define TARGET_FREEBSD_NR_openat    499
+#define TARGET_FREEBSD_NR_readlinkat    500
+#define TARGET_FREEBSD_NR_renameat  501
+#define TARGET_FREEBSD_NR_symlinkat 502
+#define TARGET_FREEBSD_NR_unlinkat  503
+#define TARGET_FREEBSD_NR_posix_openpt  504
+#define TARGET_FREEBSD_NR_gssd_syscall  505
+#define TARGET_FREEBSD_NR_jail_get  506
+#define TARGET_FREEBSD_NR_jail_set  507
+#define TARGET_FREEBSD_NR_jail_remove   508
+#define TARGET_FREEBSD_NR_closefrom 509
+#define TARGET_FREEBSD_NR___semctl  510
+#define TARGET_FREEBSD_NR_msgctl    511
+#define TARGET_FREEBSD_NR_shmctl    512
+#define TARGET_FREEBSD_NR_lpathconf 513
+#define TARGET_FREEBSD_NR_cap_new   514
+#define TARGET_FREEBSD_NR_cap_getrights 515
+#define TARGET_FREEBSD_NR_cap_enter 516
+#define TARGET_FREEBSD_NR_cap_getmode   517
+#define TARGET_FREEBSD_NR_pdfork    518
+#define TARGET_FREEBSD_NR_pdkill    519
+#define TARGET_FREEBSD_NR_pdgetpid  520
+#define TARGET_FREEBSD_NR_pselect   522
+#define TARGET_FREEBSD_NR_getloginclass 523
+#define TARGET_FREEBSD_NR_setloginclass 524
+#define TARGET_FREEBSD_NR_rctl_get_racct    525
+#define TARGET_FREEBSD_NR_rctl_get_rules    526
+#define TARGET_FREEBSD_NR_rctl_get_limits   527
+#define TARGET_FREEBSD_NR_rctl_add_rule 528
+#define TARGET_FREEBSD_NR_rctl_remove_rule  529
+#define TARGET_FREEBSD_NR_posix_fallocate   530
+#define TARGET_FREEBSD_NR_posix_fadvise 531
+#define TARGET_FREEBSD_NR_MAXSYSCALL    532

bsd-user/main.c

@@ -1004,7 +1004,7 @@ int main(int argc, char **argv)
 
 #if defined(TARGET_I386)
     env->cr[0] = CR0_PG_MASK | CR0_WP_MASK | CR0_PE_MASK;
-    env->hflags |= HF_PE_MASK;
+    env->hflags |= HF_PE_MASK | HF_CPL_MASK;
     if (env->features[FEAT_1_EDX] & CPUID_SSE) {
         env->cr[4] |= CR4_OSFXSR_MASK;
         env->hflags |= HF_OSFXSR_MASK;

bsd-user/mmap.c

@@ -74,66 +74,6 @@ void mmap_unlock(void)
 }
 #endif
 
-static void *bsd_vmalloc(size_t size)
-{
-    void *p;
-    mmap_lock();
-    /* Use map and mark the pages as used.  */
-    p = mmap(NULL, size, PROT_READ | PROT_WRITE,
-             MAP_PRIVATE | MAP_ANON, -1, 0);
-
-    if (h2g_valid(p)) {
-        /* Allocated region overlaps guest address space.
-           This may recurse.  */
-        abi_ulong addr = h2g(p);
-        page_set_flags(addr & TARGET_PAGE_MASK, TARGET_PAGE_ALIGN(addr + size),
-                       PAGE_RESERVED);
-    }
-
-    mmap_unlock();
-    return p;
-}
-
-void *g_malloc(size_t size)
-{
-    char * p;
-    size += 16;
-    p = bsd_vmalloc(size);
-    *(size_t *)p = size;
-    return p + 16;
-}
-
-/* We use map, which is always zero initialized.  */
-void * g_malloc0(size_t size)
-{
-    return g_malloc(size);
-}
-
-void g_free(void *ptr)
-{
-    /* FIXME: We should unmark the reserved pages here.  However this gets
-       complicated when one target page spans multiple host pages, so we
-       don't bother.  */
-    size_t *p;
-    p = (size_t *)((char *)ptr - 16);
-    munmap(p, *p);
-}
-
-void *g_realloc(void *ptr, size_t size)
-{
-    size_t old_size, copy;
-    void *new_ptr;
-
-    if (!ptr)
-        return g_malloc(size);
-    old_size = *(size_t *)((char *)ptr - 16);
-    copy = old_size < size ? old_size : size;
-    new_ptr = g_malloc(size);
-    memcpy(new_ptr, ptr, copy);
-    g_free(ptr);
-    return new_ptr;
-}
-
 /* NOTE: all the constants are the HOST ones, but addresses are target. */
 int target_mprotect(abi_ulong start, abi_ulong len, int prot)
 {

bsd-user/qemu.h

@@ -1,3 +1,19 @@
+/*
+ *  qemu bsd user mode definition
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
 #ifndef QEMU_H
 #define QEMU_H
 
@@ -5,6 +21,7 @@
 #include <string.h>
 
 #include "cpu.h"
+#include "exec/cpu_ldst.h"
 
 #undef DEBUG_REMAP
 #ifdef DEBUG_REMAP
@@ -149,6 +166,16 @@ void fork_end(int child);
 #include "qemu/log.h"
 
 /* strace.c */
+struct syscallname {
+    int nr;
+    const char *name;
+    const char *format;
+    void (*call)(const struct syscallname *,
+                 abi_long, abi_long, abi_long,
+                 abi_long, abi_long, abi_long);
+    void (*result)(const struct syscallname *, abi_long);
+};
+
 void
 print_freebsd_syscall(int num,
                       abi_long arg1, abi_long arg2, abi_long arg3,

bsd-user/strace.c

@@ -1,37 +1,71 @@
+/*
+ *  System call tracing and debugging
+ *
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
 #include <stdio.h>
 #include <errno.h>
 #include <sys/select.h>
 #include <sys/types.h>
 #include <unistd.h>
 #include <sys/syscall.h>
+#include <sys/ioccom.h>
+#include <ctype.h>
+
 #include "qemu.h"
 
-int do_strace=0;
-
-struct syscallname {
-    int nr;
-    const char *name;
-    const char *format;
-    void (*call)(const struct syscallname *,
-                 abi_long, abi_long, abi_long,
-                 abi_long, abi_long, abi_long);
-    void (*result)(const struct syscallname *, abi_long);
-};
+int do_strace;
 
 /*
  * Utility functions
  */
 
-static void
-print_execve(const struct syscallname *name,
-             abi_long arg1, abi_long arg2, abi_long arg3,
-             abi_long arg4, abi_long arg5, abi_long arg6)
+static void print_sysctl(const struct syscallname *name, abi_long arg1,
+        abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5,
+        abi_long arg6)
+{
+    uint32_t i;
+    int32_t *namep;
+
+    gemu_log("%s({ ", name->name);
+    namep = lock_user(VERIFY_READ, arg1, sizeof(int32_t) * arg2, 1);
+    if (namep) {
+        int32_t *p = namep;
+
+        for (i = 0; i < (uint32_t)arg2; i++) {
+            gemu_log("%d ", tswap32(*p++));
+        }
+        unlock_user(namep, arg1, 0);
+    }
+    gemu_log("}, %u, 0x" TARGET_ABI_FMT_lx ", 0x" TARGET_ABI_FMT_lx ", 0x"
+        TARGET_ABI_FMT_lx ", 0x" TARGET_ABI_FMT_lx ")",
+        (uint32_t)arg2, arg3, arg4, arg5, arg6);
+}
+
+static void print_execve(const struct syscallname *name, abi_long arg1,
+        abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5,
+        abi_long arg6)
 {
     abi_ulong arg_ptr_addr;
     char *s;
 
-    if (!(s = lock_user_string(arg1)))
+    s = lock_user_string(arg1);
+    if (s == NULL) {
         return;
+    }
     gemu_log("%s(\"%s\",{", name->name, s);
     unlock_user(s, arg1, 0);
 
@@ -39,29 +73,48 @@ print_execve(const struct syscallname *name,
         abi_ulong *arg_ptr, arg_addr;
 
         arg_ptr = lock_user(VERIFY_READ, arg_ptr_addr, sizeof(abi_ulong), 1);
-        if (!arg_ptr)
+        if (!arg_ptr) {
             return;
+        }
         arg_addr = tswapl(*arg_ptr);
         unlock_user(arg_ptr, arg_ptr_addr, 0);
-        if (!arg_addr)
+        if (!arg_addr) {
             break;
+        }
         if ((s = lock_user_string(arg_addr))) {
             gemu_log("\"%s\",", s);
             unlock_user(s, arg_addr, 0);
         }
     }
-
     gemu_log("NULL})");
 }
 
+static void print_ioctl(const struct syscallname *name,
+        abi_long arg1, abi_long arg2, abi_long arg3, abi_long arg4,
+        abi_long arg5, abi_long arg6)
+{
+    /* Decode the ioctl request */
+    gemu_log("%s(%d, 0x%0lx { IO%s%s GRP:0x%x('%c') CMD:%d LEN:%d }, 0x"
+            TARGET_ABI_FMT_lx ", ...)",
+            name->name,
+            (int)arg1,
+            (unsigned long)arg2,
+            arg2 & IOC_OUT ? "R" : "",
+            arg2 & IOC_IN ? "W" : "",
+            (unsigned)IOCGROUP(arg2),
+            isprint(IOCGROUP(arg2)) ? (char)IOCGROUP(arg2) : '?',
+            (int)arg2 & 0xFF,
+            (int)IOCPARM_LEN(arg2),
+            arg3);
+}
+
 /*
  * Variants for the return value output function
  */
 
-static void
-print_syscall_ret_addr(const struct syscallname *name, abi_long ret)
+static void print_syscall_ret_addr(const struct syscallname *name, abi_long ret)
 {
-if( ret == -1 ) {
+    if (ret == -1) {
         gemu_log(" = -1 errno=%d (%s)\n", errno, strerror(errno));
     } else {
         gemu_log(" = 0x" TARGET_ABI_FMT_lx "\n", ret);
@@ -90,10 +143,9 @@ static const struct syscallname openbsd_scnames[] = {
 #include "openbsd/strace.list"
 };
 
-static void
-print_syscall(int num, const struct syscallname *scnames, unsigned int nscnames,
-              abi_long arg1, abi_long arg2, abi_long arg3,
-              abi_long arg4, abi_long arg5, abi_long arg6)
+static void print_syscall(int num, const struct syscallname *scnames,
+        unsigned int nscnames, abi_long arg1, abi_long arg2, abi_long arg3,
+        abi_long arg4, abi_long arg5, abi_long arg6)
 {
     unsigned int i;
     const char *format="%s(" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ","
@@ -102,36 +154,37 @@ print_syscall(int num, const struct syscallname *scnames, unsigned int nscnames,
 
     gemu_log("%d ", getpid() );
 
-    for (i = 0; i < nscnames; i++)
+    for (i = 0; i < nscnames; i++) {
         if (scnames[i].nr == num) {
             if (scnames[i].call != NULL) {
                 scnames[i].call(&scnames[i], arg1, arg2, arg3, arg4, arg5,
-                                arg6);
+                        arg6);
             } else {
                 /* XXX: this format system is broken because it uses
                    host types and host pointers for strings */
-                if (scnames[i].format != NULL)
+                if (scnames[i].format != NULL) {
                     format = scnames[i].format;
-                gemu_log(format, scnames[i].name, arg1, arg2, arg3, arg4,
-                         arg5, arg6);
+                }
+                gemu_log(format, scnames[i].name, arg1, arg2, arg3, arg4, arg5,
+                        arg6);
             }
             return;
         }
+    }
     gemu_log("Unknown syscall %d\n", num);
 }
 
-static void
-print_syscall_ret(int num, abi_long ret, const struct syscallname *scnames,
-                  unsigned int nscnames)
+static void print_syscall_ret(int num, abi_long ret,
+        const struct syscallname *scnames, unsigned int nscnames)
 {
     unsigned int i;
 
-    for (i = 0; i < nscnames; i++)
+    for (i = 0; i < nscnames; i++) {
         if (scnames[i].nr == num) {
             if (scnames[i].result != NULL) {
                 scnames[i].result(&scnames[i], ret);
             } else {
-                if( ret < 0 ) {
+                if (ret < 0) {
                     gemu_log(" = -1 errno=" TARGET_ABI_FMT_ld " (%s)\n", -ret,
                              strerror(-ret));
                 } else {
@@ -140,52 +193,50 @@ print_syscall_ret(int num, abi_long ret, const struct syscallname *scnames,
             }
             break;
         }
+    }
 }
 
 /*
  * The public interface to this module.
  */
-void
-print_freebsd_syscall(int num,
-                      abi_long arg1, abi_long arg2, abi_long arg3,
-                      abi_long arg4, abi_long arg5, abi_long arg6)
+void print_freebsd_syscall(int num, abi_long arg1, abi_long arg2, abi_long arg3,
+        abi_long arg4, abi_long arg5, abi_long arg6)
 {
-    print_syscall(num, freebsd_scnames, ARRAY_SIZE(freebsd_scnames),
-                  arg1, arg2, arg3, arg4, arg5, arg6);
+
+    print_syscall(num, freebsd_scnames, ARRAY_SIZE(freebsd_scnames), arg1, arg2,
+            arg3, arg4, arg5, arg6);
 }
 
-void
-print_freebsd_syscall_ret(int num, abi_long ret)
+void print_freebsd_syscall_ret(int num, abi_long ret)
 {
+
     print_syscall_ret(num, ret, freebsd_scnames, ARRAY_SIZE(freebsd_scnames));
 }
 
-void
-print_netbsd_syscall(int num,
-                      abi_long arg1, abi_long arg2, abi_long arg3,
-                      abi_long arg4, abi_long arg5, abi_long arg6)
+void print_netbsd_syscall(int num, abi_long arg1, abi_long arg2, abi_long arg3,
+        abi_long arg4, abi_long arg5, abi_long arg6)
 {
+
     print_syscall(num, netbsd_scnames, ARRAY_SIZE(netbsd_scnames),
                   arg1, arg2, arg3, arg4, arg5, arg6);
 }
 
-void
-print_netbsd_syscall_ret(int num, abi_long ret)
+void print_netbsd_syscall_ret(int num, abi_long ret)
 {
+
     print_syscall_ret(num, ret, netbsd_scnames, ARRAY_SIZE(netbsd_scnames));
 }
 
-void
-print_openbsd_syscall(int num,
-                      abi_long arg1, abi_long arg2, abi_long arg3,
-                      abi_long arg4, abi_long arg5, abi_long arg6)
+void print_openbsd_syscall(int num, abi_long arg1, abi_long arg2, abi_long arg3,
+        abi_long arg4, abi_long arg5, abi_long arg6)
 {
-    print_syscall(num, openbsd_scnames, ARRAY_SIZE(openbsd_scnames),
-                  arg1, arg2, arg3, arg4, arg5, arg6);
+
+    print_syscall(num, openbsd_scnames, ARRAY_SIZE(openbsd_scnames), arg1, arg2,
+            arg3, arg4, arg5, arg6);
 }
 
-void
-print_openbsd_syscall_ret(int num, abi_long ret)
+void print_openbsd_syscall_ret(int num, abi_long ret)
 {
+
     print_syscall_ret(num, ret, openbsd_scnames, ARRAY_SIZE(openbsd_scnames));
 }

configure

@@ -3,6 +3,11 @@
 # qemu configure script (c) 2003 Fabrice Bellard
 #
 
+# Unset some variables known to interfere with behavior of common tools,
+# just as autoconf does.
+CLICOLOR_FORCE= GREP_OPTIONS=
+unset CLICOLOR_FORCE GREP_OPTIONS
+
 # Temporary directory used for files created while
 # configure runs. Since it is in the build directory
 # we can safely blow away any previous version of it
@@ -182,6 +187,10 @@ path_of() {
     return 1
 }
 
+have_backend () {
+    echo "$trace_backends" | grep "$1" >/dev/null
+}
+
 # default parameters
 source_path=`dirname "$0"`
 cpu=""
@@ -293,7 +302,7 @@ pkgversion=""
 pie=""
 zero_malloc=""
 qom_cast_debug="yes"
-trace_backend="nop"
+trace_backends="nop"
 trace_file="trace"
 spice=""
 rbd=""
@@ -302,8 +311,8 @@ libusb=""
 usb_redir=""
 glx=""
 zlib="yes"
-lzo="no"
-snappy="no"
+lzo=""
+snappy=""
 guest_agent=""
 guest_agent_with_vss="no"
 vss_win32_sdk=""
@@ -321,10 +330,11 @@ virtio_blk_data_plane=""
 gtk=""
 gtkabi=""
 vte=""
-tpm="no"
+tpm="yes"
 libssh2=""
 vhdx=""
-quorum="no"
+quorum=""
+numa=""
 
 # parse CC options first
 for opt do
@@ -537,6 +547,9 @@ fi
 
 # OS specific
 
+# host *BSD for user mode
+HOST_VARIANT_DIR=""
+
 case $targetos in
 CYGWIN*)
   mingw32="yes"
@@ -562,12 +575,14 @@ FreeBSD)
   # needed for kinfo_getvmmap(3) in libutil.h
   LIBS="-lutil $LIBS"
   netmap=""  # enable netmap autodetect
+  HOST_VARIANT_DIR="freebsd"
 ;;
 DragonFly)
   bsd="yes"
   make="${MAKE-gmake}"
   audio_drv_list="oss"
   audio_possible_drivers="oss sdl esd pa"
+  HOST_VARIANT_DIR="dragonfly"
 ;;
 NetBSD)
   bsd="yes"
@@ -575,12 +590,14 @@ NetBSD)
   audio_drv_list="oss"
   audio_possible_drivers="oss sdl esd"
   oss_lib="-lossaudio"
+  HOST_VARIANT_DIR="netbsd"
 ;;
 OpenBSD)
   bsd="yes"
   make="${MAKE-gmake}"
   audio_drv_list="sdl"
   audio_possible_drivers="sdl esd"
+  HOST_VARIANT_DIR="openbsd"
 ;;
 Darwin)
   bsd="yes"
@@ -598,6 +615,7 @@ Darwin)
   # Disable attempts to use ObjectiveC features in os/object.h since they
   # won't work when we're compiling with gcc as a C compiler.
   QEMU_CFLAGS="-DOS_OBJECT_USE_OBJC=0 $QEMU_CFLAGS"
+  HOST_VARIANT_DIR="darwin"
 ;;
 SunOS)
   solaris="yes"
@@ -753,7 +771,10 @@ for opt do
   ;;
   --target-list=*) target_list="$optarg"
   ;;
-  --enable-trace-backend=*) trace_backend="$optarg"
+  --enable-trace-backends=*) trace_backends="$optarg"
+  ;;
+  # XXX: backwards compatibility
+  --enable-trace-backend=*) trace_backends="$optarg"
   ;;
   --with-trace-file=*) trace_file="$optarg"
   ;;
@@ -1030,8 +1051,12 @@ for opt do
   ;;
   --disable-zlib-test) zlib="no"
   ;;
+  --disable-lzo) lzo="no"
+  ;;
   --enable-lzo) lzo="yes"
   ;;
+  --disable-snappy) snappy="no"
+  ;;
   --enable-snappy) snappy="yes"
   ;;
   --enable-guest-agent) guest_agent="yes"
@@ -1080,6 +1105,8 @@ for opt do
   ;;
   --enable-vte) vte="yes"
   ;;
+  --disable-tpm) tpm="no"
+  ;;
   --enable-tpm) tpm="yes"
   ;;
   --disable-libssh2) libssh2="no"
@@ -1094,6 +1121,10 @@ for opt do
   ;;
   --enable-quorum) quorum="yes"
   ;;
+  --disable-numa) numa="no"
+  ;;
+  --enable-numa) numa="yes"
+  ;;
   *)
       echo "ERROR: unknown option $opt"
       echo "Try '$0 --help' for more information"
@@ -1320,7 +1351,7 @@ Advanced options (experts only):
   --disable-docs           disable documentation build
   --disable-vhost-net      disable vhost-net acceleration support
   --enable-vhost-net       enable vhost-net acceleration support
-  --enable-trace-backend=B Set trace backend
+  --enable-trace-backends=B Set trace backend
                            Available backends: $($python $source_path/scripts/tracetool.py --list-backends)
   --with-trace-file=NAME   Full PATH,NAME of file to store traces
                            Default:trace-<pid>
@@ -1353,6 +1384,7 @@ Advanced options (experts only):
   --disable-glusterfs      disable GlusterFS backend
   --enable-gcov            enable test coverage analysis with gcov
   --gcov=GCOV              use specified gcov [$gcov_tool]
+  --disable-tpm            disable TPM support
   --enable-tpm             enable TPM support
   --disable-libssh2        disable ssh block device support
   --enable-libssh2         enable ssh block device support
@@ -1360,6 +1392,8 @@ Advanced options (experts only):
   --enable-vhdx            enable support for the Microsoft VHDX image format
   --disable-quorum         disable quorum block filter support
   --enable-quorum          enable quorum block filter support
+  --disable-numa           disable libnuma support
+  --enable-numa            enable libnuma support
 
 NOTE: The object files are built at the place where configure is launched
 EOF
@@ -1729,13 +1763,14 @@ if test "$lzo" != "no" ; then
 int main(void) { lzo_version(); return 0; }
 EOF
     if compile_prog "" "-llzo2" ; then
-        :
+        libs_softmmu="$libs_softmmu -llzo2"
+        lzo="yes"
     else
-        error_exit "lzo check failed" \
-            "Make sure to have the lzo libs and headers installed."
+        if test "$lzo" = "yes"; then
+            feature_not_found "liblzo2" "Install liblzo2 devel"
+        fi
+        lzo="no"
     fi
-
-    libs_softmmu="$libs_softmmu -llzo2"
 fi
 
 ##########################################
@@ -1747,13 +1782,14 @@ if test "$snappy" != "no" ; then
 int main(void) { snappy_max_compressed_length(4096); return 0; }
 EOF
     if compile_prog "" "-lsnappy" ; then
-        :
+        libs_softmmu="$libs_softmmu -lsnappy"
+        snappy="yes"
     else
-        error_exit "snappy check failed" \
-            "Make sure to have the snappy libs and headers installed."
+        if test "$snappy" = "yes"; then
+            feature_not_found "libsnappy" "Install libsnappy devel"
+        fi
+        snappy="no"
     fi
-
-    libs_softmmu="$libs_softmmu -lsnappy"
 fi
 
 ##########################################
@@ -1986,6 +2022,7 @@ fi
 
 if test "$gtk" != "no"; then
     gtkpackage="gtk+-$gtkabi"
+    gtkx11package="gtk+-x11-$gtkabi"
     if test "$gtkabi" = "3.0" ; then
       gtkversion="3.0.0"
     else
@@ -1994,6 +2031,9 @@ if test "$gtk" != "no"; then
     if $pkg_config --exists "$gtkpackage >= $gtkversion"; then
         gtk_cflags=`$pkg_config --cflags $gtkpackage`
         gtk_libs=`$pkg_config --libs $gtkpackage`
+        if $pkg_config --exists "$gtkx11package >= $gtkversion"; then
+            gtk_libs="$gtk_libs -lX11"
+        fi
         libs_softmmu="$gtk_libs $libs_softmmu"
         gtk="yes"
     elif test "$gtk" = "yes"; then
@@ -2195,9 +2235,12 @@ if compile_prog "$quorum_tls_cflags" "$quorum_tls_libs" ; then
   libs_softmmu="$quorum_tls_libs $libs_softmmu"
   libs_tools="$quorum_tls_libs $libs_softmmu"
   QEMU_CFLAGS="$QEMU_CFLAGS $quorum_tls_cflags"
+  quorum="yes"
 else
-  echo "gnutls > 2.10.0 required to compile Quorum"
-  exit 1
+  if test "$quorum" = "yes"; then
+    feature_not_found "gnutls" "gnutls > 2.10.0 required to compile Quorum"
+  fi
+  quorum="no"
 fi
 fi
 
@@ -3134,6 +3177,26 @@ if compile_prog "" "" ; then
   splice=yes
 fi
 
+##########################################
+# libnuma probe
+
+if test "$numa" != "no" ; then
+  cat > $TMPC << EOF
+#include <numa.h>
+int main(void) { return numa_available(); }
+EOF
+
+  if compile_prog "" "-lnuma" ; then
+    numa=yes
+    libs_softmmu="-lnuma $libs_softmmu"
+  else
+    if test "$numa" = "yes" ; then
+      feature_not_found "numa" "install numactl devel"
+    fi
+    numa=no
+  fi
+fi
+
 ##########################################
 # signalfd probe
 signalfd="no"
@@ -3372,46 +3435,20 @@ if compile_prog "" "" ; then
 fi
 
 ##########################################
-# Do we have libiscsi
-# We check for iscsi_write16_sync() to make sure we have a
-# at least version 1.4.0 of libiscsi.
+# Do we have libiscsi >= 1.9.0
 if test "$libiscsi" != "no" ; then
-  cat > $TMPC << EOF
-#include <stdio.h>
-#include <iscsi/iscsi.h>
-int main(void) { iscsi_write16_sync(NULL,0,0,NULL,0,0,0,0,0,0,0); return 0; }
-EOF
-  if $pkg_config --atleast-version=1.7.0 libiscsi; then
+  if $pkg_config --atleast-version=1.9.0 libiscsi; then
     libiscsi="yes"
     libiscsi_cflags=$($pkg_config --cflags libiscsi)
     libiscsi_libs=$($pkg_config --libs libiscsi)
-  elif compile_prog "" "-liscsi" ; then
-    libiscsi="yes"
-    libiscsi_libs="-liscsi"
   else
     if test "$libiscsi" = "yes" ; then
-      feature_not_found "libiscsi" "Install libiscsi devel"
+      feature_not_found "libiscsi" "Install libiscsi >= 1.9.0"
     fi
     libiscsi="no"
   fi
 fi
 
-# We also need to know the API version because there was an
-# API change from 1.4.0 to 1.5.0.
-if test "$libiscsi" = "yes"; then
-  cat >$TMPC <<EOF
-#include <iscsi/iscsi.h>
-int main(void)
-{
-  iscsi_read10_task(0, 0, 0, 0, 0, 0, 0);
-  return 0;
-}
-EOF
-  if compile_prog "" "-liscsi"; then
-    libiscsi_version="1.4.0"
-  fi
-fi
-
 ##########################################
 # Do we need libm
 cat > $TMPC << EOF
@@ -3445,9 +3482,9 @@ EOF
 if compile_prog "" "" ; then
   :
 # we need pthread for static linking. use previous pthread test result
-elif compile_prog "" "-lrt $pthread_lib" ; then
-  LIBS="-lrt $LIBS"
-  libs_qga="-lrt $libs_qga"
+elif compile_prog "" "$pthread_lib -lrt" ; then
+  LIBS="$LIBS -lrt"
+  libs_qga="$libs_qga -lrt"
 fi
 
 if test "$darwin" != "yes" -a "$mingw32" != "yes" -a "$solaris" != yes -a \
@@ -3666,15 +3703,15 @@ fi
 ##########################################
 # check if trace backend exists
 
-$python "$source_path/scripts/tracetool.py" "--backend=$trace_backend" --check-backend  > /dev/null 2> /dev/null
+$python "$source_path/scripts/tracetool.py" "--backends=$trace_backends" --check-backends  > /dev/null 2> /dev/null
 if test "$?" -ne 0 ; then
-  error_exit "invalid trace backend" \
-      "Please choose a supported trace backend."
+  error_exit "invalid trace backends" \
+      "Please choose supported trace backends."
 fi
 
 ##########################################
 # For 'ust' backend, test if ust headers are present
-if test "$trace_backend" = "ust"; then
+if have_backend "ust"; then
   cat > $TMPC << EOF
 #include <lttng/tracepoint.h>
 int main(void) { return 0; }
@@ -3700,7 +3737,7 @@ fi
 
 ##########################################
 # For 'dtrace' backend, test if 'dtrace' command is present
-if test "$trace_backend" = "dtrace"; then
+if have_backend "dtrace"; then
   if ! has 'dtrace' ; then
     error_exit "dtrace command is not found in PATH $PATH"
   fi
@@ -4170,7 +4207,7 @@ echo "uuid support      $uuid"
 echo "libcap-ng support $cap_ng"
 echo "vhost-net support $vhost_net"
 echo "vhost-scsi support $vhost_scsi"
-echo "Trace backend     $trace_backend"
+echo "Trace backends    $trace_backends"
 if test "$trace_backend" = "simple"; then
 echo "Trace output file $trace_file-<pid>"
 fi
@@ -4185,11 +4222,7 @@ echo "nss used          $smartcard_nss"
 echo "libusb            $libusb"
 echo "usb net redir     $usb_redir"
 echo "GLX support       $glx"
-if test "$libiscsi_version" = "1.4.0"; then
-echo "libiscsi support  $libiscsi (1.4.0)"
-else
 echo "libiscsi support  $libiscsi"
-fi
 echo "libnfs support    $libnfs"
 echo "build guest agent $guest_agent"
 echo "QGA VSS support   $guest_agent_with_vss"
@@ -4208,6 +4241,7 @@ echo "vhdx              $vhdx"
 echo "Quorum            $quorum"
 echo "lzo support       $lzo"
 echo "snappy support    $snappy"
+echo "NUMA host support $numa"
 
 if test "$sdl_too_old" = "yes"; then
 echo "-> Your SDL version is too old - please upgrade to have SDL support"
@@ -4482,6 +4516,9 @@ fi
 if test "$vhost_scsi" = "yes" ; then
   echo "CONFIG_VHOST_SCSI=y" >> $config_host_mak
 fi
+if test "$vhost_net" = "yes" ; then
+  echo "CONFIG_VHOST_NET_USED=y" >> $config_host_mak
+fi
 if test "$blobs" = "yes" ; then
   echo "INSTALL_BLOBS=yes" >> $config_host_mak
 fi
@@ -4546,9 +4583,6 @@ fi
 
 if test "$libiscsi" = "yes" ; then
   echo "CONFIG_LIBISCSI=m" >> $config_host_mak
-  if test "$libiscsi_version" = "1.4.0"; then
-    echo "CONFIG_LIBISCSI_1_4=y" >> $config_host_mak
-  fi
   echo "LIBISCSI_CFLAGS=$libiscsi_cflags" >> $config_host_mak
   echo "LIBISCSI_LIBS=$libiscsi_libs" >> $config_host_mak
 fi
@@ -4664,43 +4698,35 @@ if test "$tpm" = "yes"; then
   fi
 fi
 
-# use default implementation for tracing backend-specific routines
-trace_default=yes
-echo "TRACE_BACKEND=$trace_backend" >> $config_host_mak
-if test "$trace_backend" = "nop"; then
+echo "TRACE_BACKENDS=$trace_backends" >> $config_host_mak
+if have_backend "nop"; then
   echo "CONFIG_TRACE_NOP=y" >> $config_host_mak
 fi
-if test "$trace_backend" = "simple"; then
+if have_backend "simple"; then
   echo "CONFIG_TRACE_SIMPLE=y" >> $config_host_mak
-  trace_default=no
   # Set the appropriate trace file.
   trace_file="\"$trace_file-\" FMT_pid"
 fi
-if test "$trace_backend" = "stderr"; then
+if have_backend "stderr"; then
   echo "CONFIG_TRACE_STDERR=y" >> $config_host_mak
-  trace_default=no
 fi
-if test "$trace_backend" = "ust"; then
+if have_backend "ust"; then
   echo "CONFIG_TRACE_UST=y" >> $config_host_mak
 fi
-if test "$trace_backend" = "dtrace"; then
+if have_backend "dtrace"; then
   echo "CONFIG_TRACE_DTRACE=y" >> $config_host_mak
   if test "$trace_backend_stap" = "yes" ; then
     echo "CONFIG_TRACE_SYSTEMTAP=y" >> $config_host_mak
   fi
 fi
-if test "$trace_backend" = "ftrace"; then
+if have_backend "ftrace"; then
   if test "$linux" = "yes" ; then
     echo "CONFIG_TRACE_FTRACE=y" >> $config_host_mak
-    trace_default=no
   else
     feature_not_found "ftrace(trace backend)" "ftrace requires Linux"
   fi
 fi
 echo "CONFIG_TRACE_FILE=$trace_file" >> $config_host_mak
-if test "$trace_default" = "yes"; then
-  echo "CONFIG_TRACE_DEFAULT=y" >> $config_host_mak
-fi
 
 if test "$rdma" = "yes" ; then
   echo "CONFIG_RDMA=y" >> $config_host_mak
@@ -4724,6 +4750,8 @@ elif test "$ARCH" = "s390x" ; then
   QEMU_INCLUDES="-I\$(SRC_PATH)/tcg/s390 $QEMU_INCLUDES"
 elif test "$ARCH" = "x86_64" -o "$ARCH" = "x32" ; then
   QEMU_INCLUDES="-I\$(SRC_PATH)/tcg/i386 $QEMU_INCLUDES"
+elif test "$ARCH" = "ppc64" ; then
+  QEMU_INCLUDES="-I\$(SRC_PATH)/tcg/ppc $QEMU_INCLUDES"
 else
   QEMU_INCLUDES="-I\$(SRC_PATH)/tcg/\$(ARCH) $QEMU_INCLUDES"
 fi
@@ -4805,6 +4833,9 @@ if test "$linux" = "yes" ; then
   aarch64)
     linux_arch=arm64
     ;;
+  mips64)
+    linux_arch=mips
+    ;;
   *)
     # For most CPUs the kernel architecture name and QEMU CPU name match.
     linux_arch="$cpu"
@@ -4930,6 +4961,12 @@ case "$target_name" in
     TARGET_ABI_DIR=ppc
     gdb_xml_files="power64-core.xml power-fpu.xml power-altivec.xml power-spe.xml"
   ;;
+  ppc64le)
+    TARGET_ARCH=ppc64
+    TARGET_BASE_ARCH=ppc
+    TARGET_ABI_DIR=ppc
+    gdb_xml_files="power64-core.xml power-fpu.xml power-altivec.xml power-spe.xml"
+  ;;
   ppc64abi32)
     TARGET_ARCH=ppc64
     TARGET_BASE_ARCH=ppc
@@ -4982,6 +5019,9 @@ if [ "$TARGET_ABI_DIR" = "" ]; then
   TARGET_ABI_DIR=$TARGET_ARCH
 fi
 echo "TARGET_ABI_DIR=$TARGET_ABI_DIR" >> $config_target_mak
+if [ "$HOST_VARIANT_DIR" != "" ]; then
+    echo "HOST_VARIANT_DIR=$HOST_VARIANT_DIR" >> $config_target_mak
+fi
 case "$target_name" in
   i386|x86_64)
     if test "$xen" = "yes" -a "$target_softmmu" = "yes" ; then
@@ -4994,7 +5034,7 @@ case "$target_name" in
   *)
 esac
 case "$target_name" in
-  aarch64|arm|i386|x86_64|ppcemb|ppc|ppc64|s390x)
+  aarch64|arm|i386|x86_64|ppcemb|ppc|ppc64|s390x|mipsel|mips)
     # Make sure the target and host cpus are compatible
     if test "$kvm" = "yes" -a "$target_softmmu" = "yes" -a \
       \( "$target_name" = "$cpu" -o \
@@ -5002,6 +5042,7 @@ case "$target_name" in
       \( "$target_name" = "ppc64"  -a "$cpu" = "ppc" \) -o \
       \( "$target_name" = "ppc"    -a "$cpu" = "ppc64" \) -o \
       \( "$target_name" = "ppcemb" -a "$cpu" = "ppc64" \) -o \
+      \( "$target_name" = "mipsel" -a "$cpu" = "mips" \) -o \
       \( "$target_name" = "x86_64" -a "$cpu" = "i386"   \) -o \
       \( "$target_name" = "i386"   -a "$cpu" = "x86_64" \) \) ; then
       echo "CONFIG_KVM=y" >> $config_target_mak
@@ -5173,6 +5214,10 @@ if [ "$dtc_internal" = "yes" ]; then
   echo "config-host.h: subdir-dtc" >> $config_host_mak
 fi
 
+if test "$numa" = "yes"; then
+  echo "CONFIG_NUMA=y" >> $config_host_mak
+fi
+
 # build tree in object directory in case the source is not in the current directory
 DIRS="tests tests/tcg tests/tcg/cris tests/tcg/lm32 tests/libqos tests/qapi-schema tests/tcg/xtensa tests/qemu-iotests"
 DIRS="$DIRS fsdev"
@@ -5194,6 +5239,7 @@ for bios_file in \
     $source_path/pc-bios/*.dtb \
     $source_path/pc-bios/*.img \
     $source_path/pc-bios/openbios-* \
+    $source_path/pc-bios/u-boot.* \
     $source_path/pc-bios/palcode-*
 do
     FILES="$FILES pc-bios/`basename $bios_file`"

coroutine-gthread.c

@@ -30,20 +30,14 @@ typedef struct {
     CoroutineAction action;
 } CoroutineGThread;
 
-static GStaticMutex coroutine_lock = G_STATIC_MUTEX_INIT;
+static CompatGMutex coroutine_lock;
+static CompatGCond coroutine_cond;
 
 /* GLib 2.31 and beyond deprecated various parts of the thread API,
  * but the new interfaces are not available in older GLib versions
  * so we have to cope with both.
  */
 #if GLIB_CHECK_VERSION(2, 31, 0)
-/* Default zero-initialisation is sufficient for 2.31+ GCond */
-static GCond the_coroutine_cond;
-static GCond *coroutine_cond = &the_coroutine_cond;
-static inline void init_coroutine_cond(void)
-{
-}
-
 /* Awkwardly, the GPrivate API doesn't provide a way to update the
  * GDestroyNotify handler for the coroutine key dynamically. So instead
  * we track whether or not the CoroutineGThread should be freed on
@@ -84,11 +78,6 @@ static inline GThread *create_thread(GThreadFunc func, gpointer data)
 #else
 
 /* Handle older GLib versions */
-static GCond *coroutine_cond;
-static inline void init_coroutine_cond(void)
-{
-    coroutine_cond = g_cond_new();
-}
 
 static GStaticPrivate coroutine_key = G_STATIC_PRIVATE_INIT;
 
@@ -120,22 +109,20 @@ static void __attribute__((constructor)) coroutine_init(void)
         g_thread_init(NULL);
     }
 #endif
-
-    init_coroutine_cond();
 }
 
 static void coroutine_wait_runnable_locked(CoroutineGThread *co)
 {
     while (!co->runnable) {
-        g_cond_wait(coroutine_cond, g_static_mutex_get_mutex(&coroutine_lock));
+        g_cond_wait(&coroutine_cond, &coroutine_lock);
     }
 }
 
 static void coroutine_wait_runnable(CoroutineGThread *co)
 {
-    g_static_mutex_lock(&coroutine_lock);
+    g_mutex_lock(&coroutine_lock);
     coroutine_wait_runnable_locked(co);
-    g_static_mutex_unlock(&coroutine_lock);
+    g_mutex_unlock(&coroutine_lock);
 }
 
 static gpointer coroutine_thread(gpointer opaque)
@@ -177,17 +164,17 @@ CoroutineAction qemu_coroutine_switch(Coroutine *from_,
     CoroutineGThread *from = DO_UPCAST(CoroutineGThread, base, from_);
     CoroutineGThread *to = DO_UPCAST(CoroutineGThread, base, to_);
 
-    g_static_mutex_lock(&coroutine_lock);
+    g_mutex_lock(&coroutine_lock);
     from->runnable = false;
     from->action = action;
     to->runnable = true;
     to->action = action;
-    g_cond_broadcast(coroutine_cond);
+    g_cond_broadcast(&coroutine_cond);
 
     if (action != COROUTINE_TERMINATE) {
         coroutine_wait_runnable_locked(from);
     }
-    g_static_mutex_unlock(&coroutine_lock);
+    g_mutex_unlock(&coroutine_lock);
     return from->action;
 }
 

cpus.c

@@ -26,6 +26,7 @@
 #include "config-host.h"
 
 #include "monitor/monitor.h"
+#include "qapi/qmp/qerror.h"
 #include "sysemu/sysemu.h"
 #include "exec/gdbstub.h"
 #include "sysemu/dma.h"
@@ -38,6 +39,7 @@
 #include "qemu/main-loop.h"
 #include "qemu/bitmap.h"
 #include "qemu/seqlock.h"
+#include "qapi-event.h"
 
 #ifndef _WIN32
 #include "qemu/compatfd.h"
@@ -347,7 +349,7 @@ void qtest_clock_warp(int64_t dest)
     assert(qtest_enabled());
     while (clock < dest) {
         int64_t deadline = qemu_clock_deadline_ns_all(QEMU_CLOCK_VIRTUAL);
-        int64_t warp = MIN(dest - clock, deadline);
+        int64_t warp = qemu_soonest_timeout(dest - clock, deadline);
         seqlock_write_lock(&timers_state.vm_clock_seqlock);
         qemu_icount_bias += warp;
         seqlock_write_unlock(&timers_state.vm_clock_seqlock);
@@ -530,7 +532,7 @@ static int do_vm_stop(RunState state)
         pause_all_vcpus();
         runstate_set(state);
         vm_state_notify(0, state);
-        monitor_protocol_event(QEVENT_STOP, NULL);
+        qapi_event_send_stop(&error_abort);
     }
 
     bdrv_drain_all();
@@ -1206,6 +1208,7 @@ void cpu_stop_current(void)
 int vm_stop(RunState state)
 {
     if (qemu_in_vcpu_thread()) {
+        qemu_system_vmstop_request_prepare();
         qemu_system_vmstop_request(state);
         /*
          * FIXME: should not return to device code in case
@@ -1312,20 +1315,6 @@ static void tcg_exec_all(void)
     exit_request = 0;
 }
 
-void set_numa_modes(void)
-{
-    CPUState *cpu;
-    int i;
-
-    CPU_FOREACH(cpu) {
-        for (i = 0; i < nb_numa_nodes; i++) {
-            if (test_bit(cpu->cpu_index, node_cpumask[i])) {
-                cpu->numa_node = i;
-            }
-        }
-    }
-}
-
 void list_cpus(FILE *f, fprintf_function cpu_fprintf, const char *optarg)
 {
     /* XXX: implement xxx_cpu_list for targets that still miss it */

cputlb.c

@@ -22,11 +22,13 @@
 #include "exec/exec-all.h"
 #include "exec/memory.h"
 #include "exec/address-spaces.h"
+#include "exec/cpu_ldst.h"
 
 #include "exec/cputlb.h"
 
 #include "exec/memory-internal.h"
 #include "exec/ram_addr.h"
+#include "tcg/tcg.h"
 
 //#define DEBUG_TLB
 //#define DEBUG_TLB_CHECK
@@ -330,21 +332,36 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
     return qemu_ram_addr_from_host_nofail(p);
 }
 
+#define MMUSUFFIX _mmu
+
+#define SHIFT 0
+#include "softmmu_template.h"
+
+#define SHIFT 1
+#include "softmmu_template.h"
+
+#define SHIFT 2
+#include "softmmu_template.h"
+
+#define SHIFT 3
+#include "softmmu_template.h"
+#undef MMUSUFFIX
+
 #define MMUSUFFIX _cmmu
-#undef GETPC
-#define GETPC() ((uintptr_t)0)
+#undef GETPC_ADJ
+#define GETPC_ADJ 0
+#undef GETRA
+#define GETRA() ((uintptr_t)0)
 #define SOFTMMU_CODE_ACCESS
 
 #define SHIFT 0
-#include "exec/softmmu_template.h"
+#include "softmmu_template.h"
 
 #define SHIFT 1
-#include "exec/softmmu_template.h"
+#include "softmmu_template.h"
 
 #define SHIFT 2
-#include "exec/softmmu_template.h"
+#include "softmmu_template.h"
 
 #define SHIFT 3
-#include "exec/softmmu_template.h"
-
-#undef env
+#include "softmmu_template.h"

default-configs/i386-softmmu.mak

@@ -44,3 +44,4 @@ CONFIG_APIC=y
 CONFIG_IOAPIC=y
 CONFIG_ICC_BUS=y
 CONFIG_PVPANIC=y
+CONFIG_MEM_HOTPLUG=y

default-configs/ppc-linux-user.mak

@@ -1 +1,2 @@
 # Default configuration for ppc-linux-user
+CONFIG_LIBDECNUMBER=y

default-configs/ppc-softmmu.mak

@@ -49,3 +49,4 @@ CONFIG_OPENPIC_KVM=$(and $(CONFIG_E500),$(CONFIG_KVM))
 CONFIG_MC146818RTC=y
 CONFIG_ETSEC=y
 CONFIG_ISA_TESTDEV=y
+CONFIG_LIBDECNUMBER=y

default-configs/ppc64-linux-user.mak

@@ -1 +1,2 @@
 # Default configuration for ppc64-linux-user
+CONFIG_LIBDECNUMBER=y

default-configs/ppc64-softmmu.mak

@@ -58,3 +58,4 @@ CONFIG_I82374=y
 CONFIG_I8257=y
 CONFIG_MC146818RTC=y
 CONFIG_ISA_TESTDEV=y
+CONFIG_LIBDECNUMBER=y

default-configs/ppc64abi32-linux-user.mak

@@ -1 +1,2 @@
 # Default configuration for ppc64abi32-linux-user
+CONFIG_LIBDECNUMBER=y

default-configs/ppc64le-linux-user.mak

@@ -0,0 +1,2 @@
+# Default configuration for ppc64le-linux-user
+CONFIG_LIBDECNUMBER=y

default-configs/ppcemb-softmmu.mak

@@ -16,3 +16,4 @@ CONFIG_I8259=y
 CONFIG_XILINX=y
 CONFIG_XILINX_ETHLITE=y
 CONFIG_OPENPIC=y
+CONFIG_LIBDECNUMBER=y

default-configs/x86_64-softmmu.mak

@@ -44,3 +44,4 @@ CONFIG_APIC=y
 CONFIG_IOAPIC=y
 CONFIG_ICC_BUS=y
 CONFIG_PVPANIC=y
+CONFIG_MEM_HOTPLUG=y

device-hotplug.c

@@ -40,7 +40,7 @@ DriveInfo *add_init_drive(const char *optstr)
         return NULL;
 
     mc = MACHINE_GET_CLASS(current_machine);
-    dinfo = drive_init(opts, mc->block_default_type);
+    dinfo = drive_new(opts, mc->block_default_type);
     if (!dinfo) {
         qemu_opts_del(opts);
         return NULL;
@@ -76,6 +76,6 @@ void drive_hot_add(Monitor *mon, const QDict *qdict)
 
 err:
     if (dinfo) {
-        drive_put_ref(dinfo);
+        drive_del(dinfo);
     }
 }

disas.c

@@ -191,7 +191,8 @@ static int print_insn_od_target(bfd_vma pc, disassemble_info *info)
    values:
     i386 - 1 means 16 bit code, 2 means 64 bit code
     arm  - bit 0 = thumb, bit 1 = reverse endian, bit 2 = A64
-    ppc  - nonzero means little endian
+    ppc  - bits 0:15 specify (optionally) the machine instruction set;
+           bit 16 indicates little endian.
     other targets - unused
  */
 void target_disas(FILE *out, CPUArchState *env, target_ulong code,
@@ -251,11 +252,11 @@ void target_disas(FILE *out, CPUArchState *env, target_ulong code,
     s.info.mach = bfd_mach_sparc_v9b;
 #endif
 #elif defined(TARGET_PPC)
-    if (flags >> 16) {
+    if ((flags >> 16) & 1) {
         s.info.endian = BFD_ENDIAN_LITTLE;
     }
     if (flags & 0xFFFF) {
-        /* If we have a precise definitions of the instructions set, use it */
+        /* If we have a precise definition of the instruction set, use it. */
         s.info.mach = flags & 0xFFFF;
     } else {
 #ifdef TARGET_PPC64
@@ -444,6 +445,8 @@ monitor_fprintf(FILE *stream, const char *fmt, ...)
     return 0;
 }
 
+/* Disassembler for the monitor.
+   See target_disas for a description of flags. */
 void monitor_disas(Monitor *mon, CPUArchState *env,
                    target_ulong pc, int nb_insn, int is_physical, int flags)
 {
@@ -484,11 +487,19 @@ void monitor_disas(Monitor *mon, CPUArchState *env,
     s.info.mach = bfd_mach_sparc_v9b;
 #endif
 #elif defined(TARGET_PPC)
+    if (flags & 0xFFFF) {
+        /* If we have a precise definition of the instruction set, use it. */
+        s.info.mach = flags & 0xFFFF;
+    } else {
 #ifdef TARGET_PPC64
-    s.info.mach = bfd_mach_ppc64;
+        s.info.mach = bfd_mach_ppc64;
 #else
-    s.info.mach = bfd_mach_ppc;
+        s.info.mach = bfd_mach_ppc;
 #endif
+    }
+    if ((flags >> 16) & 1) {
+        s.info.endian = BFD_ENDIAN_LITTLE;
+    }
     print_insn = print_insn_ppc;
 #elif defined(TARGET_M68K)
     print_insn = print_insn_m68k;

docs/ccid.txt

@@ -47,6 +47,7 @@ In ubuntu/debian:
 Configuring and building:
     ./configure --enable-smartcard && make
 
+
 3. Using ccid-card-emulated with hardware
 
 Assuming you have a working smartcard on the host with the current
@@ -54,19 +55,55 @@ user, using NSS, qemu acts as another NSS client using ccid-card-emulated:
 
     qemu -usb -device usb-ccid -device ccid-card-emulated
 
-4. Using ccid-card-emulated with certificates
 
-You must create the certificates. This is a one time process. We use NSS
-certificates:
+4. Using ccid-card-emulated with certificates stored in files
 
-    certutil -d /etc/pki/nssdb -x -t "CT,CT,CT" -S -s "CN=cert1" -n cert1
+You must create the CA and card certificates. This is a one time process.
+We use NSS certificates:
+
+    mkdir fake-smartcard
+    cd fake-smartcard
+    certutil -N -d sql:$PWD
+    certutil -S -d sql:$PWD -s "CN=Fake Smart Card CA" -x -t TC,TC,TC -n fake-smartcard-ca
+    certutil -S -d sql:$PWD -t ,, -s "CN=John Doe" -n id-cert -c fake-smartcard-ca
+    certutil -S -d sql:$PWD -t ,, -s "CN=John Doe (signing)" --nsCertType smime -n signing-cert -c fake-smartcard-ca
+    certutil -S -d sql:$PWD -t ,, -s "CN=John Doe (encryption)" --nsCertType sslClient -n encryption-cert -c fake-smartcard-ca
 
 Note: you must have exactly three certificates.
 
-Assuming the current user can access the certificates (use certutil -L to
-verify), you can use the emulated card type with the certificates backend:
+You can use the emulated card type with the certificates backend:
+
+    qemu -usb -device usb-ccid -device ccid-card-emulated,backend=certificates,db=sql:$PWD,cert1=id-cert,cert2=signing-cert,cert3=encryption-cert
+
+To use the certificates in the guest, export the CA certificate:
+
+    certutil -L -r -d sql:$PWD -o fake-smartcard-ca.cer -n fake-smartcard-ca
+
+and import it in the guest:
+
+    certutil -A -d /etc/pki/nssdb -i fake-smartcard-ca.cer -t TC,TC,TC -n fake-smartcard-ca
+
+In a Linux guest you can then use the CoolKey PKCS #11 module to access
+the card:
+
+    certutil -d /etc/pki/nssdb -L -h all
+
+It will prompt you for the PIN (which is the password you assigned to the
+certificate database early on), and then show you all three certificates
+together with the manually imported CA cert:
+
+    Certificate Nickname                        Trust Attributes
+    fake-smartcard-ca                           CT,C,C
+    John Doe:CAC ID Certificate                 u,u,u
+    John Doe:CAC Email Signature Certificate    u,u,u
+    John Doe:CAC Email Encryption Certificate   u,u,u
+
+If this does not happen, CoolKey is not installed or not registered with
+NSS.  Registration can be done from Firefox or the command line:
+
+    modutil -dbdir /etc/pki/nssdb -add "CAC Module" -libfile /usr/lib64/pkcs11/libcoolkeypk11.so
+    modutil -dbdir /etc/pki/nssdb -list
 
-    qemu -usb -device usb-ccid -device ccid-card-emulated,backend=certificates,cert1=cert1,cert2=cert2,cert3=cert3
 
 5. Using ccid-card-passthru with client side hardware
 
@@ -74,15 +111,23 @@ on the host specify the ccid-card-passthru device with a suitable chardev:
 
     qemu -chardev socket,server,host=0.0.0.0,port=2001,id=ccid,nowait -usb -device usb-ccid -device ccid-card-passthru,chardev=ccid
 
-on the client run vscclient, built when you built the libcacard library:
-    libcacard/vscclient <qemu-host> 2001
+on the client run vscclient, built when you built QEMU:
+
+    vscclient <qemu-host> 2001
+
 
 6. Using ccid-card-passthru with client side certificates
 
-Run qemu as per #5, and run vscclient as follows:
-(Note: vscclient command line interface is in a state of change)
+This case is not particularly useful, but you can use it to debug
+your setup if #4 works but #5 does not.
+
+Follow instructions as per #4, except run QEMU and vscclient as follows:
+Run qemu as per #5, and run vscclient from the "fake-smartcard"
+directory as follows:
+
+    qemu -chardev socket,server,host=0.0.0.0,port=2001,id=ccid,nowait -usb -device usb-ccid -device ccid-card-passthru,chardev=ccid
+    vscclient -e "db=\"sql:$PWD\" use_hw=no soft=(,Test,CAC,,id-cert,signing-cert,encryption-cert)" <qemu-host> 2001
 
-    libcacard/vscclient -e "db=\"/etc/pki/nssdb\" use_hw=no soft=(,Test,CAC,,cert1,cert2,cert3)" <qemu-host> 2001
 
 7. Passthrough protocol scenario
 
@@ -126,10 +171,11 @@ kill/quit         |                          |                |               |
 
 8. libcacard
 
-ccid-card-passthru and vscclient use libcacard as the card emulator.
-libcacard implements a completely virtual CAC (DoD standard for smart cards)
-compliant card and uses NSS to actually retrive certificates and do any
-encryption using the backend (real reader + card or file backed certificates).
+Both ccid-card-emulated and vscclient use libcacard as the card emulator.
+libcacard implements a completely virtual CAC (DoD standard for smart
+cards) compliant card and uses NSS to retrieve certificates and do
+any encryption.  The backend can then be a real reader and card, or
+certificates stored in files.
 
-For documentation of cac_card see README in libcacard subdirectory.
+For documentation of the library see docs/libcacard.txt.
 

docs/qapi-code-gen.txt

@@ -215,6 +215,24 @@ An example command is:
    'data': { 'arg1': 'str', '*arg2': 'str' },
    'returns': 'str' }
 
+=== Events ===
+
+Events are defined with the keyword 'event'.  When 'data' is also specified,
+additional info will be carried on.  Finally there will be C API generated
+in qapi-event.h; when called by QEMU code, a message with timestamp will
+be emitted on the wire.  If timestamp is -1, it means failure to retrieve host
+time.
+
+An example event is:
+
+{ 'event': 'EVENT_C',
+  'data': { '*a': 'int', 'b': 'str' } }
+
+Resulting in this JSON object:
+
+{ "event": "EVENT_C",
+  "data": { "b": "test string" },
+  "timestamp": { "seconds": 1267020223, "microseconds": 435656 } }
 
 == Code generation ==
 

docs/qmp/qmp-events.txt

@@ -1,541 +0,0 @@
-                   QEMU Machine Protocol Events
-                   ============================
-
-BALLOON_CHANGE
---------------
-
-Emitted when the guest changes the actual BALLOON level. This
-value is equivalent to the 'actual' field return by the
-'query-balloon' command
-
-Data:
-
-- "actual": actual level of the guest memory balloon in bytes (json-number)
-
-Example:
-
-{ "event": "BALLOON_CHANGE",
-    "data": { "actual": 944766976 },
-    "timestamp": { "seconds": 1267020223, "microseconds": 435656 } }
-
-BLOCK_IMAGE_CORRUPTED
----------------------
-
-Emitted when a disk image is being marked corrupt.
-
-Data:
-
-- "device": Device name (json-string)
-- "msg":    Informative message (e.g., reason for the corruption) (json-string)
-- "offset": If the corruption resulted from an image access, this is the access
-            offset into the image (json-int)
-- "size":   If the corruption resulted from an image access, this is the access
-            size (json-int)
-
-Example:
-
-{ "event": "BLOCK_IMAGE_CORRUPTED",
-    "data": { "device": "ide0-hd0",
-        "msg": "Prevented active L1 table overwrite", "offset": 196608,
-        "size": 65536 },
-    "timestamp": { "seconds": 1378126126, "microseconds": 966463 } }
-
-BLOCK_IO_ERROR
---------------
-
-Emitted when a disk I/O error occurs.
-
-Data:
-
-- "device": device name (json-string)
-- "operation": I/O operation (json-string, "read" or "write")
-- "action": action that has been taken, it's one of the following (json-string):
-    "ignore": error has been ignored
-    "report": error has been reported to the device
-    "stop": error caused VM to be stopped
-
-Example:
-
-{ "event": "BLOCK_IO_ERROR",
-    "data": { "device": "ide0-hd1",
-              "operation": "write",
-              "action": "stop" },
-    "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
-Note: If action is "stop", a STOP event will eventually follow the
-BLOCK_IO_ERROR event.
-
-BLOCK_JOB_CANCELLED
--------------------
-
-Emitted when a block job has been cancelled.
-
-Data:
-
-- "type":     Job type (json-string; "stream" for image streaming
-                                     "commit" for block commit)
-- "device":   Device name (json-string)
-- "len":      Maximum progress value (json-int)
-- "offset":   Current progress value (json-int)
-              On success this is equal to len.
-              On failure this is less than len.
-- "speed":    Rate limit, bytes per second (json-int)
-
-Example:
-
-{ "event": "BLOCK_JOB_CANCELLED",
-     "data": { "type": "stream", "device": "virtio-disk0",
-               "len": 10737418240, "offset": 134217728,
-               "speed": 0 },
-     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }
-
-BLOCK_JOB_COMPLETED
--------------------
-
-Emitted when a block job has completed.
-
-Data:
-
-- "type":     Job type (json-string; "stream" for image streaming
-                                     "commit" for block commit)
-- "device":   Device name (json-string)
-- "len":      Maximum progress value (json-int)
-- "offset":   Current progress value (json-int)
-              On success this is equal to len.
-              On failure this is less than len.
-- "speed":    Rate limit, bytes per second (json-int)
-- "error":    Error message (json-string, optional)
-              Only present on failure.  This field contains a human-readable
-              error message.  There are no semantics other than that streaming
-              has failed and clients should not try to interpret the error
-              string.
-
-Example:
-
-{ "event": "BLOCK_JOB_COMPLETED",
-     "data": { "type": "stream", "device": "virtio-disk0",
-               "len": 10737418240, "offset": 10737418240,
-               "speed": 0 },
-     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }
-
-BLOCK_JOB_ERROR
----------------
-
-Emitted when a block job encounters an error.
-
-Data:
-
-- "device": device name (json-string)
-- "operation": I/O operation (json-string, "read" or "write")
-- "action": action that has been taken, it's one of the following (json-string):
-    "ignore": error has been ignored, the job may fail later
-    "report": error will be reported and the job canceled
-    "stop": error caused job to be paused
-
-Example:
-
-{ "event": "BLOCK_JOB_ERROR",
-    "data": { "device": "ide0-hd1",
-              "operation": "write",
-              "action": "stop" },
-    "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
-BLOCK_JOB_READY
----------------
-
-Emitted when a block job is ready to complete.
-
-Data:
-
-- "device": device name (json-string)
-
-Example:
-
-{ "event": "BLOCK_JOB_READY",
-    "data": { "device": "ide0-hd1" },
-    "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
-Note: The "ready to complete" status is always reset by a BLOCK_JOB_ERROR
-event.
-
-DEVICE_DELETED
---------------
-
-Emitted whenever the device removal completion is acknowledged
-by the guest.
-At this point, it's safe to reuse the specified device ID.
-Device removal can be initiated by the guest or by HMP/QMP commands.
-
-Data:
-
-- "device": device name (json-string, optional)
-- "path": device path (json-string)
-
-{ "event": "DEVICE_DELETED",
-  "data": { "device": "virtio-net-pci-0",
-            "path": "/machine/peripheral/virtio-net-pci-0" },
-  "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
-DEVICE_TRAY_MOVED
------------------
-
-It's emitted whenever the tray of a removable device is moved by the guest
-or by HMP/QMP commands.
-
-Data:
-
-- "device": device name (json-string)
-- "tray-open": true if the tray has been opened or false if it has been closed
-               (json-bool)
-
-{ "event": "DEVICE_TRAY_MOVED",
-  "data": { "device": "ide1-cd0",
-            "tray-open": true
-  },
-  "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
-
-GUEST_PANICKED
---------------
-
-Emitted when guest OS panic is detected.
-
-Data:
-
-- "action": Action that has been taken (json-string, currently always "pause").
-
-Example:
-
-{ "event": "GUEST_PANICKED",
-     "data": { "action": "pause" } }
-
-NIC_RX_FILTER_CHANGED
----------------------
-
-The event is emitted once until the query command is executed,
-the first event will always be emitted.
-
-Data:
-
-- "name": net client name (json-string)
-- "path": device path (json-string)
-
-{ "event": "NIC_RX_FILTER_CHANGED",
-  "data": { "name": "vnet0",
-            "path": "/machine/peripheral/vnet0/virtio-backend" },
-  "timestamp": { "seconds": 1368697518, "microseconds": 326866 } }
-}
-
-QUORUM_FAILURE
---------------
-
-Emitted by the Quorum block driver if it fails to establish a quorum.
-
-Data:
-
-- "reference":    device name if defined else node name.
-- "sector-num":   Number of the first sector of the failed read operation.
-- "sector-count": Failed read operation sector count.
-
-Example:
-
-{ "event": "QUORUM_FAILURE",
-     "data": { "reference": "usr1", "sector-num": 345435, "sector-count": 5 },
-     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
-
-QUORUM_REPORT_BAD
------------------
-
-Emitted to report a corruption of a Quorum file.
-
-Data:
-
-- "error":        Error message (json-string, optional)
-                  Only present on failure.  This field contains a human-readable
-                  error message.  There are no semantics other than that the
-                  block layer reported an error and clients should not try to
-                  interpret the error string.
-- "node-name":    The graph node name of the block driver state.
-- "sector-num":   Number of the first sector of the failed read operation.
-- "sector-count": Failed read operation sector count.
-
-Example:
-
-{ "event": "QUORUM_REPORT_BAD",
-     "data": { "node-name": "1.raw", "sector-num": 345435, "sector-count": 5 },
-     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
-
-RESET
------
-
-Emitted when the Virtual Machine is reseted.
-
-Data: None.
-
-Example:
-
-{ "event": "RESET",
-    "timestamp": { "seconds": 1267041653, "microseconds": 9518 } }
-
-RESUME
-------
-
-Emitted when the Virtual Machine resumes execution.
-
-Data: None.
-
-Example:
-
-{ "event": "RESUME",
-    "timestamp": { "seconds": 1271770767, "microseconds": 582542 } }
-
-RTC_CHANGE
-----------
-
-Emitted when the guest changes the RTC time.
-
-Data:
-
-- "offset": Offset between base RTC clock (as specified by -rtc base), and
-new RTC clock value (json-number)
-
-Example:
-
-{ "event": "RTC_CHANGE",
-    "data": { "offset": 78 },
-    "timestamp": { "seconds": 1267020223, "microseconds": 435656 } }
-
-SHUTDOWN
---------
-
-Emitted when the Virtual Machine is powered down.
-
-Data: None.
-
-Example:
-
-{ "event": "SHUTDOWN",
-    "timestamp": { "seconds": 1267040730, "microseconds": 682951 } }
-
-Note: If the command-line option "-no-shutdown" has been specified, a STOP
-event will eventually follow the SHUTDOWN event.
-
-SPICE_CONNECTED, SPICE_DISCONNECTED
------------------------------------
-
-Emitted when a SPICE client connects or disconnects.
-
-Data:
-
-- "server": Server information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-- "client": Client information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-
-Example:
-
-{ "timestamp": {"seconds": 1290688046, "microseconds": 388707},
-  "event": "SPICE_CONNECTED",
-  "data": {
-    "server": { "port": "5920", "family": "ipv4", "host": "127.0.0.1"},
-    "client": {"port": "52873", "family": "ipv4", "host": "127.0.0.1"}
-}}
-
-SPICE_INITIALIZED
------------------
-
-Emitted after initial handshake and authentication takes place (if any)
-and the SPICE channel is up'n'running
-
-Data:
-
-- "server": Server information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-  - "auth": authentication method (json-string, optional)
-- "client": Client information (json-object)
-  - "host": IP address (json-string)
-  - "port": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-  - "connection-id": spice connection id.  All channels with the same id
-                     belong to the same spice session (json-int)
-  - "channel-type": channel type.  "1" is the main control channel, filter for
-                    this one if you want track spice sessions only (json-int)
-  - "channel-id": channel id.  Usually "0", might be different needed when
-                  multiple channels of the same type exist, such as multiple
-                  display channels in a multihead setup (json-int)
-  - "tls": whevener the channel is encrypted (json-bool)
-
-Example:
-
-{ "timestamp": {"seconds": 1290688046, "microseconds": 417172},
-  "event": "SPICE_INITIALIZED",
-  "data": {"server": {"auth": "spice", "port": "5921",
-                      "family": "ipv4", "host": "127.0.0.1"},
-           "client": {"port": "49004", "family": "ipv4", "channel-type": 3,
-                      "connection-id": 1804289383, "host": "127.0.0.1",
-                      "channel-id": 0, "tls": true}
-}}
-
-STOP
-----
-
-Emitted when the Virtual Machine is stopped.
-
-Data: None.
-
-Example:
-
-{ "event": "STOP",
-    "timestamp": { "seconds": 1267041730, "microseconds": 281295 } }
-
-SUSPEND
--------
-
-Emitted when guest enters S3 state.
-
-Data: None.
-
-Example:
-
-{ "event": "SUSPEND",
-     "timestamp": { "seconds": 1344456160, "microseconds": 309119 } }
-
-SUSPEND_DISK
-------------
-
-Emitted when the guest makes a request to enter S4 state.
-
-Data: None.
-
-Example:
-
-{ "event": "SUSPEND_DISK",
-     "timestamp": { "seconds": 1344456160, "microseconds": 309119 } }
-
-Note: QEMU shuts down when entering S4 state.
-
-VNC_CONNECTED
--------------
-
-Emitted when a VNC client establishes a connection.
-
-Data:
-
-- "server": Server information (json-object)
-  - "host": IP address (json-string)
-  - "service": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-  - "auth": authentication method (json-string, optional)
-- "client": Client information (json-object)
-  - "host": IP address (json-string)
-  - "service": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-
-Example:
-
-{ "event": "VNC_CONNECTED",
-    "data": {
-        "server": { "auth": "sasl", "family": "ipv4",
-                    "service": "5901", "host": "0.0.0.0" },
-        "client": { "family": "ipv4", "service": "58425",
-                    "host": "127.0.0.1" } },
-    "timestamp": { "seconds": 1262976601, "microseconds": 975795 } }
-
-
-Note: This event is emitted before any authentication takes place, thus
-the authentication ID is not provided.
-
-VNC_DISCONNECTED
-----------------
-
-Emitted when the connection is closed.
-
-Data:
-
-- "server": Server information (json-object)
-  - "host": IP address (json-string)
-  - "service": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-  - "auth": authentication method (json-string, optional)
-- "client": Client information (json-object)
-  - "host": IP address (json-string)
-  - "service": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-  - "x509_dname": TLS dname (json-string, optional)
-  - "sasl_username": SASL username (json-string, optional)
-
-Example:
-
-{ "event": "VNC_DISCONNECTED",
-    "data": {
-        "server": { "auth": "sasl", "family": "ipv4",
-                    "service": "5901", "host": "0.0.0.0" },
-        "client": { "family": "ipv4", "service": "58425",
-                    "host": "127.0.0.1", "sasl_username": "luiz" } },
-    "timestamp": { "seconds": 1262976601, "microseconds": 975795 } }
-
-VNC_INITIALIZED
----------------
-
-Emitted after authentication takes place (if any) and the VNC session is
-made active.
-
-Data:
-
-- "server": Server information (json-object)
-  - "host": IP address (json-string)
-  - "service": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-  - "auth": authentication method (json-string, optional)
-- "client": Client information (json-object)
-  - "host": IP address (json-string)
-  - "service": port number (json-string)
-  - "family": address family (json-string, "ipv4" or "ipv6")
-  - "x509_dname": TLS dname (json-string, optional)
-  - "sasl_username": SASL username (json-string, optional)
-
-Example:
-
-{ "event": "VNC_INITIALIZED",
-    "data": {
-        "server": { "auth": "sasl", "family": "ipv4",
-                    "service": "5901", "host": "0.0.0.0"},
-        "client": { "family": "ipv4", "service": "46089",
-                    "host": "127.0.0.1", "sasl_username": "luiz" } },
-        "timestamp": { "seconds": 1263475302, "microseconds": 150772 } }
-
-WAKEUP
-------
-
-Emitted when the guest has woken up from S3 and is running.
-
-Data: None.
-
-Example:
-
-{ "event": "WAKEUP",
-     "timestamp": { "seconds": 1344522075, "microseconds": 745528 } }
-
-WATCHDOG
---------
-
-Emitted when the watchdog device's timer is expired.
-
-Data:
-
-- "action": Action that has been taken, it's one of the following (json-string):
-            "reset", "shutdown", "poweroff", "pause", "debug", or "none"
-
-Example:
-
-{ "event": "WATCHDOG",
-     "data": { "action": "reset" },
-     "timestamp": { "seconds": 1267061043, "microseconds": 959568 } }
-
-Note: If action is "reset", "shutdown", or "pause" the WATCHDOG event is
-followed respectively by the RESET, SHUTDOWN, or STOP events.

docs/specs/acpi_mem_hotplug.txt

@@ -0,0 +1,44 @@
+QEMU<->ACPI BIOS memory hotplug interface
+--------------------------------------
+
+ACPI BIOS GPE.3 handler is dedicated for notifying OS about memory hot-add
+events.
+
+Memory hot-plug interface (IO port 0xa00-0xa17, 1-4 byte access):
+---------------------------------------------------------------
+0xa00:
+  read access:
+      [0x0-0x3] Lo part of memory device phys address
+      [0x4-0x7] Hi part of memory device phys address
+      [0x8-0xb] Lo part of memory device size in bytes
+      [0xc-0xf] Hi part of memory device size in bytes
+      [0x10-0x13] Memory device proximity domain
+      [0x14] Memory device status fields
+          bits:
+              0: Device is enabled and may be used by guest
+              1: Device insert event, used to distinguish device for which
+                 no device check event to OSPM was issued.
+                 It's valid only when bit 1 is set.
+              2-7: reserved and should be ignored by OSPM
+      [0x15-0x17] reserved
+
+  write access:
+      [0x0-0x3] Memory device slot selector, selects active memory device.
+                All following accesses to other registers in 0xa00-0xa17
+                region will read/store data from/to selected memory device.
+      [0x4-0x7] OST event code reported by OSPM
+      [0x8-0xb] OST status code reported by OSPM
+      [0xc-0x13] reserved, writes into it are ignored
+      [0x14] Memory device control fields
+          bits:
+              0: reserved, OSPM must clear it before writing to register
+              1: if set to 1 clears device insert event, set by OSPM
+                 after it has emitted device check event for the
+                 selected memory device
+              2-7: reserved, OSPM must clear them before writing to register
+
+Selecting memory device slot beyond present range has no effect on platform:
+   - write accesses to memory hot-plug registers not documented above are
+     ignored
+   - read accesses to memory hot-plug registers not documented above return
+     all bits set to 1.

docs/specs/vhost-user.txt

@@ -0,0 +1,266 @@
+Vhost-user Protocol
+===================
+
+Copyright (c) 2014 Virtual Open Systems Sarl.
+
+This work is licensed under the terms of the GNU GPL, version 2 or later.
+See the COPYING file in the top-level directory.
+===================
+
+This protocol is aiming to complement the ioctl interface used to control the
+vhost implementation in the Linux kernel. It implements the control plane needed
+to establish virtqueue sharing with a user space process on the same host. It
+uses communication over a Unix domain socket to share file descriptors in the
+ancillary data of the message.
+
+The protocol defines 2 sides of the communication, master and slave. Master is
+the application that shares its virtqueues, in our case QEMU. Slave is the
+consumer of the virtqueues.
+
+In the current implementation QEMU is the Master, and the Slave is intended to
+be a software Ethernet switch running in user space, such as Snabbswitch.
+
+Master and slave can be either a client (i.e. connecting) or server (listening)
+in the socket communication.
+
+Message Specification
+---------------------
+
+Note that all numbers are in the machine native byte order. A vhost-user message
+consists of 3 header fields and a payload:
+
+------------------------------------
+| request | flags | size | payload |
+------------------------------------
+
+ * Request: 32-bit type of the request
+ * Flags: 32-bit bit field:
+   - Lower 2 bits are the version (currently 0x01)
+   - Bit 2 is the reply flag - needs to be sent on each reply from the slave
+ * Size - 32-bit size of the payload
+
+
+Depending on the request type, payload can be:
+
+ * A single 64-bit integer
+   -------
+   | u64 |
+   -------
+
+   u64: a 64-bit unsigned integer
+
+ * A vring state description
+   ---------------
+  | index | num |
+  ---------------
+
+   Index: a 32-bit index
+   Num: a 32-bit number
+
+ * A vring address description
+   --------------------------------------------------------------
+   | index | flags | size | descriptor | used | available | log |
+   --------------------------------------------------------------
+
+   Index: a 32-bit vring index
+   Flags: a 32-bit vring flags
+   Descriptor: a 64-bit user address of the vring descriptor table
+   Used: a 64-bit user address of the vring used ring
+   Available: a 64-bit user address of the vring available ring
+   Log: a 64-bit guest address for logging
+
+ * Memory regions description
+   ---------------------------------------------------
+   | num regions | padding | region0 | ... | region7 |
+   ---------------------------------------------------
+
+   Num regions: a 32-bit number of regions
+   Padding: 32-bit
+
+   A region is:
+   ---------------------------------------
+   | guest address | size | user address |
+   ---------------------------------------
+
+   Guest address: a 64-bit guest address of the region
+   Size: a 64-bit size
+   User address: a 64-bit user address
+
+
+In QEMU the vhost-user message is implemented with the following struct:
+
+typedef struct VhostUserMsg {
+    VhostUserRequest request;
+    uint32_t flags;
+    uint32_t size;
+    union {
+        uint64_t u64;
+        struct vhost_vring_state state;
+        struct vhost_vring_addr addr;
+        VhostUserMemory memory;
+    };
+} QEMU_PACKED VhostUserMsg;
+
+Communication
+-------------
+
+The protocol for vhost-user is based on the existing implementation of vhost
+for the Linux Kernel. Most messages that can be sent via the Unix domain socket
+implementing vhost-user have an equivalent ioctl to the kernel implementation.
+
+The communication consists of master sending message requests and slave sending
+message replies. Most of the requests don't require replies. Here is a list of
+the ones that do:
+
+ * VHOST_GET_FEATURES
+ * VHOST_GET_VRING_BASE
+
+There are several messages that the master sends with file descriptors passed
+in the ancillary data:
+
+ * VHOST_SET_MEM_TABLE
+ * VHOST_SET_LOG_FD
+ * VHOST_SET_VRING_KICK
+ * VHOST_SET_VRING_CALL
+ * VHOST_SET_VRING_ERR
+
+If Master is unable to send the full message or receives a wrong reply it will
+close the connection. An optional reconnection mechanism can be implemented.
+
+Message types
+-------------
+
+ * VHOST_USER_GET_FEATURES
+
+      Id: 2
+      Equivalent ioctl: VHOST_GET_FEATURES
+      Master payload: N/A
+      Slave payload: u64
+
+      Get from the underlying vhost implementation the features bitmask.
+
+ * VHOST_USER_SET_FEATURES
+
+      Id: 3
+      Ioctl: VHOST_SET_FEATURES
+      Master payload: u64
+
+      Enable features in the underlying vhost implementation using a bitmask.
+
+ * VHOST_USER_SET_OWNER
+
+      Id: 4
+      Equivalent ioctl: VHOST_SET_OWNER
+      Master payload: N/A
+
+      Issued when a new connection is established. It sets the current Master
+      as an owner of the session. This can be used on the Slave as a
+      "session start" flag.
+
+ * VHOST_USER_RESET_OWNER
+
+      Id: 5
+      Equivalent ioctl: VHOST_RESET_OWNER
+      Master payload: N/A
+
+      Issued when a new connection is about to be closed. The Master will no
+      longer own this connection (and will usually close it).
+
+ * VHOST_USER_SET_MEM_TABLE
+
+      Id: 6
+      Equivalent ioctl: VHOST_SET_MEM_TABLE
+      Master payload: memory regions description
+
+      Sets the memory map regions on the slave so it can translate the vring
+      addresses. In the ancillary data there is an array of file descriptors
+      for each memory mapped region. The size and ordering of the fds matches
+      the number and ordering of memory regions.
+
+ * VHOST_USER_SET_LOG_BASE
+
+      Id: 7
+      Equivalent ioctl: VHOST_SET_LOG_BASE
+      Master payload: u64
+
+      Sets the logging base address.
+
+ * VHOST_USER_SET_LOG_FD
+
+      Id: 8
+      Equivalent ioctl: VHOST_SET_LOG_FD
+      Master payload: N/A
+
+      Sets the logging file descriptor, which is passed as ancillary data.
+
+ * VHOST_USER_SET_VRING_NUM
+
+      Id: 9
+      Equivalent ioctl: VHOST_SET_VRING_NUM
+      Master payload: vring state description
+
+      Sets the number of vrings for this owner.
+
+ * VHOST_USER_SET_VRING_ADDR
+
+      Id: 10
+      Equivalent ioctl: VHOST_SET_VRING_ADDR
+      Master payload: vring address description
+      Slave payload: N/A
+
+      Sets the addresses of the different aspects of the vring.
+
+ * VHOST_USER_SET_VRING_BASE
+
+      Id: 11
+      Equivalent ioctl: VHOST_SET_VRING_BASE
+      Master payload: vring state description
+
+      Sets the base offset in the available vring.
+
+ * VHOST_USER_GET_VRING_BASE
+
+      Id: 12
+      Equivalent ioctl: VHOST_USER_GET_VRING_BASE
+      Master payload: vring state description
+      Slave payload: vring state description
+
+      Get the available vring base offset.
+
+ * VHOST_USER_SET_VRING_KICK
+
+      Id: 13
+      Equivalent ioctl: VHOST_SET_VRING_KICK
+      Master payload: u64
+
+      Set the event file descriptor for adding buffers to the vring. It
+      is passed in the ancillary data.
+      Bits (0-7) of the payload contain the vring index. Bit 8 is the
+      invalid FD flag. This flag is set when there is no file descriptor
+      in the ancillary data. This signals that polling should be used
+      instead of waiting for a kick.
+
+ * VHOST_USER_SET_VRING_CALL
+
+      Id: 14
+      Equivalent ioctl: VHOST_SET_VRING_CALL
+      Master payload: u64
+
+      Set the event file descriptor to signal when buffers are used. It
+      is passed in the ancillary data.
+      Bits (0-7) of the payload contain the vring index. Bit 8 is the
+      invalid FD flag. This flag is set when there is no file descriptor
+      in the ancillary data. This signals that polling will be used
+      instead of waiting for the call.
+
+ * VHOST_USER_SET_VRING_ERR
+
+      Id: 15
+      Equivalent ioctl: VHOST_SET_VRING_ERR
+      Master payload: u64
+
+      Set the event file descriptor to signal when error occurs. It
+      is passed in the ancillary data.
+      Bits (0-7) of the payload contain the vring index. Bit 8 is the
+      invalid FD flag. This flag is set when there is no file descriptor
+      in the ancillary data.

docs/tracing.txt

@@ -9,7 +9,7 @@ for debugging, profiling, and observing execution.
 
 1. Build with the 'simple' trace backend:
 
-    ./configure --enable-trace-backend=simple
+    ./configure --enable-trace-backends=simple
     make
 
 2. Create a file with the events you want to trace:
@@ -142,7 +142,7 @@ script.
 The trace backend is chosen at configure time and only one trace backend can
 be built into the binary:
 
-    ./configure --trace-backend=simple
+    ./configure --trace-backends=simple
 
 For a list of supported trace backends, try ./configure --help or see below.
 

docs/virtio-balloon-stats.txt

@@ -35,7 +35,8 @@ which will return a dictionary containing:
 
   o A key named last-update, which contains the last stats update
     timestamp in seconds. Since this timestamp is generated by the host,
-    a buggy guest can't influence its value
+    a buggy guest can't influence its value. The value is 0 if the guest
+    has not updated the stats (yet).
 
 It's also important to note the following:
 
@@ -49,7 +50,7 @@ It's also important to note the following:
 
  - Polling can be enabled even if the guest doesn't have stats support
    or the balloon driver wasn't loaded in the guest. If this is the case
-   and stats are queried, an error will be returned
+   and stats are queried, last-update will be 0.
 
  - The polling timer is only re-armed when the guest responds to the
    statistics request. This means that if a (buggy) guest doesn't ever

dump.c

@@ -36,9 +36,9 @@
 #define ELF_MACHINE_UNAME "Unknown"
 #endif
 
-static uint16_t cpu_convert_to_target16(uint16_t val, int endian)
+uint16_t cpu_to_dump16(DumpState *s, uint16_t val)
 {
-    if (endian == ELFDATA2LSB) {
+    if (s->dump_info.d_endian == ELFDATA2LSB) {
         val = cpu_to_le16(val);
     } else {
         val = cpu_to_be16(val);
@@ -47,9 +47,9 @@ static uint16_t cpu_convert_to_target16(uint16_t val, int endian)
     return val;
 }
 
-static uint32_t cpu_convert_to_target32(uint32_t val, int endian)
+uint32_t cpu_to_dump32(DumpState *s, uint32_t val)
 {
-    if (endian == ELFDATA2LSB) {
+    if (s->dump_info.d_endian == ELFDATA2LSB) {
         val = cpu_to_le32(val);
     } else {
         val = cpu_to_be32(val);
@@ -58,9 +58,9 @@ static uint32_t cpu_convert_to_target32(uint32_t val, int endian)
     return val;
 }
 
-static uint64_t cpu_convert_to_target64(uint64_t val, int endian)
+uint64_t cpu_to_dump64(DumpState *s, uint64_t val)
 {
-    if (endian == ELFDATA2LSB) {
+    if (s->dump_info.d_endian == ELFDATA2LSB) {
         val = cpu_to_le64(val);
     } else {
         val = cpu_to_be64(val);
@@ -69,38 +69,6 @@ static uint64_t cpu_convert_to_target64(uint64_t val, int endian)
     return val;
 }
 
-typedef struct DumpState {
-    GuestPhysBlockList guest_phys_blocks;
-    ArchDumpInfo dump_info;
-    MemoryMappingList list;
-    uint16_t phdr_num;
-    uint32_t sh_info;
-    bool have_section;
-    bool resume;
-    ssize_t note_size;
-    hwaddr memory_offset;
-    int fd;
-
-    GuestPhysBlock *next_block;
-    ram_addr_t start;
-    bool has_filter;
-    int64_t begin;
-    int64_t length;
-
-    uint8_t *note_buf;          /* buffer for notes */
-    size_t note_buf_offset;     /* the writing place in note_buf */
-    uint32_t nr_cpus;           /* number of guest's cpu */
-    size_t page_size;           /* guest's page size */
-    uint32_t page_shift;        /* guest's page shift */
-    uint64_t max_mapnr;         /* the biggest guest's phys-mem's number */
-    size_t len_dump_bitmap;     /* the size of the place used to store
-                                   dump_bitmap in vmcore */
-    off_t offset_dump_bitmap;   /* offset of dump_bitmap part in vmcore */
-    off_t offset_page;          /* offset of page part in vmcore */
-    size_t num_dumpable;        /* number of page that can be dumped */
-    uint32_t flag_compress;     /* indicate the compression format */
-} DumpState;
-
 static int dump_cleanup(DumpState *s)
 {
     int ret = 0;
@@ -139,29 +107,25 @@ static int write_elf64_header(DumpState *s)
 {
     Elf64_Ehdr elf_header;
     int ret;
-    int endian = s->dump_info.d_endian;
 
     memset(&elf_header, 0, sizeof(Elf64_Ehdr));
     memcpy(&elf_header, ELFMAG, SELFMAG);
     elf_header.e_ident[EI_CLASS] = ELFCLASS64;
     elf_header.e_ident[EI_DATA] = s->dump_info.d_endian;
     elf_header.e_ident[EI_VERSION] = EV_CURRENT;
-    elf_header.e_type = cpu_convert_to_target16(ET_CORE, endian);
-    elf_header.e_machine = cpu_convert_to_target16(s->dump_info.d_machine,
-                                                   endian);
-    elf_header.e_version = cpu_convert_to_target32(EV_CURRENT, endian);
-    elf_header.e_ehsize = cpu_convert_to_target16(sizeof(elf_header), endian);
-    elf_header.e_phoff = cpu_convert_to_target64(sizeof(Elf64_Ehdr), endian);
-    elf_header.e_phentsize = cpu_convert_to_target16(sizeof(Elf64_Phdr),
-                                                     endian);
-    elf_header.e_phnum = cpu_convert_to_target16(s->phdr_num, endian);
+    elf_header.e_type = cpu_to_dump16(s, ET_CORE);
+    elf_header.e_machine = cpu_to_dump16(s, s->dump_info.d_machine);
+    elf_header.e_version = cpu_to_dump32(s, EV_CURRENT);
+    elf_header.e_ehsize = cpu_to_dump16(s, sizeof(elf_header));
+    elf_header.e_phoff = cpu_to_dump64(s, sizeof(Elf64_Ehdr));
+    elf_header.e_phentsize = cpu_to_dump16(s, sizeof(Elf64_Phdr));
+    elf_header.e_phnum = cpu_to_dump16(s, s->phdr_num);
     if (s->have_section) {
         uint64_t shoff = sizeof(Elf64_Ehdr) + sizeof(Elf64_Phdr) * s->sh_info;
 
-        elf_header.e_shoff = cpu_convert_to_target64(shoff, endian);
-        elf_header.e_shentsize = cpu_convert_to_target16(sizeof(Elf64_Shdr),
-                                                         endian);
-        elf_header.e_shnum = cpu_convert_to_target16(1, endian);
+        elf_header.e_shoff = cpu_to_dump64(s, shoff);
+        elf_header.e_shentsize = cpu_to_dump16(s, sizeof(Elf64_Shdr));
+        elf_header.e_shnum = cpu_to_dump16(s, 1);
     }
 
     ret = fd_write_vmcore(&elf_header, sizeof(elf_header), s);
@@ -177,29 +141,25 @@ static int write_elf32_header(DumpState *s)
 {
     Elf32_Ehdr elf_header;
     int ret;
-    int endian = s->dump_info.d_endian;
 
     memset(&elf_header, 0, sizeof(Elf32_Ehdr));
     memcpy(&elf_header, ELFMAG, SELFMAG);
     elf_header.e_ident[EI_CLASS] = ELFCLASS32;
-    elf_header.e_ident[EI_DATA] = endian;
+    elf_header.e_ident[EI_DATA] = s->dump_info.d_endian;
     elf_header.e_ident[EI_VERSION] = EV_CURRENT;
-    elf_header.e_type = cpu_convert_to_target16(ET_CORE, endian);
-    elf_header.e_machine = cpu_convert_to_target16(s->dump_info.d_machine,
-                                                   endian);
-    elf_header.e_version = cpu_convert_to_target32(EV_CURRENT, endian);
-    elf_header.e_ehsize = cpu_convert_to_target16(sizeof(elf_header), endian);
-    elf_header.e_phoff = cpu_convert_to_target32(sizeof(Elf32_Ehdr), endian);
-    elf_header.e_phentsize = cpu_convert_to_target16(sizeof(Elf32_Phdr),
-                                                     endian);
-    elf_header.e_phnum = cpu_convert_to_target16(s->phdr_num, endian);
+    elf_header.e_type = cpu_to_dump16(s, ET_CORE);
+    elf_header.e_machine = cpu_to_dump16(s, s->dump_info.d_machine);
+    elf_header.e_version = cpu_to_dump32(s, EV_CURRENT);
+    elf_header.e_ehsize = cpu_to_dump16(s, sizeof(elf_header));
+    elf_header.e_phoff = cpu_to_dump32(s, sizeof(Elf32_Ehdr));
+    elf_header.e_phentsize = cpu_to_dump16(s, sizeof(Elf32_Phdr));
+    elf_header.e_phnum = cpu_to_dump16(s, s->phdr_num);
     if (s->have_section) {
         uint32_t shoff = sizeof(Elf32_Ehdr) + sizeof(Elf32_Phdr) * s->sh_info;
 
-        elf_header.e_shoff = cpu_convert_to_target32(shoff, endian);
-        elf_header.e_shentsize = cpu_convert_to_target16(sizeof(Elf32_Shdr),
-                                                         endian);
-        elf_header.e_shnum = cpu_convert_to_target16(1, endian);
+        elf_header.e_shoff = cpu_to_dump32(s, shoff);
+        elf_header.e_shentsize = cpu_to_dump16(s, sizeof(Elf32_Shdr));
+        elf_header.e_shnum = cpu_to_dump16(s, 1);
     }
 
     ret = fd_write_vmcore(&elf_header, sizeof(elf_header), s);
@@ -217,15 +177,14 @@ static int write_elf64_load(DumpState *s, MemoryMapping *memory_mapping,
 {
     Elf64_Phdr phdr;
     int ret;
-    int endian = s->dump_info.d_endian;
 
     memset(&phdr, 0, sizeof(Elf64_Phdr));
-    phdr.p_type = cpu_convert_to_target32(PT_LOAD, endian);
-    phdr.p_offset = cpu_convert_to_target64(offset, endian);
-    phdr.p_paddr = cpu_convert_to_target64(memory_mapping->phys_addr, endian);
-    phdr.p_filesz = cpu_convert_to_target64(filesz, endian);
-    phdr.p_memsz = cpu_convert_to_target64(memory_mapping->length, endian);
-    phdr.p_vaddr = cpu_convert_to_target64(memory_mapping->virt_addr, endian);
+    phdr.p_type = cpu_to_dump32(s, PT_LOAD);
+    phdr.p_offset = cpu_to_dump64(s, offset);
+    phdr.p_paddr = cpu_to_dump64(s, memory_mapping->phys_addr);
+    phdr.p_filesz = cpu_to_dump64(s, filesz);
+    phdr.p_memsz = cpu_to_dump64(s, memory_mapping->length);
+    phdr.p_vaddr = cpu_to_dump64(s, memory_mapping->virt_addr);
 
     assert(memory_mapping->length >= filesz);
 
@@ -244,15 +203,14 @@ static int write_elf32_load(DumpState *s, MemoryMapping *memory_mapping,
 {
     Elf32_Phdr phdr;
     int ret;
-    int endian = s->dump_info.d_endian;
 
     memset(&phdr, 0, sizeof(Elf32_Phdr));
-    phdr.p_type = cpu_convert_to_target32(PT_LOAD, endian);
-    phdr.p_offset = cpu_convert_to_target32(offset, endian);
-    phdr.p_paddr = cpu_convert_to_target32(memory_mapping->phys_addr, endian);
-    phdr.p_filesz = cpu_convert_to_target32(filesz, endian);
-    phdr.p_memsz = cpu_convert_to_target32(memory_mapping->length, endian);
-    phdr.p_vaddr = cpu_convert_to_target32(memory_mapping->virt_addr, endian);
+    phdr.p_type = cpu_to_dump32(s, PT_LOAD);
+    phdr.p_offset = cpu_to_dump32(s, offset);
+    phdr.p_paddr = cpu_to_dump32(s, memory_mapping->phys_addr);
+    phdr.p_filesz = cpu_to_dump32(s, filesz);
+    phdr.p_memsz = cpu_to_dump32(s, memory_mapping->length);
+    phdr.p_vaddr = cpu_to_dump32(s, memory_mapping->virt_addr);
 
     assert(memory_mapping->length >= filesz);
 
@@ -268,16 +226,15 @@ static int write_elf32_load(DumpState *s, MemoryMapping *memory_mapping,
 static int write_elf64_note(DumpState *s)
 {
     Elf64_Phdr phdr;
-    int endian = s->dump_info.d_endian;
     hwaddr begin = s->memory_offset - s->note_size;
     int ret;
 
     memset(&phdr, 0, sizeof(Elf64_Phdr));
-    phdr.p_type = cpu_convert_to_target32(PT_NOTE, endian);
-    phdr.p_offset = cpu_convert_to_target64(begin, endian);
+    phdr.p_type = cpu_to_dump32(s, PT_NOTE);
+    phdr.p_offset = cpu_to_dump64(s, begin);
     phdr.p_paddr = 0;
-    phdr.p_filesz = cpu_convert_to_target64(s->note_size, endian);
-    phdr.p_memsz = cpu_convert_to_target64(s->note_size, endian);
+    phdr.p_filesz = cpu_to_dump64(s, s->note_size);
+    phdr.p_memsz = cpu_to_dump64(s, s->note_size);
     phdr.p_vaddr = 0;
 
     ret = fd_write_vmcore(&phdr, sizeof(Elf64_Phdr), s);
@@ -324,15 +281,14 @@ static int write_elf32_note(DumpState *s)
 {
     hwaddr begin = s->memory_offset - s->note_size;
     Elf32_Phdr phdr;
-    int endian = s->dump_info.d_endian;
     int ret;
 
     memset(&phdr, 0, sizeof(Elf32_Phdr));
-    phdr.p_type = cpu_convert_to_target32(PT_NOTE, endian);
-    phdr.p_offset = cpu_convert_to_target32(begin, endian);
+    phdr.p_type = cpu_to_dump32(s, PT_NOTE);
+    phdr.p_offset = cpu_to_dump32(s, begin);
     phdr.p_paddr = 0;
-    phdr.p_filesz = cpu_convert_to_target32(s->note_size, endian);
-    phdr.p_memsz = cpu_convert_to_target32(s->note_size, endian);
+    phdr.p_filesz = cpu_to_dump32(s, s->note_size);
+    phdr.p_memsz = cpu_to_dump32(s, s->note_size);
     phdr.p_vaddr = 0;
 
     ret = fd_write_vmcore(&phdr, sizeof(Elf32_Phdr), s);
@@ -374,7 +330,6 @@ static int write_elf_section(DumpState *s, int type)
 {
     Elf32_Shdr shdr32;
     Elf64_Shdr shdr64;
-    int endian = s->dump_info.d_endian;
     int shdr_size;
     void *shdr;
     int ret;
@@ -382,12 +337,12 @@ static int write_elf_section(DumpState *s, int type)
     if (type == 0) {
         shdr_size = sizeof(Elf32_Shdr);
         memset(&shdr32, 0, shdr_size);
-        shdr32.sh_info = cpu_convert_to_target32(s->sh_info, endian);
+        shdr32.sh_info = cpu_to_dump32(s, s->sh_info);
         shdr = &shdr32;
     } else {
         shdr_size = sizeof(Elf64_Shdr);
         memset(&shdr64, 0, shdr_size);
-        shdr64.sh_info = cpu_convert_to_target32(s->sh_info, endian);
+        shdr64.sh_info = cpu_to_dump32(s, s->sh_info);
         shdr = &shdr64;
     }
 
@@ -711,27 +666,25 @@ static int create_vmcore(DumpState *s)
 
 static int write_start_flat_header(int fd)
 {
-    uint8_t *buf;
-    MakedumpfileHeader mh;
+    MakedumpfileHeader *mh;
     int ret = 0;
 
-    memset(&mh, 0, sizeof(mh));
-    strncpy(mh.signature, MAKEDUMPFILE_SIGNATURE,
-            strlen(MAKEDUMPFILE_SIGNATURE));
+    QEMU_BUILD_BUG_ON(sizeof *mh > MAX_SIZE_MDF_HEADER);
+    mh = g_malloc0(MAX_SIZE_MDF_HEADER);
 
-    mh.type = cpu_to_be64(TYPE_FLAT_HEADER);
-    mh.version = cpu_to_be64(VERSION_FLAT_HEADER);
+    memcpy(mh->signature, MAKEDUMPFILE_SIGNATURE,
+           MIN(sizeof mh->signature, sizeof MAKEDUMPFILE_SIGNATURE));
 
-    buf = g_malloc0(MAX_SIZE_MDF_HEADER);
-    memcpy(buf, &mh, sizeof(mh));
+    mh->type = cpu_to_be64(TYPE_FLAT_HEADER);
+    mh->version = cpu_to_be64(VERSION_FLAT_HEADER);
 
     size_t written_size;
-    written_size = qemu_write_full(fd, buf, MAX_SIZE_MDF_HEADER);
+    written_size = qemu_write_full(fd, mh, MAX_SIZE_MDF_HEADER);
     if (written_size != MAX_SIZE_MDF_HEADER) {
         ret = -1;
     }
 
-    g_free(buf);
+    g_free(mh);
     return ret;
 }
 
@@ -795,7 +748,6 @@ static int create_header32(DumpState *s)
     DiskDumpHeader32 *dh = NULL;
     KdumpSubHeader32 *kh = NULL;
     size_t size;
-    int endian = s->dump_info.d_endian;
     uint32_t block_size;
     uint32_t sub_hdr_size;
     uint32_t bitmap_blocks;
@@ -807,18 +759,17 @@ static int create_header32(DumpState *s)
     dh = g_malloc0(size);
 
     strncpy(dh->signature, KDUMP_SIGNATURE, strlen(KDUMP_SIGNATURE));
-    dh->header_version = cpu_convert_to_target32(6, endian);
-    block_size = s->page_size;
-    dh->block_size = cpu_convert_to_target32(block_size, endian);
+    dh->header_version = cpu_to_dump32(s, 6);
+    block_size = TARGET_PAGE_SIZE;
+    dh->block_size = cpu_to_dump32(s, block_size);
     sub_hdr_size = sizeof(struct KdumpSubHeader32) + s->note_size;
     sub_hdr_size = DIV_ROUND_UP(sub_hdr_size, block_size);
-    dh->sub_hdr_size = cpu_convert_to_target32(sub_hdr_size, endian);
+    dh->sub_hdr_size = cpu_to_dump32(s, sub_hdr_size);
     /* dh->max_mapnr may be truncated, full 64bit is in kh.max_mapnr_64 */
-    dh->max_mapnr = cpu_convert_to_target32(MIN(s->max_mapnr, UINT_MAX),
-                                            endian);
-    dh->nr_cpus = cpu_convert_to_target32(s->nr_cpus, endian);
+    dh->max_mapnr = cpu_to_dump32(s, MIN(s->max_mapnr, UINT_MAX));
+    dh->nr_cpus = cpu_to_dump32(s, s->nr_cpus);
     bitmap_blocks = DIV_ROUND_UP(s->len_dump_bitmap, block_size) * 2;
-    dh->bitmap_blocks = cpu_convert_to_target32(bitmap_blocks, endian);
+    dh->bitmap_blocks = cpu_to_dump32(s, bitmap_blocks);
     strncpy(dh->utsname.machine, ELF_MACHINE_UNAME, sizeof(dh->utsname.machine));
 
     if (s->flag_compress & DUMP_DH_COMPRESSED_ZLIB) {
@@ -834,7 +785,7 @@ static int create_header32(DumpState *s)
         status |= DUMP_DH_COMPRESSED_SNAPPY;
     }
 #endif
-    dh->status = cpu_convert_to_target32(status, endian);
+    dh->status = cpu_to_dump32(s, status);
 
     if (write_buffer(s->fd, 0, dh, size) < 0) {
         dump_error(s, "dump: failed to write disk dump header.\n");
@@ -847,13 +798,13 @@ static int create_header32(DumpState *s)
     kh = g_malloc0(size);
 
     /* 64bit max_mapnr_64 */
-    kh->max_mapnr_64 = cpu_convert_to_target64(s->max_mapnr, endian);
-    kh->phys_base = cpu_convert_to_target32(PHYS_BASE, endian);
-    kh->dump_level = cpu_convert_to_target32(DUMP_LEVEL, endian);
+    kh->max_mapnr_64 = cpu_to_dump64(s, s->max_mapnr);
+    kh->phys_base = cpu_to_dump32(s, PHYS_BASE);
+    kh->dump_level = cpu_to_dump32(s, DUMP_LEVEL);
 
     offset_note = DISKDUMP_HEADER_BLOCKS * block_size + size;
-    kh->offset_note = cpu_convert_to_target64(offset_note, endian);
-    kh->note_size = cpu_convert_to_target32(s->note_size, endian);
+    kh->offset_note = cpu_to_dump64(s, offset_note);
+    kh->note_size = cpu_to_dump32(s, s->note_size);
 
     if (write_buffer(s->fd, DISKDUMP_HEADER_BLOCKS *
                      block_size, kh, size) < 0) {
@@ -902,7 +853,6 @@ static int create_header64(DumpState *s)
     DiskDumpHeader64 *dh = NULL;
     KdumpSubHeader64 *kh = NULL;
     size_t size;
-    int endian = s->dump_info.d_endian;
     uint32_t block_size;
     uint32_t sub_hdr_size;
     uint32_t bitmap_blocks;
@@ -914,18 +864,17 @@ static int create_header64(DumpState *s)
     dh = g_malloc0(size);
 
     strncpy(dh->signature, KDUMP_SIGNATURE, strlen(KDUMP_SIGNATURE));
-    dh->header_version = cpu_convert_to_target32(6, endian);
-    block_size = s->page_size;
-    dh->block_size = cpu_convert_to_target32(block_size, endian);
+    dh->header_version = cpu_to_dump32(s, 6);
+    block_size = TARGET_PAGE_SIZE;
+    dh->block_size = cpu_to_dump32(s, block_size);
     sub_hdr_size = sizeof(struct KdumpSubHeader64) + s->note_size;
     sub_hdr_size = DIV_ROUND_UP(sub_hdr_size, block_size);
-    dh->sub_hdr_size = cpu_convert_to_target32(sub_hdr_size, endian);
+    dh->sub_hdr_size = cpu_to_dump32(s, sub_hdr_size);
     /* dh->max_mapnr may be truncated, full 64bit is in kh.max_mapnr_64 */
-    dh->max_mapnr = cpu_convert_to_target32(MIN(s->max_mapnr, UINT_MAX),
-                                            endian);
-    dh->nr_cpus = cpu_convert_to_target32(s->nr_cpus, endian);
+    dh->max_mapnr = cpu_to_dump32(s, MIN(s->max_mapnr, UINT_MAX));
+    dh->nr_cpus = cpu_to_dump32(s, s->nr_cpus);
     bitmap_blocks = DIV_ROUND_UP(s->len_dump_bitmap, block_size) * 2;
-    dh->bitmap_blocks = cpu_convert_to_target32(bitmap_blocks, endian);
+    dh->bitmap_blocks = cpu_to_dump32(s, bitmap_blocks);
     strncpy(dh->utsname.machine, ELF_MACHINE_UNAME, sizeof(dh->utsname.machine));
 
     if (s->flag_compress & DUMP_DH_COMPRESSED_ZLIB) {
@@ -941,7 +890,7 @@ static int create_header64(DumpState *s)
         status |= DUMP_DH_COMPRESSED_SNAPPY;
     }
 #endif
-    dh->status = cpu_convert_to_target32(status, endian);
+    dh->status = cpu_to_dump32(s, status);
 
     if (write_buffer(s->fd, 0, dh, size) < 0) {
         dump_error(s, "dump: failed to write disk dump header.\n");
@@ -954,13 +903,13 @@ static int create_header64(DumpState *s)
     kh = g_malloc0(size);
 
     /* 64bit max_mapnr_64 */
-    kh->max_mapnr_64 = cpu_convert_to_target64(s->max_mapnr, endian);
-    kh->phys_base = cpu_convert_to_target64(PHYS_BASE, endian);
-    kh->dump_level = cpu_convert_to_target32(DUMP_LEVEL, endian);
+    kh->max_mapnr_64 = cpu_to_dump64(s, s->max_mapnr);
+    kh->phys_base = cpu_to_dump64(s, PHYS_BASE);
+    kh->dump_level = cpu_to_dump32(s, DUMP_LEVEL);
 
     offset_note = DISKDUMP_HEADER_BLOCKS * block_size + size;
-    kh->offset_note = cpu_convert_to_target64(offset_note, endian);
-    kh->note_size = cpu_convert_to_target64(s->note_size, endian);
+    kh->offset_note = cpu_to_dump64(s, offset_note);
+    kh->note_size = cpu_to_dump64(s, s->note_size);
 
     if (write_buffer(s->fd, DISKDUMP_HEADER_BLOCKS *
                      block_size, kh, size) < 0) {
@@ -1004,7 +953,7 @@ out:
 
 static int write_dump_header(DumpState *s)
 {
-    if (s->dump_info.d_machine == EM_386) {
+    if (s->dump_info.d_class == ELFCLASS32) {
         return create_header32(s);
     } else {
         return create_header64(s);
@@ -1086,9 +1035,9 @@ static bool get_next_page(GuestPhysBlock **blockptr, uint64_t *pfnptr,
     if (!block) {
         block = QTAILQ_FIRST(&s->guest_phys_blocks.head);
         *blockptr = block;
-        assert(block->target_start % s->page_size == 0);
-        assert(block->target_end % s->page_size == 0);
-        *pfnptr = paddr_to_pfn(block->target_start, s->page_shift);
+        assert((block->target_start & ~TARGET_PAGE_MASK) == 0);
+        assert((block->target_end & ~TARGET_PAGE_MASK) == 0);
+        *pfnptr = paddr_to_pfn(block->target_start);
         if (bufptr) {
             *bufptr = block->host_addr;
         }
@@ -1096,10 +1045,10 @@ static bool get_next_page(GuestPhysBlock **blockptr, uint64_t *pfnptr,
     }
 
     *pfnptr = *pfnptr + 1;
-    addr = pfn_to_paddr(*pfnptr, s->page_shift);
+    addr = pfn_to_paddr(*pfnptr);
 
     if ((addr >= block->target_start) &&
-        (addr + s->page_size <= block->target_end)) {
+        (addr + TARGET_PAGE_SIZE <= block->target_end)) {
         buf = block->host_addr + (addr - block->target_start);
     } else {
         /* the next page is in the next block */
@@ -1108,9 +1057,9 @@ static bool get_next_page(GuestPhysBlock **blockptr, uint64_t *pfnptr,
         if (!block) {
             return false;
         }
-        assert(block->target_start % s->page_size == 0);
-        assert(block->target_end % s->page_size == 0);
-        *pfnptr = paddr_to_pfn(block->target_start, s->page_shift);
+        assert((block->target_start & ~TARGET_PAGE_MASK) == 0);
+        assert((block->target_end & ~TARGET_PAGE_MASK) == 0);
+        *pfnptr = paddr_to_pfn(block->target_start);
         buf = block->host_addr;
     }
 
@@ -1224,42 +1173,24 @@ static void free_data_cache(DataCache *data_cache)
 
 static size_t get_len_buf_out(size_t page_size, uint32_t flag_compress)
 {
-    size_t len_buf_out_zlib, len_buf_out_lzo, len_buf_out_snappy;
-    size_t len_buf_out;
+    switch (flag_compress) {
+    case DUMP_DH_COMPRESSED_ZLIB:
+        return compressBound(page_size);
 
-    /* init buf_out */
-    len_buf_out_zlib = len_buf_out_lzo = len_buf_out_snappy = 0;
-
-    /* buf size for zlib */
-    len_buf_out_zlib = compressBound(page_size);
-
-    /* buf size for lzo */
-#ifdef CONFIG_LZO
-    if (flag_compress & DUMP_DH_COMPRESSED_LZO) {
-        if (lzo_init() != LZO_E_OK) {
-            /* return 0 to indicate lzo is unavailable */
-            return 0;
-        }
-    }
-
-    /*
-     * LZO will expand incompressible data by a little amount. please check the
-     * following URL to see the expansion calculation:
-     * http://www.oberhumer.com/opensource/lzo/lzofaq.php
-     */
-    len_buf_out_lzo = page_size + page_size / 16 + 64 + 3;
-#endif
+    case DUMP_DH_COMPRESSED_LZO:
+        /*
+         * LZO will expand incompressible data by a little amount. Please check
+         * the following URL to see the expansion calculation:
+         * http://www.oberhumer.com/opensource/lzo/lzofaq.php
+         */
+        return page_size + page_size / 16 + 64 + 3;
 
 #ifdef CONFIG_SNAPPY
-    /* buf size for snappy */
-    len_buf_out_snappy = snappy_max_compressed_length(page_size);
+    case DUMP_DH_COMPRESSED_SNAPPY:
+        return snappy_max_compressed_length(page_size);
 #endif
-
-    /* get the biggest that can store all kinds of compressed page */
-    len_buf_out = MAX(len_buf_out_zlib,
-                      MAX(len_buf_out_lzo, len_buf_out_snappy));
-
-    return len_buf_out;
+    }
+    return 0;
 }
 
 /*
@@ -1282,7 +1213,6 @@ static int write_dump_pages(DumpState *s)
     off_t offset_desc, offset_data;
     PageDescriptor pd, pd_zero;
     uint8_t *buf;
-    int endian = s->dump_info.d_endian;
     GuestPhysBlock *block_iter = NULL;
     uint64_t pfn_iter;
 
@@ -1294,11 +1224,8 @@ static int write_dump_pages(DumpState *s)
     prepare_data_cache(&page_data, s, offset_data);
 
     /* prepare buffer to store compressed data */
-    len_buf_out = get_len_buf_out(s->page_size, s->flag_compress);
-    if (len_buf_out == 0) {
-        dump_error(s, "dump: failed to get length of output buffer.\n");
-        goto out;
-    }
+    len_buf_out = get_len_buf_out(TARGET_PAGE_SIZE, s->flag_compress);
+    assert(len_buf_out != 0);
 
 #ifdef CONFIG_LZO
     wrkmem = g_malloc(LZO1X_1_MEM_COMPRESS);
@@ -1310,19 +1237,19 @@ static int write_dump_pages(DumpState *s)
      * init zero page's page_desc and page_data, because every zero page
      * uses the same page_data
      */
-    pd_zero.size = cpu_convert_to_target32(s->page_size, endian);
-    pd_zero.flags = cpu_convert_to_target32(0, endian);
-    pd_zero.offset = cpu_convert_to_target64(offset_data, endian);
-    pd_zero.page_flags = cpu_convert_to_target64(0, endian);
-    buf = g_malloc0(s->page_size);
-    ret = write_cache(&page_data, buf, s->page_size, false);
+    pd_zero.size = cpu_to_dump32(s, TARGET_PAGE_SIZE);
+    pd_zero.flags = cpu_to_dump32(s, 0);
+    pd_zero.offset = cpu_to_dump64(s, offset_data);
+    pd_zero.page_flags = cpu_to_dump64(s, 0);
+    buf = g_malloc0(TARGET_PAGE_SIZE);
+    ret = write_cache(&page_data, buf, TARGET_PAGE_SIZE, false);
     g_free(buf);
     if (ret < 0) {
         dump_error(s, "dump: failed to write page data(zero page).\n");
         goto out;
     }
 
-    offset_data += s->page_size;
+    offset_data += TARGET_PAGE_SIZE;
 
     /*
      * dump memory to vmcore page by page. zero page will all be resided in the
@@ -1330,7 +1257,7 @@ static int write_dump_pages(DumpState *s)
      */
     while (get_next_page(&block_iter, &pfn_iter, &buf, s)) {
         /* check zero page */
-        if (is_zero_page(buf, s->page_size)) {
+        if (is_zero_page(buf, TARGET_PAGE_SIZE)) {
             ret = write_cache(&page_desc, &pd_zero, sizeof(PageDescriptor),
                               false);
             if (ret < 0) {
@@ -1351,11 +1278,11 @@ static int write_dump_pages(DumpState *s)
              */
              size_out = len_buf_out;
              if ((s->flag_compress & DUMP_DH_COMPRESSED_ZLIB) &&
-                    (compress2(buf_out, (uLongf *)&size_out, buf, s->page_size,
-                    Z_BEST_SPEED) == Z_OK) && (size_out < s->page_size)) {
-                pd.flags = cpu_convert_to_target32(DUMP_DH_COMPRESSED_ZLIB,
-                                                   endian);
-                pd.size  = cpu_convert_to_target32(size_out, endian);
+                    (compress2(buf_out, (uLongf *)&size_out, buf,
+                               TARGET_PAGE_SIZE, Z_BEST_SPEED) == Z_OK) &&
+                    (size_out < TARGET_PAGE_SIZE)) {
+                pd.flags = cpu_to_dump32(s, DUMP_DH_COMPRESSED_ZLIB);
+                pd.size  = cpu_to_dump32(s, size_out);
 
                 ret = write_cache(&page_data, buf_out, size_out, false);
                 if (ret < 0) {
@@ -1364,12 +1291,11 @@ static int write_dump_pages(DumpState *s)
                 }
 #ifdef CONFIG_LZO
             } else if ((s->flag_compress & DUMP_DH_COMPRESSED_LZO) &&
-                    (lzo1x_1_compress(buf, s->page_size, buf_out,
+                    (lzo1x_1_compress(buf, TARGET_PAGE_SIZE, buf_out,
                     (lzo_uint *)&size_out, wrkmem) == LZO_E_OK) &&
-                    (size_out < s->page_size)) {
-                pd.flags = cpu_convert_to_target32(DUMP_DH_COMPRESSED_LZO,
-                                                   endian);
-                pd.size  = cpu_convert_to_target32(size_out, endian);
+                    (size_out < TARGET_PAGE_SIZE)) {
+                pd.flags = cpu_to_dump32(s, DUMP_DH_COMPRESSED_LZO);
+                pd.size  = cpu_to_dump32(s, size_out);
 
                 ret = write_cache(&page_data, buf_out, size_out, false);
                 if (ret < 0) {
@@ -1379,12 +1305,11 @@ static int write_dump_pages(DumpState *s)
 #endif
 #ifdef CONFIG_SNAPPY
             } else if ((s->flag_compress & DUMP_DH_COMPRESSED_SNAPPY) &&
-                    (snappy_compress((char *)buf, s->page_size,
+                    (snappy_compress((char *)buf, TARGET_PAGE_SIZE,
                     (char *)buf_out, &size_out) == SNAPPY_OK) &&
-                    (size_out < s->page_size)) {
-                pd.flags = cpu_convert_to_target32(
-                                        DUMP_DH_COMPRESSED_SNAPPY, endian);
-                pd.size  = cpu_convert_to_target32(size_out, endian);
+                    (size_out < TARGET_PAGE_SIZE)) {
+                pd.flags = cpu_to_dump32(s, DUMP_DH_COMPRESSED_SNAPPY);
+                pd.size  = cpu_to_dump32(s, size_out);
 
                 ret = write_cache(&page_data, buf_out, size_out, false);
                 if (ret < 0) {
@@ -1395,13 +1320,13 @@ static int write_dump_pages(DumpState *s)
             } else {
                 /*
                  * fall back to save in plaintext, size_out should be
-                 * assigned to s->page_size
+                 * assigned TARGET_PAGE_SIZE
                  */
-                pd.flags = cpu_convert_to_target32(0, endian);
-                size_out = s->page_size;
-                pd.size = cpu_convert_to_target32(size_out, endian);
+                pd.flags = cpu_to_dump32(s, 0);
+                size_out = TARGET_PAGE_SIZE;
+                pd.size = cpu_to_dump32(s, size_out);
 
-                ret = write_cache(&page_data, buf, s->page_size, false);
+                ret = write_cache(&page_data, buf, TARGET_PAGE_SIZE, false);
                 if (ret < 0) {
                     dump_error(s, "dump: failed to write page data.\n");
                     goto out;
@@ -1409,8 +1334,8 @@ static int write_dump_pages(DumpState *s)
             }
 
             /* get and write page desc here */
-            pd.page_flags = cpu_convert_to_target64(0, endian);
-            pd.offset = cpu_convert_to_target64(offset_data, endian);
+            pd.page_flags = cpu_to_dump64(s, 0);
+            pd.offset = cpu_to_dump64(s, offset_data);
             offset_data += size_out;
 
             ret = write_cache(&page_desc, &pd, sizeof(PageDescriptor), false);
@@ -1536,7 +1461,7 @@ static void get_max_mapnr(DumpState *s)
     GuestPhysBlock *last_block;
 
     last_block = QTAILQ_LAST(&s->guest_phys_blocks.head, GuestPhysBlockHead);
-    s->max_mapnr = paddr_to_pfn(last_block->target_end, s->page_shift);
+    s->max_mapnr = paddr_to_pfn(last_block->target_end);
 }
 
 static int dump_init(DumpState *s, int fd, bool has_format,
@@ -1613,14 +1538,12 @@ static int dump_init(DumpState *s, int fd, bool has_format,
     }
 
     s->nr_cpus = nr_cpus;
-    s->page_size = TARGET_PAGE_SIZE;
-    s->page_shift = ffs(s->page_size) - 1;
 
     get_max_mapnr(s);
 
     uint64_t tmp;
-    tmp = DIV_ROUND_UP(DIV_ROUND_UP(s->max_mapnr, CHAR_BIT), s->page_size);
-    s->len_dump_bitmap = tmp * s->page_size;
+    tmp = DIV_ROUND_UP(DIV_ROUND_UP(s->max_mapnr, CHAR_BIT), TARGET_PAGE_SIZE);
+    s->len_dump_bitmap = tmp * TARGET_PAGE_SIZE;
 
     /* init for kdump-compressed format */
     if (has_format && format != DUMP_GUEST_MEMORY_FORMAT_ELF) {
@@ -1630,6 +1553,12 @@ static int dump_init(DumpState *s, int fd, bool has_format,
             break;
 
         case DUMP_GUEST_MEMORY_FORMAT_KDUMP_LZO:
+#ifdef CONFIG_LZO
+            if (lzo_init() != LZO_E_OK) {
+                error_setg(errp, "failed to initialize the LZO library");
+                goto cleanup;
+            }
+#endif
             s->flag_compress = DUMP_DH_COMPRESSED_LZO;
             break;
 

exec.c

@@ -50,7 +50,6 @@
 
 #include "exec/memory-internal.h"
 #include "exec/ram_addr.h"
-#include "qemu/cache-utils.h"
 
 #include "qemu/range.h"
 
@@ -70,6 +69,12 @@ AddressSpace address_space_memory;
 MemoryRegion io_mem_rom, io_mem_notdirty;
 static MemoryRegion io_mem_unassigned;
 
+/* RAM is pre-allocated and passed into qemu_ram_alloc_from_ptr */
+#define RAM_PREALLOC   (1 << 0)
+
+/* RAM is mmap-ed with MAP_SHARED */
+#define RAM_SHARED     (1 << 1)
+
 #endif
 
 struct CPUTailQ cpus = QTAILQ_HEAD_INITIALIZER(cpus);
@@ -1011,16 +1016,10 @@ static long gethugepagesize(const char *path)
     return fs.f_bsize;
 }
 
-static sigjmp_buf sigjump;
-
-static void sigbus_handler(int signal)
-{
-    siglongjmp(sigjump, 1);
-}
-
 static void *file_ram_alloc(RAMBlock *block,
                             ram_addr_t memory,
-                            const char *path)
+                            const char *path,
+                            Error **errp)
 {
     char *filename;
     char *sanitized_name;
@@ -1039,7 +1038,8 @@ static void *file_ram_alloc(RAMBlock *block,
     }
 
     if (kvm_enabled() && !kvm_has_sync_mmu()) {
-        fprintf(stderr, "host lacks kvm mmu notifiers, -mem-path unsupported\n");
+        error_setg(errp,
+                   "host lacks kvm mmu notifiers, -mem-path unsupported");
         goto error;
     }
 
@@ -1056,7 +1056,8 @@ static void *file_ram_alloc(RAMBlock *block,
 
     fd = mkstemp(filename);
     if (fd < 0) {
-        perror("unable to create backing store for hugepages");
+        error_setg_errno(errp, errno,
+                         "unable to create backing store for hugepages");
         g_free(filename);
         goto error;
     }
@@ -1071,53 +1072,22 @@ static void *file_ram_alloc(RAMBlock *block,
      * If anything goes wrong with it under other filesystems,
      * mmap will fail.
      */
-    if (ftruncate(fd, memory))
+    if (ftruncate(fd, memory)) {
         perror("ftruncate");
+    }
 
-    area = mmap(0, memory, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
+    area = mmap(0, memory, PROT_READ | PROT_WRITE,
+                (block->flags & RAM_SHARED ? MAP_SHARED : MAP_PRIVATE),
+                fd, 0);
     if (area == MAP_FAILED) {
-        perror("file_ram_alloc: can't mmap RAM pages");
+        error_setg_errno(errp, errno,
+                         "unable to map backing store for hugepages");
         close(fd);
         goto error;
     }
 
     if (mem_prealloc) {
-        int ret, i;
-        struct sigaction act, oldact;
-        sigset_t set, oldset;
-
-        memset(&act, 0, sizeof(act));
-        act.sa_handler = &sigbus_handler;
-        act.sa_flags = 0;
-
-        ret = sigaction(SIGBUS, &act, &oldact);
-        if (ret) {
-            perror("file_ram_alloc: failed to install signal handler");
-            exit(1);
-        }
-
-        /* unblock SIGBUS */
-        sigemptyset(&set);
-        sigaddset(&set, SIGBUS);
-        pthread_sigmask(SIG_UNBLOCK, &set, &oldset);
-
-        if (sigsetjmp(sigjump, 1)) {
-            fprintf(stderr, "file_ram_alloc: failed to preallocate pages\n");
-            exit(1);
-        }
-
-        /* MAP_POPULATE silently ignores failures */
-        for (i = 0; i < (memory/hpagesize); i++) {
-            memset(area + (hpagesize*i), 0, 1);
-        }
-
-        ret = sigaction(SIGBUS, &oldact, NULL);
-        if (ret) {
-            perror("file_ram_alloc: failed to reinstall signal handler");
-            exit(1);
-        }
-
-        pthread_sigmask(SIG_SETMASK, &oldset, NULL);
+        os_mem_prealloc(fd, area, memory);
     }
 
     block->fd = fd;
@@ -1129,14 +1099,6 @@ error:
     }
     return NULL;
 }
-#else
-static void *file_ram_alloc(RAMBlock *block,
-                            ram_addr_t memory,
-                            const char *path)
-{
-    fprintf(stderr, "-mem-path not supported on this host\n");
-    exit(1);
-}
 #endif
 
 static ram_addr_t find_ram_offset(ram_addr_t size)
@@ -1201,17 +1163,24 @@ static void qemu_ram_setup_dump(void *addr, ram_addr_t size)
     }
 }
 
-void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev)
+static RAMBlock *find_ram_block(ram_addr_t addr)
 {
-    RAMBlock *new_block, *block;
+    RAMBlock *block;
 
-    new_block = NULL;
     QTAILQ_FOREACH(block, &ram_list.blocks, next) {
         if (block->offset == addr) {
-            new_block = block;
-            break;
+            return block;
         }
     }
+
+    return NULL;
+}
+
+void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev)
+{
+    RAMBlock *new_block = find_ram_block(addr);
+    RAMBlock *block;
+
     assert(new_block);
     assert(!new_block->idstr[0]);
 
@@ -1236,6 +1205,15 @@ void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev)
     qemu_mutex_unlock_ramlist();
 }
 
+void qemu_ram_unset_idstr(ram_addr_t addr)
+{
+    RAMBlock *block = find_ram_block(addr);
+
+    if (block) {
+        memset(block->idstr, 0, sizeof(block->idstr));
+    }
+}
+
 static int memory_try_enable_merging(void *addr, size_t len)
 {
     if (!qemu_opt_get_bool(qemu_get_machine_opts(), "mem-merge", true)) {
@@ -1246,56 +1224,30 @@ static int memory_try_enable_merging(void *addr, size_t len)
     return qemu_madvise(addr, len, QEMU_MADV_MERGEABLE);
 }
 
-ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
-                                   MemoryRegion *mr)
+static ram_addr_t ram_block_add(RAMBlock *new_block)
 {
-    RAMBlock *block, *new_block;
+    RAMBlock *block;
     ram_addr_t old_ram_size, new_ram_size;
 
     old_ram_size = last_ram_offset() >> TARGET_PAGE_BITS;
 
-    size = TARGET_PAGE_ALIGN(size);
-    new_block = g_malloc0(sizeof(*new_block));
-    new_block->fd = -1;
-
     /* This assumes the iothread lock is taken here too.  */
     qemu_mutex_lock_ramlist();
-    new_block->mr = mr;
-    new_block->offset = find_ram_offset(size);
-    if (host) {
-        new_block->host = host;
-        new_block->flags |= RAM_PREALLOC_MASK;
-    } else if (xen_enabled()) {
-        if (mem_path) {
-            fprintf(stderr, "-mem-path not supported with Xen\n");
-            exit(1);
-        }
-        xen_ram_alloc(new_block->offset, size, mr);
-    } else {
-        if (mem_path) {
-            if (phys_mem_alloc != qemu_anon_ram_alloc) {
-                /*
-                 * file_ram_alloc() needs to allocate just like
-                 * phys_mem_alloc, but we haven't bothered to provide
-                 * a hook there.
-                 */
-                fprintf(stderr,
-                        "-mem-path not supported with this accelerator\n");
-                exit(1);
-            }
-            new_block->host = file_ram_alloc(new_block, size, mem_path);
-        }
-        if (!new_block->host) {
-            new_block->host = phys_mem_alloc(size);
+    new_block->offset = find_ram_offset(new_block->length);
+
+    if (!new_block->host) {
+        if (xen_enabled()) {
+            xen_ram_alloc(new_block->offset, new_block->length, new_block->mr);
+        } else {
+            new_block->host = phys_mem_alloc(new_block->length);
             if (!new_block->host) {
                 fprintf(stderr, "Cannot set up guest memory '%s': %s\n",
                         new_block->mr->name, strerror(errno));
                 exit(1);
             }
-            memory_try_enable_merging(new_block->host, size);
+            memory_try_enable_merging(new_block->host, new_block->length);
         }
     }
-    new_block->length = size;
 
     /* Keep the list sorted from biggest to smallest block.  */
     QTAILQ_FOREACH(block, &ram_list.blocks, next) {
@@ -1323,18 +1275,75 @@ ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
                                    old_ram_size, new_ram_size);
        }
     }
-    cpu_physical_memory_set_dirty_range(new_block->offset, size);
+    cpu_physical_memory_set_dirty_range(new_block->offset, new_block->length);
 
-    qemu_ram_setup_dump(new_block->host, size);
-    qemu_madvise(new_block->host, size, QEMU_MADV_HUGEPAGE);
-    qemu_madvise(new_block->host, size, QEMU_MADV_DONTFORK);
+    qemu_ram_setup_dump(new_block->host, new_block->length);
+    qemu_madvise(new_block->host, new_block->length, QEMU_MADV_HUGEPAGE);
+    qemu_madvise(new_block->host, new_block->length, QEMU_MADV_DONTFORK);
 
-    if (kvm_enabled())
-        kvm_setup_guest_memory(new_block->host, size);
+    if (kvm_enabled()) {
+        kvm_setup_guest_memory(new_block->host, new_block->length);
+    }
 
     return new_block->offset;
 }
 
+#ifdef __linux__
+ram_addr_t qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
+                                    bool share, const char *mem_path,
+                                    Error **errp)
+{
+    RAMBlock *new_block;
+
+    if (xen_enabled()) {
+        error_setg(errp, "-mem-path not supported with Xen");
+        return -1;
+    }
+
+    if (phys_mem_alloc != qemu_anon_ram_alloc) {
+        /*
+         * file_ram_alloc() needs to allocate just like
+         * phys_mem_alloc, but we haven't bothered to provide
+         * a hook there.
+         */
+        error_setg(errp,
+                   "-mem-path not supported with this accelerator");
+        return -1;
+    }
+
+    size = TARGET_PAGE_ALIGN(size);
+    new_block = g_malloc0(sizeof(*new_block));
+    new_block->mr = mr;
+    new_block->length = size;
+    new_block->flags = share ? RAM_SHARED : 0;
+    new_block->host = file_ram_alloc(new_block, size,
+                                     mem_path, errp);
+    if (!new_block->host) {
+        g_free(new_block);
+        return -1;
+    }
+
+    return ram_block_add(new_block);
+}
+#endif
+
+ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
+                                   MemoryRegion *mr)
+{
+    RAMBlock *new_block;
+
+    size = TARGET_PAGE_ALIGN(size);
+    new_block = g_malloc0(sizeof(*new_block));
+    new_block->mr = mr;
+    new_block->length = size;
+    new_block->fd = -1;
+    new_block->host = host;
+    if (host) {
+        new_block->flags |= RAM_PREALLOC;
+    }
+    return ram_block_add(new_block);
+}
+
 ram_addr_t qemu_ram_alloc(ram_addr_t size, MemoryRegion *mr)
 {
     return qemu_ram_alloc_from_ptr(size, NULL, mr);
@@ -1369,7 +1378,7 @@ void qemu_ram_free(ram_addr_t addr)
             QTAILQ_REMOVE(&ram_list.blocks, block, next);
             ram_list.mru_block = NULL;
             ram_list.version++;
-            if (block->flags & RAM_PREALLOC_MASK) {
+            if (block->flags & RAM_PREALLOC) {
                 ;
             } else if (xen_enabled()) {
                 xen_invalidate_map_cache_entry(block->host);
@@ -1401,7 +1410,7 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
         offset = addr - block->offset;
         if (offset < block->length) {
             vaddr = block->host + offset;
-            if (block->flags & RAM_PREALLOC_MASK) {
+            if (block->flags & RAM_PREALLOC) {
                 ;
             } else if (xen_enabled()) {
                 abort();
@@ -1409,12 +1418,8 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
                 flags = MAP_FIXED;
                 munmap(vaddr, length);
                 if (block->fd >= 0) {
-#ifdef MAP_POPULATE
-                    flags |= mem_prealloc ? MAP_POPULATE | MAP_SHARED :
-                        MAP_PRIVATE;
-#else
-                    flags |= MAP_PRIVATE;
-#endif
+                    flags |= (block->flags & RAM_SHARED ?
+                              MAP_SHARED : MAP_PRIVATE);
                     area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
                                 flags, block->fd, offset);
                 } else {
@@ -1444,6 +1449,13 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
 }
 #endif /* !_WIN32 */
 
+int qemu_get_ram_fd(ram_addr_t addr)
+{
+    RAMBlock *block = qemu_get_ram_block(addr);
+
+    return block->fd;
+}
+
 /* Return a host pointer to ram allocated with qemu_ram_alloc.
    With the exception of the softmmu code in this file, this should
    only be used for local memory (e.g. video ram) that the device owns,
@@ -1760,10 +1772,12 @@ static subpage_t *subpage_init(AddressSpace *as, hwaddr base)
     return mmio;
 }
 
-static uint16_t dummy_section(PhysPageMap *map, MemoryRegion *mr)
+static uint16_t dummy_section(PhysPageMap *map, AddressSpace *as,
+                              MemoryRegion *mr)
 {
+    assert(as);
     MemoryRegionSection section = {
-        .address_space = &address_space_memory,
+        .address_space = as,
         .mr = mr,
         .offset_within_address_space = 0,
         .offset_within_region = 0,
@@ -1795,13 +1809,13 @@ static void mem_begin(MemoryListener *listener)
     AddressSpaceDispatch *d = g_new0(AddressSpaceDispatch, 1);
     uint16_t n;
 
-    n = dummy_section(&d->map, &io_mem_unassigned);
+    n = dummy_section(&d->map, as, &io_mem_unassigned);
     assert(n == PHYS_SECTION_UNASSIGNED);
-    n = dummy_section(&d->map, &io_mem_notdirty);
+    n = dummy_section(&d->map, as, &io_mem_notdirty);
     assert(n == PHYS_SECTION_NOTDIRTY);
-    n = dummy_section(&d->map, &io_mem_rom);
+    n = dummy_section(&d->map, as, &io_mem_rom);
     assert(n == PHYS_SECTION_ROM);
-    n = dummy_section(&d->map, &io_mem_watch);
+    n = dummy_section(&d->map, as, &io_mem_watch);
     assert(n == PHYS_SECTION_WATCH);
 
     d->phys_map  = (PhysPageEntry) { .ptr = PHYS_MAP_NODE_NIL, .skip = 1 };

fpu/softfloat-macros.h

@@ -55,7 +55,7 @@ these four paragraphs for those parts of this code that are retained.
 | The result is stored in the location pointed to by `zPtr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void shift32RightJamming(uint32_t a, int_fast16_t count, uint32_t *zPtr)
+static inline void shift32RightJamming(uint32_t a, int_fast16_t count, uint32_t *zPtr)
 {
     uint32_t z;
 
@@ -81,7 +81,7 @@ INLINE void shift32RightJamming(uint32_t a, int_fast16_t count, uint32_t *zPtr)
 | The result is stored in the location pointed to by `zPtr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void shift64RightJamming(uint64_t a, int_fast16_t count, uint64_t *zPtr)
+static inline void shift64RightJamming(uint64_t a, int_fast16_t count, uint64_t *zPtr)
 {
     uint64_t z;
 
@@ -115,7 +115,7 @@ INLINE void shift64RightJamming(uint64_t a, int_fast16_t count, uint64_t *zPtr)
 | described above, and is returned at the location pointed to by `z1Ptr'.)
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  shift64ExtraRightJamming(
      uint64_t a0, uint64_t a1, int_fast16_t count, uint64_t *z0Ptr, uint64_t *z1Ptr)
 {
@@ -152,7 +152,7 @@ INLINE void
 | which are stored at the locations pointed to by `z0Ptr' and `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  shift128Right(
      uint64_t a0, uint64_t a1, int_fast16_t count, uint64_t *z0Ptr, uint64_t *z1Ptr)
 {
@@ -187,7 +187,7 @@ INLINE void
 | the locations pointed to by `z0Ptr' and `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  shift128RightJamming(
      uint64_t a0, uint64_t a1, int_fast16_t count, uint64_t *z0Ptr, uint64_t *z1Ptr)
 {
@@ -238,7 +238,7 @@ INLINE void
 | `z2Ptr'.)
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  shift128ExtraRightJamming(
      uint64_t a0,
      uint64_t a1,
@@ -296,7 +296,7 @@ INLINE void
 | pieces which are stored at the locations pointed to by `z0Ptr' and `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  shortShift128Left(
      uint64_t a0, uint64_t a1, int_fast16_t count, uint64_t *z0Ptr, uint64_t *z1Ptr)
 {
@@ -315,7 +315,7 @@ INLINE void
 | `z1Ptr', and `z2Ptr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  shortShift192Left(
      uint64_t a0,
      uint64_t a1,
@@ -350,7 +350,7 @@ INLINE void
 | are stored at the locations pointed to by `z0Ptr' and `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  add128(
      uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1, uint64_t *z0Ptr, uint64_t *z1Ptr )
 {
@@ -370,7 +370,7 @@ INLINE void
 | `z1Ptr', and `z2Ptr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  add192(
      uint64_t a0,
      uint64_t a1,
@@ -408,7 +408,7 @@ INLINE void
 | `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  sub128(
      uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1, uint64_t *z0Ptr, uint64_t *z1Ptr )
 {
@@ -426,7 +426,7 @@ INLINE void
 | pointed to by `z0Ptr', `z1Ptr', and `z2Ptr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  sub192(
      uint64_t a0,
      uint64_t a1,
@@ -462,7 +462,7 @@ INLINE void
 | `z0Ptr' and `z1Ptr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void mul64To128( uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t *z1Ptr )
+static inline void mul64To128( uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t *z1Ptr )
 {
     uint32_t aHigh, aLow, bHigh, bLow;
     uint64_t z0, zMiddleA, zMiddleB, z1;
@@ -492,7 +492,7 @@ INLINE void mul64To128( uint64_t a, uint64_t b, uint64_t *z0Ptr, uint64_t *z1Ptr
 | `z2Ptr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  mul128By64To192(
      uint64_t a0,
      uint64_t a1,
@@ -520,7 +520,7 @@ INLINE void
 | the locations pointed to by `z0Ptr', `z1Ptr', `z2Ptr', and `z3Ptr'.
 *----------------------------------------------------------------------------*/
 
-INLINE void
+static inline void
  mul128To256(
      uint64_t a0,
      uint64_t a1,
@@ -702,7 +702,7 @@ static int8 countLeadingZeros64( uint64_t a )
 | Otherwise, returns 0.
 *----------------------------------------------------------------------------*/
 
-INLINE flag eq128( uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1 )
+static inline flag eq128( uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1 )
 {
 
     return ( a0 == b0 ) && ( a1 == b1 );
@@ -715,7 +715,7 @@ INLINE flag eq128( uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1 )
 | Otherwise, returns 0.
 *----------------------------------------------------------------------------*/
 
-INLINE flag le128( uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1 )
+static inline flag le128( uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1 )
 {
 
     return ( a0 < b0 ) || ( ( a0 == b0 ) && ( a1 <= b1 ) );
@@ -728,7 +728,7 @@ INLINE flag le128( uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1 )
 | returns 0.
 *----------------------------------------------------------------------------*/
 
-INLINE flag lt128( uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1 )
+static inline flag lt128( uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1 )
 {
 
     return ( a0 < b0 ) || ( ( a0 == b0 ) && ( a1 < b1 ) );
@@ -741,7 +741,7 @@ INLINE flag lt128( uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1 )
 | Otherwise, returns 0.
 *----------------------------------------------------------------------------*/
 
-INLINE flag ne128( uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1 )
+static inline flag ne128( uint64_t a0, uint64_t a1, uint64_t b0, uint64_t b1 )
 {
 
     return ( a0 != b0 ) || ( a1 != b1 );

fpu/softfloat.c

@@ -66,7 +66,7 @@ these four paragraphs for those parts of this code that are retained.
 | Returns the fraction bits of the half-precision floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE uint32_t extractFloat16Frac(float16 a)
+static inline uint32_t extractFloat16Frac(float16 a)
 {
     return float16_val(a) & 0x3ff;
 }
@@ -75,7 +75,7 @@ INLINE uint32_t extractFloat16Frac(float16 a)
 | Returns the exponent bits of the half-precision floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE int_fast16_t extractFloat16Exp(float16 a)
+static inline int_fast16_t extractFloat16Exp(float16 a)
 {
     return (float16_val(a) >> 10) & 0x1f;
 }
@@ -84,7 +84,7 @@ INLINE int_fast16_t extractFloat16Exp(float16 a)
 | Returns the sign bit of the single-precision floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE flag extractFloat16Sign(float16 a)
+static inline flag extractFloat16Sign(float16 a)
 {
     return float16_val(a)>>15;
 }
@@ -255,7 +255,7 @@ static int64 roundAndPackUint64(flag zSign, uint64_t absZ0,
 | Returns the fraction bits of the single-precision floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE uint32_t extractFloat32Frac( float32 a )
+static inline uint32_t extractFloat32Frac( float32 a )
 {
 
     return float32_val(a) & 0x007FFFFF;
@@ -266,7 +266,7 @@ INLINE uint32_t extractFloat32Frac( float32 a )
 | Returns the exponent bits of the single-precision floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE int_fast16_t extractFloat32Exp(float32 a)
+static inline int_fast16_t extractFloat32Exp(float32 a)
 {
 
     return ( float32_val(a)>>23 ) & 0xFF;
@@ -277,7 +277,7 @@ INLINE int_fast16_t extractFloat32Exp(float32 a)
 | Returns the sign bit of the single-precision floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE flag extractFloat32Sign( float32 a )
+static inline flag extractFloat32Sign( float32 a )
 {
 
     return float32_val(a)>>31;
@@ -328,7 +328,7 @@ static void
 | significand.
 *----------------------------------------------------------------------------*/
 
-INLINE float32 packFloat32(flag zSign, int_fast16_t zExp, uint32_t zSig)
+static inline float32 packFloat32(flag zSign, int_fast16_t zExp, uint32_t zSig)
 {
 
     return make_float32(
@@ -440,7 +440,7 @@ static float32
 | Returns the fraction bits of the double-precision floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE uint64_t extractFloat64Frac( float64 a )
+static inline uint64_t extractFloat64Frac( float64 a )
 {
 
     return float64_val(a) & LIT64( 0x000FFFFFFFFFFFFF );
@@ -451,7 +451,7 @@ INLINE uint64_t extractFloat64Frac( float64 a )
 | Returns the exponent bits of the double-precision floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE int_fast16_t extractFloat64Exp(float64 a)
+static inline int_fast16_t extractFloat64Exp(float64 a)
 {
 
     return ( float64_val(a)>>52 ) & 0x7FF;
@@ -462,7 +462,7 @@ INLINE int_fast16_t extractFloat64Exp(float64 a)
 | Returns the sign bit of the double-precision floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE flag extractFloat64Sign( float64 a )
+static inline flag extractFloat64Sign( float64 a )
 {
 
     return float64_val(a)>>63;
@@ -513,7 +513,7 @@ static void
 | significand.
 *----------------------------------------------------------------------------*/
 
-INLINE float64 packFloat64(flag zSign, int_fast16_t zExp, uint64_t zSig)
+static inline float64 packFloat64(flag zSign, int_fast16_t zExp, uint64_t zSig)
 {
 
     return make_float64(
@@ -625,7 +625,7 @@ static float64
 | value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE uint64_t extractFloatx80Frac( floatx80 a )
+static inline uint64_t extractFloatx80Frac( floatx80 a )
 {
 
     return a.low;
@@ -637,7 +637,7 @@ INLINE uint64_t extractFloatx80Frac( floatx80 a )
 | value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE int32 extractFloatx80Exp( floatx80 a )
+static inline int32 extractFloatx80Exp( floatx80 a )
 {
 
     return a.high & 0x7FFF;
@@ -649,7 +649,7 @@ INLINE int32 extractFloatx80Exp( floatx80 a )
 | `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE flag extractFloatx80Sign( floatx80 a )
+static inline flag extractFloatx80Sign( floatx80 a )
 {
 
     return a.high>>15;
@@ -679,7 +679,7 @@ static void
 | extended double-precision floating-point value, returning the result.
 *----------------------------------------------------------------------------*/
 
-INLINE floatx80 packFloatx80( flag zSign, int32 zExp, uint64_t zSig )
+static inline floatx80 packFloatx80( flag zSign, int32 zExp, uint64_t zSig )
 {
     floatx80 z;
 
@@ -921,7 +921,7 @@ static floatx80
 | floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE uint64_t extractFloat128Frac1( float128 a )
+static inline uint64_t extractFloat128Frac1( float128 a )
 {
 
     return a.low;
@@ -933,7 +933,7 @@ INLINE uint64_t extractFloat128Frac1( float128 a )
 | floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE uint64_t extractFloat128Frac0( float128 a )
+static inline uint64_t extractFloat128Frac0( float128 a )
 {
 
     return a.high & LIT64( 0x0000FFFFFFFFFFFF );
@@ -945,7 +945,7 @@ INLINE uint64_t extractFloat128Frac0( float128 a )
 | `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE int32 extractFloat128Exp( float128 a )
+static inline int32 extractFloat128Exp( float128 a )
 {
 
     return ( a.high>>48 ) & 0x7FFF;
@@ -956,7 +956,7 @@ INLINE int32 extractFloat128Exp( float128 a )
 | Returns the sign bit of the quadruple-precision floating-point value `a'.
 *----------------------------------------------------------------------------*/
 
-INLINE flag extractFloat128Sign( float128 a )
+static inline flag extractFloat128Sign( float128 a )
 {
 
     return a.high>>63;
@@ -1017,7 +1017,7 @@ static void
 | significand.
 *----------------------------------------------------------------------------*/
 
-INLINE float128
+static inline float128
  packFloat128( flag zSign, int32 zExp, uint64_t zSig0, uint64_t zSig1 )
 {
     float128 z;
@@ -7088,7 +7088,7 @@ uint64_t float64_to_uint64_round_to_zero (float64 a STATUS_PARAM)
 }
 
 #define COMPARE(s, nan_exp)                                                  \
-INLINE int float ## s ## _compare_internal( float ## s a, float ## s b,      \
+static inline int float ## s ## _compare_internal( float ## s a, float ## s b,      \
                                       int is_quiet STATUS_PARAM )            \
 {                                                                            \
     flag aSign, bSign;                                                       \
@@ -7140,7 +7140,7 @@ int float ## s ## _compare_quiet( float ## s a, float ## s b STATUS_PARAM )  \
 COMPARE(32, 0xff)
 COMPARE(64, 0x7ff)
 
-INLINE int floatx80_compare_internal( floatx80 a, floatx80 b,
+static inline int floatx80_compare_internal( floatx80 a, floatx80 b,
                                       int is_quiet STATUS_PARAM )
 {
     flag aSign, bSign;
@@ -7186,7 +7186,7 @@ int floatx80_compare_quiet( floatx80 a, floatx80 b STATUS_PARAM )
     return floatx80_compare_internal(a, b, 1 STATUS_VAR);
 }
 
-INLINE int float128_compare_internal( float128 a, float128 b,
+static inline int float128_compare_internal( float128 a, float128 b,
                                       int is_quiet STATUS_PARAM )
 {
     flag aSign, bSign;
@@ -7242,7 +7242,7 @@ int float128_compare_quiet( float128 a, float128 b STATUS_PARAM )
  * semantics provided by many CPUs which predate that specification.
  */
 #define MINMAX(s)                                                       \
-INLINE float ## s float ## s ## _minmax(float ## s a, float ## s b,     \
+static inline float ## s float ## s ## _minmax(float ## s a, float ## s b,     \
                                         int ismin, int isieee STATUS_PARAM) \
 {                                                                       \
     flag aSign, bSign;                                                  \

hmp-commands.hx

@@ -335,6 +335,7 @@ ETEXI
         .params     = "tag|id",
         .help       = "restore a VM snapshot from its tag or id",
         .mhandler.cmd = do_loadvm,
+        .command_completion = loadvm_completion,
     },
 
 STEXI
@@ -350,6 +351,7 @@ ETEXI
         .params     = "tag|id",
         .help       = "delete a VM snapshot from its tag or id",
         .mhandler.cmd = do_delvm,
+        .command_completion = delvm_completion,
     },
 
 STEXI
@@ -852,6 +854,7 @@ ETEXI
         .params     = "device data",
         .help       = "Write to a ring buffer character device",
         .mhandler.cmd = hmp_ringbuf_write,
+        .command_completion = ringbuf_write_completion,
     },
 
 STEXI
@@ -868,6 +871,7 @@ ETEXI
         .params     = "device size",
         .help       = "Read from a ring buffer character device",
         .mhandler.cmd = hmp_ringbuf_read,
+        .command_completion = ringbuf_write_completion,
     },
 
 STEXI
@@ -973,6 +977,7 @@ ETEXI
         .params     = "capability state",
         .help       = "Enable/Disable the usage of a capability for migration",
         .mhandler.cmd = hmp_migrate_set_capability,
+        .command_completion = migrate_set_capability_completion,
     },
 
 STEXI
@@ -1206,9 +1211,10 @@ ETEXI
     {
         .name       = "host_net_add",
         .args_type  = "device:s,opts:s?",
-        .params     = "tap|user|socket|vde|netmap|dump [options]",
+        .params     = "tap|user|socket|vde|netmap|bridge|vhost-user|dump [options]",
         .help       = "add host VLAN client",
         .mhandler.cmd = net_host_device_add,
+        .command_completion = host_net_add_completion,
     },
 
 STEXI
@@ -1223,6 +1229,7 @@ ETEXI
         .params     = "vlan_id name",
         .help       = "remove host VLAN client",
         .mhandler.cmd = net_host_device_remove,
+        .command_completion = host_net_remove_completion,
     },
 
 STEXI
@@ -1234,7 +1241,7 @@ ETEXI
     {
         .name       = "netdev_add",
         .args_type  = "netdev:O",
-        .params     = "[user|tap|socket|vde|bridge|hubport|netmap],id=str[,prop=value][,...]",
+        .params     = "[user|tap|socket|vde|bridge|hubport|netmap|vhost-user],id=str[,prop=value][,...]",
         .help       = "add host network device",
         .mhandler.cmd = hmp_netdev_add,
         .command_completion = netdev_add_completion,
@@ -1357,6 +1364,7 @@ ETEXI
         .params     = "[reset|shutdown|poweroff|pause|debug|none]",
         .help       = "change watchdog action",
         .mhandler.cmd = do_watchdog_action,
+        .command_completion = watchdog_action_completion,
     },
 
 STEXI

hmp.c

@@ -22,6 +22,8 @@
 #include "qemu/sockets.h"
 #include "monitor/monitor.h"
 #include "qapi/opts-visitor.h"
+#include "qapi/string-output-visitor.h"
+#include "qapi-visit.h"
 #include "ui/console.h"
 #include "block/qapi.h"
 #include "qemu-io.h"
@@ -463,7 +465,8 @@ void hmp_info_vnc(Monitor *mon, const QDict *qdict)
         for (client = info->clients; client; client = client->next) {
             monitor_printf(mon, "Client:\n");
             monitor_printf(mon, "     address: %s:%s\n",
-                           client->value->host, client->value->service);
+                           client->value->base->host,
+                           client->value->base->service);
             monitor_printf(mon, "  x509_dname: %s\n",
                            client->value->x509_dname ?
                            client->value->x509_dname : "none");
@@ -511,7 +514,7 @@ void hmp_info_spice(Monitor *mon, const QDict *qdict)
         for (chan = info->channels; chan; chan = chan->next) {
             monitor_printf(mon, "Channel:\n");
             monitor_printf(mon, "     address: %s:%s%s\n",
-                           chan->value->host, chan->value->port,
+                           chan->value->base->host, chan->value->base->port,
                            chan->value->tls ? " [tls]" : "");
             monitor_printf(mon, "     session: %" PRId64 "\n",
                            chan->value->connection_id);
@@ -1676,3 +1679,37 @@ void hmp_object_del(Monitor *mon, const QDict *qdict)
     qmp_object_del(id, &err);
     hmp_handle_error(mon, &err);
 }
+
+void hmp_info_memdev(Monitor *mon, const QDict *qdict)
+{
+    Error *err = NULL;
+    MemdevList *memdev_list = qmp_query_memdev(&err);
+    MemdevList *m = memdev_list;
+    StringOutputVisitor *ov;
+    int i = 0;
+
+
+    while (m) {
+        ov = string_output_visitor_new(false);
+        visit_type_uint16List(string_output_get_visitor(ov),
+                              &m->value->host_nodes, NULL, NULL);
+        monitor_printf(mon, "memory backend: %d\n", i);
+        monitor_printf(mon, "  size:  %" PRId64 "\n", m->value->size);
+        monitor_printf(mon, "  merge: %s\n",
+                       m->value->merge ? "true" : "false");
+        monitor_printf(mon, "  dump: %s\n",
+                       m->value->dump ? "true" : "false");
+        monitor_printf(mon, "  prealloc: %s\n",
+                       m->value->prealloc ? "true" : "false");
+        monitor_printf(mon, "  policy: %s\n",
+                       HostMemPolicy_lookup[m->value->policy]);
+        monitor_printf(mon, "  host nodes: %s\n",
+                       string_output_get_string(ov));
+
+        string_output_visitor_cleanup(ov);
+        m = m->next;
+        i++;
+    }
+
+    monitor_printf(mon, "\n");
+}

hmp.h

@@ -93,6 +93,7 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict);
 void hmp_cpu_add(Monitor *mon, const QDict *qdict);
 void hmp_object_add(Monitor *mon, const QDict *qdict);
 void hmp_object_del(Monitor *mon, const QDict *qdict);
+void hmp_info_memdev(Monitor *mon, const QDict *qdict);
 void object_add_completion(ReadLineState *rs, int nb_args, const char *str);
 void object_del_completion(ReadLineState *rs, int nb_args, const char *str);
 void device_add_completion(ReadLineState *rs, int nb_args, const char *str);
@@ -103,5 +104,16 @@ void chardev_add_completion(ReadLineState *rs, int nb_args, const char *str);
 void set_link_completion(ReadLineState *rs, int nb_args, const char *str);
 void netdev_add_completion(ReadLineState *rs, int nb_args, const char *str);
 void netdev_del_completion(ReadLineState *rs, int nb_args, const char *str);
+void ringbuf_write_completion(ReadLineState *rs, int nb_args, const char *str);
+void ringbuf_read_completion(ReadLineState *rs, int nb_args, const char *str);
+void watchdog_action_completion(ReadLineState *rs, int nb_args,
+                                const char *str);
+void migrate_set_capability_completion(ReadLineState *rs, int nb_args,
+                                       const char *str);
+void host_net_add_completion(ReadLineState *rs, int nb_args, const char *str);
+void host_net_remove_completion(ReadLineState *rs, int nb_args,
+                                const char *str);
+void delvm_completion(ReadLineState *rs, int nb_args, const char *str);
+void loadvm_completion(ReadLineState *rs, int nb_args, const char *str);
 
 #endif

hw/9pfs/virtio-9p-device.c

@@ -34,7 +34,7 @@ static void virtio_9p_get_config(VirtIODevice *vdev, uint8_t *config)
 
     len = strlen(s->tag);
     cfg = g_malloc0(sizeof(struct virtio_9p_config) + len);
-    stw_raw(&cfg->tag_len, len);
+    stw_p(&cfg->tag_len, len);
     /* We don't copy the terminating null to config space */
     memcpy(cfg->tag, s->tag, len);
     memcpy(config, cfg, s->config_size);

hw/9pfs/virtio-9p.c

@@ -299,9 +299,7 @@ static int v9fs_xattr_fid_clunk(V9fsPDU *pdu, V9fsFidState *fidp)
 free_out:
     v9fs_string_free(&fidp->fs.xattr.name);
 free_value:
-    if (fidp->fs.xattr.value) {
-        g_free(fidp->fs.xattr.value);
-    }
+    g_free(fidp->fs.xattr.value);
     return retval;
 }
 

hw/Makefile.objs

@@ -29,6 +29,7 @@ devices-dirs-$(CONFIG_SOFTMMU) += usb/
 devices-dirs-$(CONFIG_VIRTIO) += virtio/
 devices-dirs-$(CONFIG_SOFTMMU) += watchdog/
 devices-dirs-$(CONFIG_SOFTMMU) += xen/
+devices-dirs-$(CONFIG_MEM_HOTPLUG) += mem/
 devices-dirs-y += core/
 common-obj-y += $(devices-dirs-y)
 obj-y += $(devices-dirs-y)

hw/acpi/Makefile.objs

@@ -1 +1,3 @@
 common-obj-$(CONFIG_ACPI) += core.o piix4.o ich9.o pcihp.o cpu_hotplug.o
+common-obj-$(CONFIG_ACPI) += memory_hotplug.o
+common-obj-$(CONFIG_ACPI) += acpi_interface.o

hw/acpi/acpi_interface.c

@@ -0,0 +1,15 @@
+#include "hw/acpi/acpi_dev_interface.h"
+#include "qemu/module.h"
+
+static void register_types(void)
+{
+    static const TypeInfo acpi_dev_if_info = {
+        .name          = TYPE_ACPI_DEVICE_IF,
+        .parent        = TYPE_INTERFACE,
+        .class_size = sizeof(AcpiDeviceIfClass),
+    };
+
+    type_register_static(&acpi_dev_if_info);
+}
+
+type_init(register_types)

hw/acpi/core.c

@@ -22,11 +22,11 @@
 #include "hw/hw.h"
 #include "hw/i386/pc.h"
 #include "hw/acpi/acpi.h"
-#include "monitor/monitor.h"
 #include "qemu/config-file.h"
 #include "qapi/opts-visitor.h"
 #include "qapi/dealloc-visitor.h"
 #include "qapi-visit.h"
+#include "qapi-event.h"
 
 struct acpi_table_header {
     uint16_t _length;         /* our length, not actual part of the hdr */
@@ -550,7 +550,7 @@ static void acpi_pm1_cnt_write(ACPIREGS *ar, uint16_t val)
             break;
         default:
             if (sus_typ == ar->pm1.cnt.s4_val) { /* S4 request */
-                monitor_protocol_event(QEVENT_SUSPEND_DISK, NULL);
+                qapi_event_send_suspend_disk(&error_abort);
                 qemu_system_shutdown_request();
             }
             break;

hw/acpi/ich9.c

@@ -34,6 +34,7 @@
 #include "exec/address-spaces.h"
 
 #include "hw/i386/ich9.h"
+#include "hw/mem/pc-dimm.h"
 
 //#define DEBUG
 
@@ -139,11 +140,27 @@ static int ich9_pm_post_load(void *opaque, int version_id)
      .offset     = vmstate_offset_pointer(_state, _field, uint8_t),  \
  }
 
+static bool vmstate_test_use_memhp(void *opaque)
+{
+    ICH9LPCPMRegs *s = opaque;
+    return s->acpi_memory_hotplug.is_enabled;
+}
+
+static const VMStateDescription vmstate_memhp_state = {
+    .name = "ich9_pm/memhp",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .minimum_version_id_old = 1,
+    .fields      = (VMStateField[]) {
+        VMSTATE_MEMORY_HOTPLUG(acpi_memory_hotplug, ICH9LPCPMRegs),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 const VMStateDescription vmstate_ich9_pm = {
     .name = "ich9_pm",
     .version_id = 1,
     .minimum_version_id = 1,
-    .minimum_version_id_old = 1,
     .post_load = ich9_pm_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINT16(acpi_regs.pm1.evt.sts, ICH9LPCPMRegs),
@@ -156,6 +173,13 @@ const VMStateDescription vmstate_ich9_pm = {
         VMSTATE_UINT32(smi_en, ICH9LPCPMRegs),
         VMSTATE_UINT32(smi_sts, ICH9LPCPMRegs),
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (VMStateSubsection[]) {
+        {
+            .vmsd = &vmstate_memhp_state,
+            .needed = vmstate_test_use_memhp,
+        },
+        VMSTATE_END_OF_LIST()
     }
 };
 
@@ -224,6 +248,11 @@ void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm,
                         &pm->gpe_cpu, ICH9_CPU_HOTPLUG_IO_BASE);
     pm->cpu_added_notifier.notify = ich9_cpu_added_req;
     qemu_register_cpu_added_notifier(&pm->cpu_added_notifier);
+
+    if (pm->acpi_memory_hotplug.is_enabled) {
+        acpi_memory_hotplug_init(pci_address_space_io(lpc_pci), OBJECT(lpc_pci),
+                                 &pm->acpi_memory_hotplug);
+    }
 }
 
 static void ich9_pm_get_gpe0_blk(Object *obj, Visitor *v,
@@ -236,9 +265,25 @@ static void ich9_pm_get_gpe0_blk(Object *obj, Visitor *v,
     visit_type_uint32(v, &value, name, errp);
 }
 
+static bool ich9_pm_get_memory_hotplug_support(Object *obj, Error **errp)
+{
+    ICH9LPCState *s = ICH9_LPC_DEVICE(obj);
+
+    return s->pm.acpi_memory_hotplug.is_enabled;
+}
+
+static void ich9_pm_set_memory_hotplug_support(Object *obj, bool value,
+                                               Error **errp)
+{
+    ICH9LPCState *s = ICH9_LPC_DEVICE(obj);
+
+    s->pm.acpi_memory_hotplug.is_enabled = value;
+}
+
 void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm, Error **errp)
 {
     static const uint32_t gpe0_len = ICH9_PMIO_GPE0_LEN;
+    pm->acpi_memory_hotplug.is_enabled = true;
 
     object_property_add_uint32_ptr(obj, ACPI_PM_PROP_PM_IO_BASE,
                                    &pm->pm_io_base, errp);
@@ -247,4 +292,27 @@ void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm, Error **errp)
                         NULL, NULL, pm, NULL);
     object_property_add_uint32_ptr(obj, ACPI_PM_PROP_GPE0_BLK_LEN,
                                    &gpe0_len, errp);
+    object_property_add_bool(obj, "memory-hotplug-support",
+                             ich9_pm_get_memory_hotplug_support,
+                             ich9_pm_set_memory_hotplug_support,
+                             NULL);
+}
+
+void ich9_pm_device_plug_cb(ICH9LPCPMRegs *pm, DeviceState *dev, Error **errp)
+{
+    if (pm->acpi_memory_hotplug.is_enabled &&
+        object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
+        acpi_memory_plug_cb(&pm->acpi_regs, pm->irq, &pm->acpi_memory_hotplug,
+                            dev, errp);
+    } else {
+        error_setg(errp, "acpi: device plug request for not supported device"
+                   " type: %s", object_get_typename(OBJECT(dev)));
+    }
+}
+
+void ich9_pm_ospm_status(AcpiDeviceIf *adev, ACPIOSTInfoList ***list)
+{
+    ICH9LPCState *s = ICH9_LPC_DEVICE(adev);
+
+    acpi_memory_ospm_status(&s->pm.acpi_memory_hotplug, list);
 }