gtk: update window size after showing/hiding tabs

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>

.gitignore

@@ -4,6 +4,7 @@
 /config-host.*
 /config-target.*
 /config.status
+/config-temp
 /trace/generated-tracers.h
 /trace/generated-tracers.c
 /trace/generated-tracers-dtrace.h

.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

@@ -243,8 +243,8 @@ S: Maintained
 F: hw/*/exynos*
 
 Calxeda Highbank
-M: Mark Langsdorf <mark.langsdorf@calxeda.com>
-S: Supported
+M: Rob Herring <robh@kernel.org>
+S: Maintained
 F: hw/arm/highbank.c
 F: hw/net/xgmac.c
 

Makefile

@@ -52,12 +52,12 @@ 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

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) \

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;
@@ -975,12 +974,12 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
     xh_len = qemu_get_be16(f);
 
     if (xh_flags != ENCODING_FLAG_XBZRLE) {
-        fprintf(stderr, "Failed to load XBZRLE page - wrong compression!\n");
+        error_report("Failed to load XBZRLE page - wrong compression!");
         return -1;
     }
 
     if (xh_len > TARGET_PAGE_SIZE) {
-        fprintf(stderr, "Failed to load XBZRLE page - len overflow!\n");
+        error_report("Failed to load XBZRLE page - len overflow!");
         return -1;
     }
     /* load data and decode */
@@ -989,7 +988,7 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
     /* decode RLE */
     if (xbzrle_decode_buffer(xbzrle_decoded_buf, xh_len, host,
                              TARGET_PAGE_SIZE) == -1) {
-        fprintf(stderr, "Failed to load XBZRLE page - decode error!\n");
+        error_report("Failed to load XBZRLE page - decode error!");
         return -1;
     }
 
@@ -1006,7 +1005,7 @@ static inline void *host_from_stream_offset(QEMUFile *f,
 
     if (flags & RAM_SAVE_FLAG_CONTINUE) {
         if (!block) {
-            fprintf(stderr, "Ack, bad migration stream!\n");
+            error_report("Ack, bad migration stream!");
             return NULL;
         }
 
@@ -1022,7 +1021,7 @@ static inline void *host_from_stream_offset(QEMUFile *f,
             return memory_region_get_ram_ptr(block->mr) + offset;
     }
 
-    fprintf(stderr, "Can't find block %s!\n", id);
+    error_report("Can't find block %s!", id);
     return NULL;
 }
 
@@ -1075,10 +1074,9 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                 QTAILQ_FOREACH(block, &ram_list.blocks, next) {
                     if (!strncmp(id, block->idstr, sizeof(id))) {
                         if (block->length != length) {
-                            fprintf(stderr,
-                                    "Length mismatch: %s: " RAM_ADDR_FMT
-                                    " in != " RAM_ADDR_FMT "\n", id, length,
-                                    block->length);
+                            error_report("Length mismatch: %s: " RAM_ADDR_FMT
+                                         " in != " RAM_ADDR_FMT, id, length,
+                                         block->length);
                             ret =  -EINVAL;
                             goto done;
                         }
@@ -1087,8 +1085,8 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
                 }
 
                 if (!block) {
-                    fprintf(stderr, "Unknown ramblock \"%s\", cannot "
-                            "accept migration\n", id);
+                    error_report("Unknown ramblock \"%s\", cannot "
+                                 "accept migration", id);
                     ret = -EINVAL;
                     goto done;
                 }
@@ -1243,12 +1241,11 @@ void select_soundhw(const char *optarg)
 
             if (!c->name) {
                 if (l > 80) {
-                    fprintf(stderr,
-                            "Unknown sound card name (too big to show)\n");
+                    error_report("Unknown sound card name (too big to show)");
                 }
                 else {
-                    fprintf(stderr, "Unknown sound card name `%.*s'\n",
-                            (int) l, p);
+                    error_report("Unknown sound card name `%.*s'",
+                                 (int) l, p);
                 }
                 bad_card = 1;
             }
@@ -1271,13 +1268,13 @@ void audio_init(void)
         if (c->enabled) {
             if (c->isa) {
                 if (!isa_bus) {
-                    fprintf(stderr, "ISA bus not available for %s\n", c->name);
+                    error_report("ISA bus not available for %s", c->name);
                     exit(1);
                 }
                 c->init.init_isa(isa_bus);
             } else {
                 if (!pci_bus) {
-                    fprintf(stderr, "PCI bus not available for %s\n", c->name);
+                    error_report("PCI bus not available for %s", c->name);
                     exit(1);
                 }
                 c->init.init_pci(pci_bus);

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/spiceaudio.c

@@ -105,7 +105,7 @@ static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)
     bytes = muldiv64 (ticks, info->bytes_per_second, get_ticks_per_sec ());
     samples = (bytes - rate->bytes_sent) >> info->shift;
     if (samples < 0 || samples > 65536) {
-        fprintf (stderr, "Resetting rate control (%" PRId64 " samples)\n", samples);
+        error_report("Resetting rate control (%" PRId64 " samples)", samples);
         rate_start (rate);
         samples = 0;
     }

audio/wavcapture.c

@@ -63,8 +63,7 @@ static void wav_destroy (void *opaque)
         }
     doclose:
         if (fclose (wav->f)) {
-            fprintf (stderr, "wav_destroy: fclose failed: %s",
-                     strerror (errno));
+            error_report("wav_destroy: fclose failed: %s", strerror(errno));
         }
     }
 

block-migration.c

@@ -59,6 +59,7 @@ typedef struct BlkMigDevState {
     unsigned long *aio_bitmap;
     int64_t completed_sectors;
     BdrvDirtyBitmap *dirty_bitmap;
+    Error *blocker;
 } BlkMigDevState;
 
 typedef struct BlkMigBlock {
@@ -361,7 +362,8 @@ static void init_blk_migration_it(void *opaque, BlockDriverState *bs)
         bmds->completed_sectors = 0;
         bmds->shared_base = block_mig_state.shared_base;
         alloc_aio_bitmap(bmds);
-        bdrv_set_in_use(bs, 1);
+        error_setg(&bmds->blocker, "block device is in use by migration");
+        bdrv_op_block_all(bs, bmds->blocker);
         bdrv_ref(bs);
 
         block_mig_state.total_sector_sum += sectors;
@@ -599,7 +601,8 @@ static void blk_mig_cleanup(void)
     blk_mig_lock();
     while ((bmds = QSIMPLEQ_FIRST(&block_mig_state.bmds_list)) != NULL) {
         QSIMPLEQ_REMOVE_HEAD(&block_mig_state.bmds_list, entry);
-        bdrv_set_in_use(bmds->bs, 0);
+        bdrv_op_unblock_all(bmds->bs, bmds->blocker);
+        error_free(bmds->blocker);
         bdrv_unref(bmds->bs);
         g_free(bmds->aio_bitmap);
         g_free(bmds);
@@ -626,6 +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();
@@ -635,8 +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

@@ -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,
@@ -335,6 +336,7 @@ void bdrv_register(BlockDriver *bdrv)
 BlockDriverState *bdrv_new(const char *device_name, Error **errp)
 {
     BlockDriverState *bs;
+    int i;
 
     if (bdrv_find(device_name)) {
         error_setg(errp, "Device with id '%s' already exists",
@@ -353,12 +355,16 @@ BlockDriverState *bdrv_new(const char *device_name, Error **errp)
     if (device_name[0] != '\0') {
         QTAILQ_INSERT_TAIL(&bdrv_states, bs, device_list);
     }
+    for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
+        QLIST_INIT(&bs->op_blockers[i]);
+    }
     bdrv_iostatus_disable(bs);
     notifier_list_init(&bs->close_notifiers);
     notifier_with_return_list_init(&bs->before_write_notifiers);
     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;
 }
@@ -1090,6 +1096,37 @@ fail:
     return ret;
 }
 
+void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd)
+{
+
+    if (bs->backing_hd) {
+        assert(bs->backing_blocker);
+        bdrv_op_unblock_all(bs->backing_hd, bs->backing_blocker);
+    } else if (backing_hd) {
+        error_setg(&bs->backing_blocker,
+                   "device is used as backing hd of '%s'",
+                   bs->device_name);
+    }
+
+    bs->backing_hd = backing_hd;
+    if (!backing_hd) {
+        error_free(bs->backing_blocker);
+        bs->backing_blocker = NULL;
+        goto out;
+    }
+    bs->open_flags &= ~BDRV_O_NO_BACKING;
+    pstrcpy(bs->backing_file, sizeof(bs->backing_file), backing_hd->filename);
+    pstrcpy(bs->backing_format, sizeof(bs->backing_format),
+            backing_hd->drv ? backing_hd->drv->format_name : "");
+
+    bdrv_op_block_all(bs->backing_hd, bs->backing_blocker);
+    /* Otherwise we won't be able to commit due to check in bdrv_commit */
+    bdrv_op_unblock(bs->backing_hd, BLOCK_OP_TYPE_COMMIT,
+                    bs->backing_blocker);
+out:
+    bdrv_refresh_limits(bs);
+}
+
 /*
  * Opens the backing file for a BlockDriverState if not yet open
  *
@@ -1103,6 +1140,7 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
     char *backing_filename = g_malloc0(PATH_MAX);
     int ret = 0;
     BlockDriver *back_drv = NULL;
+    BlockDriverState *backing_hd;
     Error *local_err = NULL;
 
     if (bs->backing_hd != NULL) {
@@ -1125,30 +1163,26 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
         bdrv_get_full_backing_filename(bs, backing_filename, PATH_MAX);
     }
 
+    backing_hd = bdrv_new("", errp);
+
     if (bs->backing_format[0] != '\0') {
         back_drv = bdrv_find_format(bs->backing_format);
     }
 
     assert(bs->backing_hd == NULL);
-    ret = bdrv_open(&bs->backing_hd,
+    ret = bdrv_open(&backing_hd,
                     *backing_filename ? backing_filename : NULL, NULL, options,
                     bdrv_backing_flags(bs->open_flags), back_drv, &local_err);
     if (ret < 0) {
-        bs->backing_hd = NULL;
+        bdrv_unref(backing_hd);
+        backing_hd = NULL;
         bs->open_flags |= BDRV_O_NO_BACKING;
         error_setg(errp, "Could not open backing file: %s",
                    error_get_pretty(local_err));
         error_free(local_err);
         goto free_exit;
     }
-
-    if (bs->backing_hd->file) {
-        pstrcpy(bs->backing_file, sizeof(bs->backing_file),
-                bs->backing_hd->file->filename);
-    }
-
-    /* Recalculate the BlockLimits with the backing file */
-    bdrv_refresh_limits(bs);
+    bdrv_set_backing_hd(bs, backing_hd);
 
 free_exit:
     g_free(backing_filename);
@@ -1196,6 +1230,7 @@ int bdrv_open_image(BlockDriverState **pbs, const char *filename,
                        bdref_key);
             ret = -EINVAL;
         }
+        QDECREF(image_options);
         goto done;
     }
 
@@ -1274,6 +1309,33 @@ out:
     g_free(tmp_filename);
 }
 
+static QDict *parse_json_filename(const char *filename, Error **errp)
+{
+    QObject *options_obj;
+    QDict *options;
+    int ret;
+
+    ret = strstart(filename, "json:", &filename);
+    assert(ret);
+
+    options_obj = qobject_from_json(filename);
+    if (!options_obj) {
+        error_setg(errp, "Could not parse the JSON options");
+        return NULL;
+    }
+
+    if (qobject_type(options_obj) != QTYPE_QDICT) {
+        qobject_decref(options_obj);
+        error_setg(errp, "Invalid JSON object given");
+        return NULL;
+    }
+
+    options = qobject_to_qdict(options_obj);
+    qdict_flatten(options);
+
+    return options;
+}
+
 /*
  * Opens a disk image (raw, qcow2, vmdk, ...)
  *
@@ -1337,6 +1399,20 @@ int bdrv_open(BlockDriverState **pbs, const char *filename,
         options = qdict_new();
     }
 
+    if (filename && g_str_has_prefix(filename, "json:")) {
+        QDict *json_options = parse_json_filename(filename, &local_err);
+        if (local_err) {
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        /* Options given in the filename have lower priority than options
+         * specified directly */
+        qdict_join(options, json_options, false);
+        QDECREF(json_options);
+        filename = NULL;
+    }
+
     bs->options = options;
     options = qdict_clone_shallow(options);
 
@@ -1743,8 +1819,9 @@ void bdrv_close(BlockDriverState *bs)
 
     if (bs->drv) {
         if (bs->backing_hd) {
-            bdrv_unref(bs->backing_hd);
-            bs->backing_hd = NULL;
+            BlockDriverState *backing_hd = bs->backing_hd;
+            bdrv_set_backing_hd(bs, NULL);
+            bdrv_unref(backing_hd);
         }
         bs->drv->bdrv_close(bs);
         g_free(bs->opaque);
@@ -1781,7 +1858,11 @@ 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);
     }
 }
 
@@ -1806,17 +1887,6 @@ 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
  *
@@ -1836,12 +1906,20 @@ 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;
+        }
     }
 }
 
@@ -1904,13 +1982,14 @@ static void bdrv_move_feature_fields(BlockDriverState *bs_dest,
     bs_dest->refcnt             = bs_src->refcnt;
 
     /* job */
-    bs_dest->in_use             = bs_src->in_use;
     bs_dest->job                = bs_src->job;
 
     /* keep the same entry in bdrv_states */
     pstrcpy(bs_dest->device_name, sizeof(bs_dest->device_name),
             bs_src->device_name);
     bs_dest->device_list = bs_src->device_list;
+    memcpy(bs_dest->op_blockers, bs_src->op_blockers,
+           sizeof(bs_dest->op_blockers));
 }
 
 /*
@@ -1945,7 +2024,6 @@ void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old)
     assert(QLIST_EMPTY(&bs_new->dirty_bitmaps));
     assert(bs_new->job == NULL);
     assert(bs_new->dev == NULL);
-    assert(bs_new->in_use == 0);
     assert(bs_new->io_limits_enabled == false);
     assert(!throttle_have_timer(&bs_new->throttle_state));
 
@@ -1964,7 +2042,6 @@ void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old)
     /* Check a few fields that should remain attached to the device */
     assert(bs_new->dev == NULL);
     assert(bs_new->job == NULL);
-    assert(bs_new->in_use == 0);
     assert(bs_new->io_limits_enabled == false);
     assert(!throttle_have_timer(&bs_new->throttle_state));
 
@@ -1997,19 +2074,14 @@ void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top)
 
     /* The contents of 'tmp' will become bs_top, as we are
      * swapping bs_new and bs_top contents. */
-    bs_top->backing_hd = bs_new;
-    bs_top->open_flags &= ~BDRV_O_NO_BACKING;
-    pstrcpy(bs_top->backing_file, sizeof(bs_top->backing_file),
-            bs_new->filename);
-    pstrcpy(bs_top->backing_format, sizeof(bs_top->backing_format),
-            bs_new->drv ? bs_new->drv->format_name : "");
+    bdrv_set_backing_hd(bs_top, bs_new);
 }
 
 static void bdrv_delete(BlockDriverState *bs)
 {
     assert(!bs->dev);
     assert(!bs->job);
-    assert(!bs->in_use);
+    assert(bdrv_op_blocker_is_empty(bs));
     assert(!bs->refcnt);
     assert(QLIST_EMPTY(&bs->dirty_bitmaps));
 
@@ -2191,7 +2263,8 @@ int bdrv_commit(BlockDriverState *bs)
         return -ENOTSUP;
     }
 
-    if (bdrv_in_use(bs) || bdrv_in_use(bs->backing_hd)) {
+    if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT, NULL) ||
+        bdrv_op_is_blocked(bs->backing_hd, BLOCK_OP_TYPE_COMMIT, NULL)) {
         return -EBUSY;
     }
 
@@ -2282,12 +2355,17 @@ 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;
 }
@@ -2595,13 +2673,11 @@ int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top,
     if (ret) {
         goto exit;
     }
-    new_top_bs->backing_hd = base_bs;
-
-    bdrv_refresh_limits(new_top_bs);
+    bdrv_set_backing_hd(new_top_bs, base_bs);
 
     QSIMPLEQ_FOREACH_SAFE(intermediate_state, &states_to_delete, entry, next) {
         /* so that bdrv_close() does not recursively close the chain */
-        intermediate_state->bs->backing_hd = NULL;
+        bdrv_set_backing_hd(intermediate_state->bs, NULL);
         bdrv_unref(intermediate_state->bs);
     }
     ret = 0;
@@ -2707,10 +2783,12 @@ 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;
@@ -3248,6 +3326,15 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
 
     ret = notifier_with_return_list_notify(&bs->before_write_notifiers, req);
 
+    if (!ret && bs->detect_zeroes != BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF &&
+        !(flags & BDRV_REQ_ZERO_WRITE) && drv->bdrv_co_write_zeroes &&
+        qemu_iovec_is_zero(qiov)) {
+        flags |= BDRV_REQ_ZERO_WRITE;
+        if (bs->detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP) {
+            flags |= BDRV_REQ_MAY_UNMAP;
+        }
+    }
+
     if (ret < 0) {
         /* Do nothing, write notifier decided to fail this request */
     } else if (flags & BDRV_REQ_ZERO_WRITE) {
@@ -3444,8 +3531,9 @@ int bdrv_truncate(BlockDriverState *bs, int64_t offset)
         return -ENOTSUP;
     if (bs->read_only)
         return -EACCES;
-    if (bdrv_in_use(bs))
+    if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_RESIZE, NULL)) {
         return -EBUSY;
+    }
     ret = drv->bdrv_truncate(bs, offset);
     if (ret == 0) {
         ret = refresh_total_sectors(bs, offset >> BDRV_SECTOR_BITS);
@@ -3753,10 +3841,15 @@ 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;
@@ -3864,7 +3957,7 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
 
     if (!bs->drv->bdrv_co_get_block_status) {
         *pnum = nb_sectors;
-        ret = BDRV_BLOCK_DATA;
+        ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED;
         if (bs->drv->protocol_name) {
             ret |= BDRV_BLOCK_OFFSET_VALID | (sector_num * BDRV_SECTOR_SIZE);
         }
@@ -3883,6 +3976,10 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
                                      *pnum, pnum);
     }
 
+    if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) {
+        ret |= BDRV_BLOCK_ALLOCATED;
+    }
+
     if (!(ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO)) {
         if (bdrv_unallocated_blocks_are_zero(bs)) {
             ret |= BDRV_BLOCK_ZERO;
@@ -3943,10 +4040,12 @@ 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;
@@ -3959,9 +4058,7 @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num,
     if (ret < 0) {
         return ret;
     }
-    return
-        (ret & BDRV_BLOCK_DATA) ||
-        ((ret & BDRV_BLOCK_ZERO) && !bdrv_has_zero_init(bs));
+    return (ret & BDRV_BLOCK_ALLOCATED);
 }
 
 /*
@@ -4541,7 +4638,7 @@ 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);
@@ -4580,13 +4677,14 @@ 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);
     }
 }
 
@@ -4623,7 +4721,7 @@ 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);
 }
 
@@ -4659,7 +4757,7 @@ 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);
 }
 
@@ -4686,7 +4784,7 @@ 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);
 }
 
@@ -4897,7 +4995,11 @@ 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;
@@ -4910,7 +5012,11 @@ 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);
     }
 }
 
@@ -4926,10 +5032,12 @@ 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);
         }
     }
 
@@ -5039,10 +5147,12 @@ 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);
         }
     }
 
@@ -5273,15 +5383,74 @@ void bdrv_unref(BlockDriverState *bs)
     }
 }
 
-void bdrv_set_in_use(BlockDriverState *bs, int in_use)
+struct BdrvOpBlocker {
+    Error *reason;
+    QLIST_ENTRY(BdrvOpBlocker) list;
+};
+
+bool bdrv_op_is_blocked(BlockDriverState *bs, BlockOpType op, Error **errp)
 {
-    assert(bs->in_use != in_use);
-    bs->in_use = in_use;
+    BdrvOpBlocker *blocker;
+    assert((int) op >= 0 && op < BLOCK_OP_TYPE_MAX);
+    if (!QLIST_EMPTY(&bs->op_blockers[op])) {
+        blocker = QLIST_FIRST(&bs->op_blockers[op]);
+        if (errp) {
+            error_setg(errp, "Device '%s' is busy: %s",
+                       bs->device_name, error_get_pretty(blocker->reason));
+        }
+        return true;
+    }
+    return false;
 }
 
-int bdrv_in_use(BlockDriverState *bs)
+void bdrv_op_block(BlockDriverState *bs, BlockOpType op, Error *reason)
 {
-    return bs->in_use;
+    BdrvOpBlocker *blocker;
+    assert((int) op >= 0 && op < BLOCK_OP_TYPE_MAX);
+
+    blocker = g_malloc0(sizeof(BdrvOpBlocker));
+    blocker->reason = reason;
+    QLIST_INSERT_HEAD(&bs->op_blockers[op], blocker, list);
+}
+
+void bdrv_op_unblock(BlockDriverState *bs, BlockOpType op, Error *reason)
+{
+    BdrvOpBlocker *blocker, *next;
+    assert((int) op >= 0 && op < BLOCK_OP_TYPE_MAX);
+    QLIST_FOREACH_SAFE(blocker, &bs->op_blockers[op], list, next) {
+        if (blocker->reason == reason) {
+            QLIST_REMOVE(blocker, list);
+            g_free(blocker);
+        }
+    }
+}
+
+void bdrv_op_block_all(BlockDriverState *bs, Error *reason)
+{
+    int i;
+    for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
+        bdrv_op_block(bs, i, reason);
+    }
+}
+
+void bdrv_op_unblock_all(BlockDriverState *bs, Error *reason)
+{
+    int i;
+    for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
+        bdrv_op_unblock(bs, i, reason);
+    }
+}
+
+bool bdrv_op_blocker_is_empty(BlockDriverState *bs)
+{
+    int i;
+
+    for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
+        if (!QLIST_EMPTY(&bs->op_blockers[i])) {
+            return false;
+        }
+    }
+    return true;
 }
 
 void bdrv_iostatus_enable(BlockDriverState *bs)
@@ -5494,8 +5663,66 @@ 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,

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/curl.c

@@ -23,6 +23,7 @@
  */
 #include "qemu-common.h"
 #include "block/block_int.h"
+#include "qapi/qmp/qbool.h"
 #include <curl/curl.h>
 
 // #define DEBUG
@@ -37,6 +38,21 @@
 #if LIBCURL_VERSION_NUM >= 0x071000
 /* The multi interface timer callback was introduced in 7.16.0 */
 #define NEED_CURL_TIMER_CALLBACK
+#define HAVE_SOCKET_ACTION
+#endif
+
+#ifndef HAVE_SOCKET_ACTION
+/* If curl_multi_socket_action isn't available, define it statically here in
+ * terms of curl_multi_socket. Note that ev_bitmask will be ignored, which is
+ * less efficient but still safe. */
+static CURLMcode __curl_multi_socket_action(CURLM *multi_handle,
+                                            curl_socket_t sockfd,
+                                            int ev_bitmask,
+                                            int *running_handles)
+{
+    return curl_multi_socket(multi_handle, sockfd, running_handles);
+}
+#define curl_multi_socket_action __curl_multi_socket_action
 #endif
 
 #define PROTOCOLS (CURLPROTO_HTTP | CURLPROTO_HTTPS | \
@@ -46,12 +62,16 @@
 #define CURL_NUM_STATES 8
 #define CURL_NUM_ACB    8
 #define SECTOR_SIZE     512
-#define READ_AHEAD_SIZE (256 * 1024)
+#define READ_AHEAD_DEFAULT (256 * 1024)
 
 #define FIND_RET_NONE   0
 #define FIND_RET_OK     1
 #define FIND_RET_WAIT   2
 
+#define CURL_BLOCK_OPT_URL       "url"
+#define CURL_BLOCK_OPT_READAHEAD "readahead"
+#define CURL_BLOCK_OPT_SSLVERIFY "sslverify"
+
 struct BDRVCURLState;
 
 typedef struct CURLAIOCB {
@@ -88,7 +108,9 @@ typedef struct BDRVCURLState {
     CURLState states[CURL_NUM_STATES];
     char *url;
     size_t readahead_size;
+    bool sslverify;
     bool accept_range;
+    AioContext *aio_context;
 } BDRVCURLState;
 
 static void curl_clean_state(CURLState *s);
@@ -113,25 +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;
     }
 
@@ -344,7 +370,7 @@ static CURLState *curl_init_state(BDRVCURLState *s)
             break;
         }
         if (!state) {
-            qemu_aio_wait();
+            aio_poll(state->s->aio_context, true);
         }
     } while(!state);
 
@@ -354,6 +380,8 @@ static CURLState *curl_init_state(BDRVCURLState *s)
             return NULL;
         }
         curl_easy_setopt(state->curl, CURLOPT_URL, s->url);
+        curl_easy_setopt(state->curl, CURLOPT_SSL_VERIFYPEER,
+                         (long) s->sslverify);
         curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, 5);
         curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION,
                          (void *)curl_read_cb);
@@ -396,43 +424,52 @@ static void curl_clean_state(CURLState *s)
 static void curl_parse_filename(const char *filename, QDict *options,
                                 Error **errp)
 {
+    qdict_put(options, CURL_BLOCK_OPT_URL, qstring_from_str(filename));
+}
 
-    #define RA_OPTSTR ":readahead="
-    char *file;
-    char *ra;
-    const char *ra_val;
-    int parse_state = 0;
+static void curl_detach_aio_context(BlockDriverState *bs)
+{
+    BDRVCURLState *s = bs->opaque;
+    int i;
 
-    file = g_strdup(filename);
-
-    /* Parse a trailing ":readahead=#:" param, if present. */
-    ra = file + strlen(file) - 1;
-    while (ra >= file) {
-        if (parse_state == 0) {
-            if (*ra == ':') {
-                parse_state++;
-            } else {
-                break;
-            }
-        } else if (parse_state == 1) {
-            if (*ra > '9' || *ra < '0') {
-                char *opt_start = ra - strlen(RA_OPTSTR) + 1;
-                if (opt_start > file &&
-                    strncmp(opt_start, RA_OPTSTR, strlen(RA_OPTSTR)) == 0) {
-                    ra_val = ra + 1;
-                    ra -= strlen(RA_OPTSTR) - 1;
-                    *ra = '\0';
-                    qdict_put(options, "readahead", qstring_from_str(ra_val));
-                }
-                break;
-            }
+    for (i = 0; i < CURL_NUM_STATES; i++) {
+        if (s->states[i].in_use) {
+            curl_clean_state(&s->states[i]);
         }
-        ra--;
+        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);
+        s->multi = NULL;
     }
 
-    qdict_put(options, "url", qstring_from_str(file));
+    timer_del(&s->timer);
+}
 
-    g_free(file);
+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 = {
@@ -440,15 +477,20 @@ static QemuOptsList runtime_opts = {
     .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
     .desc = {
         {
-            .name = "url",
+            .name = CURL_BLOCK_OPT_URL,
             .type = QEMU_OPT_STRING,
             .help = "URL to open",
         },
         {
-            .name = "readahead",
+            .name = CURL_BLOCK_OPT_READAHEAD,
             .type = QEMU_OPT_SIZE,
             .help = "Readahead size",
         },
+        {
+            .name = CURL_BLOCK_OPT_SSLVERIFY,
+            .type = QEMU_OPT_BOOL,
+            .help = "Verify SSL certificate"
+        },
         { /* end of list */ }
     },
 };
@@ -477,14 +519,17 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
         goto out_noclean;
     }
 
-    s->readahead_size = qemu_opt_get_size(opts, "readahead", READ_AHEAD_SIZE);
+    s->readahead_size = qemu_opt_get_size(opts, CURL_BLOCK_OPT_READAHEAD,
+                                          READ_AHEAD_DEFAULT);
     if ((s->readahead_size & 0x1ff) != 0) {
         error_setg(errp, "HTTP_READAHEAD_SIZE %zd is not a multiple of 512",
                    s->readahead_size);
         goto out_noclean;
     }
 
-    file = qemu_opt_get(opts, "url");
+    s->sslverify = qemu_opt_get_bool(opts, CURL_BLOCK_OPT_SSLVERIFY, true);
+
+    file = qemu_opt_get(opts, CURL_BLOCK_OPT_URL);
     if (file == NULL) {
         error_setg(errp, "curl block driver requires an 'url' option");
         goto out_noclean;
@@ -496,6 +541,7 @@ 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)
@@ -528,19 +574,7 @@ 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;
@@ -635,7 +669,7 @@ 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;
 }
@@ -643,25 +677,9 @@ 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);
 }
@@ -673,68 +691,83 @@ 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) {
@@ -549,6 +551,7 @@ 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 +608,7 @@ 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 +637,7 @@ 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) {

block/iscsi.c

@@ -49,6 +49,7 @@
 
 typedef struct IscsiLun {
     struct iscsi_context *iscsi;
+    AioContext *aio_context;
     int lun;
     enum scsi_inquiry_peripheral_device_type type;
     int block_size;
@@ -73,6 +74,7 @@ typedef struct IscsiTask {
     struct scsi_task *task;
     Coroutine *co;
     QEMUBH *bh;
+    IscsiLun *iscsilun;
 } IscsiTask;
 
 typedef struct IscsiAIOCB {
@@ -133,7 +135,7 @@ 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);
 }
 
@@ -169,7 +171,8 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
 
 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);
     }
 }
@@ -177,8 +180,9 @@ out:
 static void iscsi_co_init_iscsitask(IscsiLun *iscsilun, struct IscsiTask *iTask)
 {
     *iTask = (struct IscsiTask) {
-        .co         = qemu_coroutine_self(),
-        .retries    = ISCSI_CMD_RETRIES,
+        .co             = qemu_coroutine_self(),
+        .retries        = ISCSI_CMD_RETRIES,
+        .iscsilun       = iscsilun,
     };
 }
 
@@ -209,7 +213,7 @@ 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 +236,11 @@ 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);
 
     }
 
@@ -381,6 +386,7 @@ retry:
 }
 
 
+#if defined(LIBISCSI_FEATURE_IOVECTOR)
 static bool iscsi_allocationmap_is_allocated(IscsiLun *iscsilun,
                                              int64_t sector_num, int nb_sectors)
 {
@@ -393,9 +399,6 @@ static bool iscsi_allocationmap_is_allocated(IscsiLun *iscsilun,
                            sector_num / iscsilun->cluster_sectors) == size);
 }
 
-
-#if defined(LIBISCSI_FEATURE_IOVECTOR)
-
 static int64_t coroutine_fn iscsi_co_get_block_status(BlockDriverState *bs,
                                                   int64_t sector_num,
                                                   int nb_sectors, int *pnum)
@@ -793,7 +796,7 @@ 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;
@@ -1197,6 +1200,40 @@ 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);
+
+#if defined(LIBISCSI_FEATURE_NOP_COUNTER)
+    /* 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);
+#endif
+}
+
 /*
  * We support iscsi url's on the form
  * iscsi://[<username>%<password>@]<host>[:<port>]/<targetname>/<lun>
@@ -1303,6 +1340,7 @@ 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;
 
@@ -1376,11 +1414,7 @@ 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
@@ -1424,11 +1458,7 @@ 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);
@@ -1532,10 +1562,7 @@ 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;
@@ -1606,6 +1633,9 @@ 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

@@ -498,7 +498,7 @@ immediate_exit:
             /* drop the bs loop chain formed by the swap: break the loop then
              * trigger the unref from the top one */
             BlockDriverState *p = s->base->backing_hd;
-            s->base->backing_hd = NULL;
+            bdrv_set_backing_hd(s->base, NULL);
             bdrv_unref(p);
         }
     }

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;
@@ -84,7 +87,8 @@ 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,
     };
 }
 
@@ -116,7 +120,8 @@ 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);
     }
 }
@@ -224,13 +229,34 @@ 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 +371,8 @@ 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) {
@@ -368,6 +396,8 @@ static int nfs_file_create(const char *url, QEMUOptionParameter *options,
     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")) {
@@ -407,7 +437,7 @@ 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 +450,25 @@ 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/qapi.c

@@ -50,6 +50,7 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs)
     }
 
     info->backing_file_depth = bdrv_get_backing_file_depth(bs);
+    info->detect_zeroes = bs->detect_zeroes;
 
     if (bs->io_limits_enabled) {
         ThrottleConfig cfg;
@@ -474,6 +475,7 @@ static void dump_qobject(fprintf_function func_fprintf, void *f,
         case QTYPE_QERROR: {
             QString *value = qerror_human((QError *)obj);
             func_fprintf(f, "%s", qstring_get_str(value));
+            QDECREF(value);
             break;
         }
         case QTYPE_NONE:

block/qcow.c

@@ -48,9 +48,10 @@ typedef struct QCowHeader {
     uint64_t size; /* in bytes */
     uint8_t cluster_bits;
     uint8_t l2_bits;
+    uint16_t padding;
     uint32_t crypt_method;
     uint64_t l1_table_offset;
-} QCowHeader;
+} QEMU_PACKED QCowHeader;
 
 #define L2_CACHE_SIZE 16
 
@@ -60,7 +61,7 @@ typedef struct BDRVQcowState {
     int cluster_sectors;
     int l2_bits;
     int l2_size;
-    int l1_size;
+    unsigned int l1_size;
     uint64_t cluster_offset_mask;
     uint64_t l1_table_offset;
     uint64_t *l1_table;
@@ -96,7 +97,8 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
                      Error **errp)
 {
     BDRVQcowState *s = bs->opaque;
-    int len, i, shift, ret;
+    unsigned int len, i, shift;
+    int ret;
     QCowHeader header;
 
     ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
@@ -127,11 +129,25 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    if (header.size <= 1 || header.cluster_bits < 9) {
-        error_setg(errp, "invalid value in qcow header");
+    if (header.size <= 1) {
+        error_setg(errp, "Image size is too small (must be at least 2 bytes)");
         ret = -EINVAL;
         goto fail;
     }
+    if (header.cluster_bits < 9 || header.cluster_bits > 16) {
+        error_setg(errp, "Cluster size must be between 512 and 64k");
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    /* l2_bits specifies number of entries; storing a uint64_t in each entry,
+     * so bytes = num_entries << 3. */
+    if (header.l2_bits < 9 - 3 || header.l2_bits > 16 - 3) {
+        error_setg(errp, "L2 table size must be between 512 and 64k");
+        ret = -EINVAL;
+        goto fail;
+    }
+
     if (header.crypt_method > QCOW_CRYPT_AES) {
         error_setg(errp, "invalid encryption method in qcow header");
         ret = -EINVAL;
@@ -151,7 +167,19 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
 
     /* read the level 1 table */
     shift = s->cluster_bits + s->l2_bits;
-    s->l1_size = (header.size + (1LL << shift) - 1) >> shift;
+    if (header.size > UINT64_MAX - (1LL << shift)) {
+        error_setg(errp, "Image too large");
+        ret = -EINVAL;
+        goto fail;
+    } else {
+        uint64_t l1_size = (header.size + (1LL << shift) - 1) >> shift;
+        if (l1_size > INT_MAX / sizeof(uint64_t)) {
+            error_setg(errp, "Image too large");
+            ret = -EINVAL;
+            goto fail;
+        }
+        s->l1_size = l1_size;
+    }
 
     s->l1_table_offset = header.l1_table_offset;
     s->l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
@@ -175,7 +203,9 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     if (header.backing_file_offset != 0) {
         len = header.backing_file_size;
         if (len > 1023) {
-            len = 1023;
+            error_setg(errp, "Backing file name too long");
+            ret = -EINVAL;
+            goto fail;
         }
         ret = bdrv_pread(bs->file, header.backing_file_offset,
                    bs->backing_file, len);

block/qcow2-cluster.c

@@ -379,7 +379,8 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,
     BLKDBG_EVENT(bs->file, BLKDBG_COW_READ);
 
     if (!bs->drv) {
-        return -ENOMEDIUM;
+        ret = -ENOMEDIUM;
+        goto out;
     }
 
     /* Call .bdrv_co_readv() directly instead of using the public block-layer

block/qcow2.c

@@ -1308,6 +1308,7 @@ static void qcow2_invalidate_cache(BlockDriverState *bs, Error **errp)
     options = qdict_clone_shallow(bs->options);
 
     ret = qcow2_open(bs, options, flags, &local_err);
+    QDECREF(options);
     if (local_err) {
         error_setg(errp, "Could not reopen qcow2 layer: %s",
                    error_get_pretty(local_err));
@@ -1318,8 +1319,6 @@ static void qcow2_invalidate_cache(BlockDriverState *bs, Error **errp)
         return;
     }
 
-    QDECREF(options);
-
     if (crypt_method) {
         s->crypt_method = crypt_method;
         memcpy(&s->aes_encrypt_key, &aes_encrypt_key, sizeof(aes_encrypt_key));

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);
@@ -919,7 +939,8 @@ 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
@@ -1644,6 +1665,8 @@ 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/quorum.c

@@ -848,25 +848,49 @@ 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;
@@ -1192,7 +1225,7 @@ again:
         if (size == 0)
 #endif
 #if defined(__APPLE__) && defined(__MACH__)
-        size = LONG_LONG_MAX;
+        size = LLONG_MAX;
 #else
         size = lseek(fd, 0LL, SEEK_END);
 #endif
@@ -1478,6 +1511,9 @@ static BlockDriver bdrv_file = {
     .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,
+
     .create_options = raw_create_options,
 };
 
@@ -1878,6 +1914,9 @@ 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,
@@ -2020,6 +2059,9 @@ 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,
@@ -2145,6 +2187,9 @@ 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,
@@ -2276,6 +2321,9 @@ 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 +2331,6 @@ 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);
@@ -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/rbd.c

@@ -105,7 +105,7 @@ typedef struct BDRVRBDState {
 static int qemu_rbd_next_tok(char *dst, int dst_len,
                              char *src, char delim,
                              const char *name,
-                             char **p)
+                             char **p, Error **errp)
 {
     int l;
     char *end;
@@ -128,10 +128,10 @@ static int qemu_rbd_next_tok(char *dst, int dst_len,
     }
     l = strlen(src);
     if (l >= dst_len) {
-        error_report("%s too long", name);
+        error_setg(errp, "%s too long", name);
         return -EINVAL;
     } else if (l == 0) {
-        error_report("%s too short", name);
+        error_setg(errp, "%s too short", name);
         return -EINVAL;
     }
 
@@ -157,13 +157,15 @@ static int qemu_rbd_parsename(const char *filename,
                               char *pool, int pool_len,
                               char *snap, int snap_len,
                               char *name, int name_len,
-                              char *conf, int conf_len)
+                              char *conf, int conf_len,
+                              Error **errp)
 {
     const char *start;
     char *p, *buf;
     int ret;
 
     if (!strstart(filename, "rbd:", &start)) {
+        error_setg(errp, "File name must start with 'rbd:'");
         return -EINVAL;
     }
 
@@ -172,7 +174,8 @@ static int qemu_rbd_parsename(const char *filename,
     *snap = '\0';
     *conf = '\0';
 
-    ret = qemu_rbd_next_tok(pool, pool_len, p, '/', "pool name", &p);
+    ret = qemu_rbd_next_tok(pool, pool_len, p,
+                            '/', "pool name", &p, errp);
     if (ret < 0 || !p) {
         ret = -EINVAL;
         goto done;
@@ -180,21 +183,25 @@ static int qemu_rbd_parsename(const char *filename,
     qemu_rbd_unescape(pool);
 
     if (strchr(p, '@')) {
-        ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p);
+        ret = qemu_rbd_next_tok(name, name_len, p,
+                                '@', "object name", &p, errp);
         if (ret < 0) {
             goto done;
         }
-        ret = qemu_rbd_next_tok(snap, snap_len, p, ':', "snap name", &p);
+        ret = qemu_rbd_next_tok(snap, snap_len, p,
+                                ':', "snap name", &p, errp);
         qemu_rbd_unescape(snap);
     } else {
-        ret = qemu_rbd_next_tok(name, name_len, p, ':', "object name", &p);
+        ret = qemu_rbd_next_tok(name, name_len, p,
+                                ':', "object name", &p, errp);
     }
     qemu_rbd_unescape(name);
     if (ret < 0 || !p) {
         goto done;
     }
 
-    ret = qemu_rbd_next_tok(conf, conf_len, p, '\0', "configuration", &p);
+    ret = qemu_rbd_next_tok(conf, conf_len, p,
+                            '\0', "configuration", &p, errp);
 
 done:
     g_free(buf);
@@ -229,7 +236,7 @@ static char *qemu_rbd_parse_clientname(const char *conf, char *clientname)
     return NULL;
 }
 
-static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
+static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
 {
     char *p, *buf;
     char name[RBD_MAX_CONF_NAME_SIZE];
@@ -241,20 +248,20 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
 
     while (p) {
         ret = qemu_rbd_next_tok(name, sizeof(name), p,
-                                '=', "conf option name", &p);
+                                '=', "conf option name", &p, errp);
         if (ret < 0) {
             break;
         }
         qemu_rbd_unescape(name);
 
         if (!p) {
-            error_report("conf option %s has no value", name);
+            error_setg(errp, "conf option %s has no value", name);
             ret = -EINVAL;
             break;
         }
 
         ret = qemu_rbd_next_tok(value, sizeof(value), p,
-                                ':', "conf option value", &p);
+                                ':', "conf option value", &p, errp);
         if (ret < 0) {
             break;
         }
@@ -263,7 +270,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
         if (strcmp(name, "conf") == 0) {
             ret = rados_conf_read_file(cluster, value);
             if (ret < 0) {
-                error_report("error reading conf file %s", value);
+                error_setg(errp, "error reading conf file %s", value);
                 break;
             }
         } else if (strcmp(name, "id") == 0) {
@@ -271,7 +278,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
         } else {
             ret = rados_conf_set(cluster, name, value);
             if (ret < 0) {
-                error_report("invalid conf option %s", name);
+                error_setg(errp, "invalid conf option %s", name);
                 ret = -EINVAL;
                 break;
             }
@@ -285,6 +292,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
 static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options,
                            Error **errp)
 {
+    Error *local_err = NULL;
     int64_t bytes = 0;
     int64_t objsize;
     int obj_order = 0;
@@ -301,7 +309,8 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options,
     if (qemu_rbd_parsename(filename, pool, sizeof(pool),
                            snap_buf, sizeof(snap_buf),
                            name, sizeof(name),
-                           conf, sizeof(conf)) < 0) {
+                           conf, sizeof(conf), &local_err) < 0) {
+        error_propagate(errp, local_err);
         return -EINVAL;
     }
 
@@ -313,11 +322,11 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options,
             if (options->value.n) {
                 objsize = options->value.n;
                 if ((objsize - 1) & objsize) {    /* not a power of 2? */
-                    error_report("obj size needs to be power of 2");
+                    error_setg(errp, "obj size needs to be power of 2");
                     return -EINVAL;
                 }
                 if (objsize < 4096) {
-                    error_report("obj size too small");
+                    error_setg(errp, "obj size too small");
                     return -EINVAL;
                 }
                 obj_order = ffs(objsize) - 1;
@@ -328,7 +337,7 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options,
 
     clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
     if (rados_create(&cluster, clientname) < 0) {
-        error_report("error initializing");
+        error_setg(errp, "error initializing");
         return -EIO;
     }
 
@@ -338,20 +347,20 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options,
     }
 
     if (conf[0] != '\0' &&
-        qemu_rbd_set_conf(cluster, conf) < 0) {
-        error_report("error setting config options");
+        qemu_rbd_set_conf(cluster, conf, &local_err) < 0) {
         rados_shutdown(cluster);
+        error_propagate(errp, local_err);
         return -EIO;
     }
 
     if (rados_connect(cluster) < 0) {
-        error_report("error connecting");
+        error_setg(errp, "error connecting");
         rados_shutdown(cluster);
         return -EIO;
     }
 
     if (rados_ioctx_create(cluster, pool, &io_ctx) < 0) {
-        error_report("error opening pool %s", pool);
+        error_setg(errp, "error opening pool %s", pool);
         rados_shutdown(cluster);
         return -EIO;
     }
@@ -441,8 +450,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
     opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
     if (local_err) {
-        qerror_report_err(local_err);
-        error_free(local_err);
+        error_propagate(errp, local_err);
         qemu_opts_del(opts);
         return -EINVAL;
     }
@@ -452,7 +460,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
     if (qemu_rbd_parsename(filename, pool, sizeof(pool),
                            snap_buf, sizeof(snap_buf),
                            s->name, sizeof(s->name),
-                           conf, sizeof(conf)) < 0) {
+                           conf, sizeof(conf), errp) < 0) {
         r = -EINVAL;
         goto failed_opts;
     }
@@ -460,7 +468,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
     clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
     r = rados_create(&s->cluster, clientname);
     if (r < 0) {
-        error_report("error initializing");
+        error_setg(&local_err, "error initializing");
         goto failed_opts;
     }
 
@@ -488,28 +496,27 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     if (conf[0] != '\0') {
-        r = qemu_rbd_set_conf(s->cluster, conf);
+        r = qemu_rbd_set_conf(s->cluster, conf, errp);
         if (r < 0) {
-            error_report("error setting config options");
             goto failed_shutdown;
         }
     }
 
     r = rados_connect(s->cluster);
     if (r < 0) {
-        error_report("error connecting");
+        error_setg(&local_err, "error connecting");
         goto failed_shutdown;
     }
 
     r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
     if (r < 0) {
-        error_report("error opening pool %s", pool);
+        error_setg(&local_err, "error opening pool %s", pool);
         goto failed_shutdown;
     }
 
     r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
     if (r < 0) {
-        error_report("error reading header from %s", s->name);
+        error_setg(&local_err, "error reading header from %s", s->name);
         goto failed_open;
     }
 
@@ -548,7 +555,7 @@ 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);
@@ -581,7 +588,8 @@ 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);
 }
 
@@ -677,13 +685,16 @@ 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;
 }

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);
     }
 }
 
@@ -526,17 +531,16 @@ static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
     return acb;
 }
 
-static int connect_to_sdog(BDRVSheepdogState *s)
+static int connect_to_sdog(BDRVSheepdogState *s, Error **errp)
 {
     int fd;
-    Error *err = NULL;
 
     if (s->is_unix) {
-        fd = unix_connect(s->host_spec, &err);
+        fd = unix_connect(s->host_spec, errp);
     } else {
-        fd = inet_connect(s->host_spec, &err);
+        fd = inet_connect(s->host_spec, errp);
 
-        if (err == NULL) {
+        if (fd >= 0) {
             int ret = socket_set_nodelay(fd);
             if (ret < 0) {
                 error_report("%s", strerror(errno));
@@ -544,10 +548,7 @@ static int connect_to_sdog(BDRVSheepdogState *s)
         }
     }
 
-    if (err != NULL) {
-        qerror_report_err(err);
-        error_free(err);
-    } else {
+    if (fd >= 0) {
         qemu_set_nonblock(fd);
     }
 
@@ -582,6 +583,7 @@ static void restart_co_req(void *opaque)
 
 typedef struct SheepdogReqCo {
     int sockfd;
+    AioContext *aio_context;
     SheepdogReq *hdr;
     void *data;
     unsigned int *wlen;
@@ -602,14 +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)) {
@@ -634,18 +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,
@@ -660,7 +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);
         }
     }
 
@@ -668,11 +671,11 @@ 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);
+static int get_sheep_fd(BDRVSheepdogState *s, Error **errp);
 static void co_write_request(void *opaque);
 
 static AIOReq *find_pending_req(BDRVSheepdogState *s, uint64_t oid)
@@ -702,17 +705,18 @@ 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);
     }
 }
 
 static coroutine_fn void reconnect_to_sdog(void *opaque)
 {
+    Error *local_err = NULL;
     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;
 
@@ -723,9 +727,11 @@ static coroutine_fn void reconnect_to_sdog(void *opaque)
 
     /* Try to reconnect the sheepdog server every one second. */
     while (s->fd < 0) {
-        s->fd = get_sheep_fd(s);
+        s->fd = get_sheep_fd(s, &local_err);
         if (s->fd < 0) {
             DPRINTF("Wait for connection to be established\n");
+            error_report("%s", error_get_pretty(local_err));
+            error_free(local_err);
             co_aio_sleep_ns(bdrv_get_aio_context(s->bs), QEMU_CLOCK_REALTIME,
                             1000000000ULL);
         }
@@ -798,7 +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
@@ -914,16 +920,16 @@ static void co_write_request(void *opaque)
  * We cannot use this descriptor for other operations because
  * the block driver may be on waiting response from the server.
  */
-static int get_sheep_fd(BDRVSheepdogState *s)
+static int get_sheep_fd(BDRVSheepdogState *s, Error **errp)
 {
     int fd;
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, errp);
     if (fd < 0) {
         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;
 }
 
@@ -1061,7 +1067,7 @@ static int parse_vdiname(BDRVSheepdogState *s, const char *filename,
 
 static int find_vdi_name(BDRVSheepdogState *s, const char *filename,
                          uint32_t snapid, const char *tag, uint32_t *vid,
-                         bool lock)
+                         bool lock, Error **errp)
 {
     int ret, fd;
     SheepdogVdiReq hdr;
@@ -1069,7 +1075,7 @@ static int find_vdi_name(BDRVSheepdogState *s, const char *filename,
     unsigned int wlen, rlen = 0;
     char buf[SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN];
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, errp);
     if (fd < 0) {
         return fd;
     }
@@ -1093,14 +1099,15 @@ 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;
     }
 
     if (rsp->result != SD_RES_SUCCESS) {
-        error_report("cannot get vdi info, %s, %s %" PRIu32 " %s",
-                     sd_strerror(rsp->result), filename, snapid, tag);
+        error_setg(errp, "cannot get vdi info, %s, %s %" PRIu32 " %s",
+                   sd_strerror(rsp->result), filename, snapid, tag);
         if (rsp->result == SD_RES_NO_VDI) {
             ret = -ENOENT;
         } else {
@@ -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;
@@ -1244,49 +1254,59 @@ 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);
 }
 
 /* update inode with the latest state */
 static int reload_inode(BDRVSheepdogState *s, uint32_t snapid, const char *tag)
 {
+    Error *local_err = NULL;
     SheepdogInode *inode;
     int ret = 0, fd;
     uint32_t vid = 0;
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, &local_err);
     if (fd < 0) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         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);
+    ret = find_vdi_name(s, s->name, snapid, tag, &vid, false, &local_err);
     if (ret) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         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:
@@ -1310,6 +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;
@@ -1322,7 +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)) {
@@ -1340,20 +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",
@@ -1382,12 +1420,12 @@ 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);
     if (local_err) {
-        qerror_report_err(local_err);
-        error_free(local_err);
+        error_propagate(errp, local_err);
         ret = -EINVAL;
         goto out;
     }
@@ -1408,15 +1446,16 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
         ret = parse_vdiname(s, filename, vdi, &snapid, tag);
     }
     if (ret < 0) {
+        error_setg(errp, "Can't parse filename");
         goto out;
     }
-    s->fd = get_sheep_fd(s);
+    s->fd = get_sheep_fd(s, errp);
     if (s->fd < 0) {
         ret = s->fd;
         goto out;
     }
 
-    ret = find_vdi_name(s, vdi, snapid, tag, &vid, true);
+    ret = find_vdi_name(s, vdi, snapid, tag, &vid, true, errp);
     if (ret) {
         goto out;
     }
@@ -1436,19 +1475,20 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
         s->is_snapshot = true;
     }
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, errp);
     if (fd < 0) {
         ret = fd;
         goto out;
     }
 
     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);
 
     if (ret) {
+        error_setg(errp, "Can't read snapshot inode");
         goto out;
     }
 
@@ -1463,7 +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);
     }
@@ -1472,7 +1512,8 @@ out:
     return ret;
 }
 
-static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot)
+static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot,
+                        Error **errp)
 {
     SheepdogVdiReq hdr;
     SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr;
@@ -1480,7 +1521,7 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot)
     unsigned int wlen, rlen = 0;
     char buf[SD_MAX_VDI_LEN];
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, errp);
     if (fd < 0) {
         return fd;
     }
@@ -1505,16 +1546,17 @@ 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);
 
     if (ret) {
+        error_setg_errno(errp, -ret, "create failed");
         return ret;
     }
 
     if (rsp->result != SD_RES_SUCCESS) {
-        error_report("%s, %s", sd_strerror(rsp->result), s->inode.name);
+        error_setg(errp, "%s, %s", sd_strerror(rsp->result), s->inode.name);
         return -EIO;
     }
 
@@ -1525,21 +1567,18 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot)
     return 0;
 }
 
-static int sd_prealloc(const char *filename)
+static int sd_prealloc(const char *filename, Error **errp)
 {
     BlockDriverState *bs = NULL;
     uint32_t idx, max_idx;
     int64_t vdi_size;
     void *buf = g_malloc0(SD_DATA_OBJ_SIZE);
-    Error *local_err = NULL;
     int ret;
 
     ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
-                    NULL, &local_err);
+                    NULL, errp);
     if (ret < 0) {
-        qerror_report_err(local_err);
-        error_free(local_err);
-        goto out;
+        goto out_with_err_set;
     }
 
     vdi_size = bdrv_getlength(bs);
@@ -1563,7 +1602,12 @@ static int sd_prealloc(const char *filename)
             goto out;
         }
     }
+
 out:
+    if (ret < 0) {
+        error_setg_errno(errp, -ret, "Can't pre-allocate");
+    }
+out_with_err_set:
     if (bs) {
         bdrv_unref(bs);
     }
@@ -1636,7 +1680,6 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
     char tag[SD_MAX_VDI_TAG_LEN];
     uint32_t snapid;
     bool prealloc = false;
-    Error *local_err = NULL;
 
     s = g_malloc0(sizeof(BDRVSheepdogState));
 
@@ -1647,6 +1690,7 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
         ret = parse_vdiname(s, filename, s->name, &snapid, tag);
     }
     if (ret < 0) {
+        error_setg(errp, "Can't parse filename");
         goto out;
     }
 
@@ -1661,8 +1705,8 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
             } else if (!strcmp(options->value.s, "full")) {
                 prealloc = true;
             } else {
-                error_report("Invalid preallocation mode: '%s'",
-                             options->value.s);
+                error_setg(errp, "Invalid preallocation mode: '%s'",
+                           options->value.s);
                 ret = -EINVAL;
                 goto out;
             }
@@ -1670,6 +1714,8 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
             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;
                 }
             }
@@ -1678,7 +1724,7 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
     }
 
     if (s->inode.vdi_size > SD_MAX_VDI_SIZE) {
-        error_report("too big image size");
+        error_setg(errp, "too big image size");
         ret = -EINVAL;
         goto out;
     }
@@ -1691,24 +1737,22 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
         /* Currently, only Sheepdog backing image is supported. */
         drv = bdrv_find_protocol(backing_file, true);
         if (!drv || strcmp(drv->protocol_name, "sheepdog") != 0) {
-            error_report("backing_file must be a sheepdog image");
+            error_setg(errp, "backing_file must be a sheepdog image");
             ret = -EINVAL;
             goto out;
         }
 
         bs = NULL;
         ret = bdrv_open(&bs, backing_file, NULL, NULL, BDRV_O_PROTOCOL, NULL,
-                        &local_err);
+                        errp);
         if (ret < 0) {
-            qerror_report_err(local_err);
-            error_free(local_err);
             goto out;
         }
 
         base = bs->opaque;
 
         if (!is_snapshot(&base->inode)) {
-            error_report("cannot clone from a non snapshot vdi");
+            error_setg(errp, "cannot clone from a non snapshot vdi");
             bdrv_unref(bs);
             ret = -EINVAL;
             goto out;
@@ -1717,12 +1761,14 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
         bdrv_unref(bs);
     }
 
-    ret = do_sd_create(s, &vid, 0);
-    if (!prealloc || ret) {
+    ret = do_sd_create(s, &vid, 0, errp);
+    if (ret) {
         goto out;
     }
 
-    ret = sd_prealloc(filename);
+    if (prealloc) {
+        ret = sd_prealloc(filename, errp);
+    }
 out:
     g_free(s);
     return ret;
@@ -1730,6 +1776,7 @@ out:
 
 static void sd_close(BlockDriverState *bs)
 {
+    Error *local_err = NULL;
     BDRVSheepdogState *s = bs->opaque;
     SheepdogVdiReq hdr;
     SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr;
@@ -1738,8 +1785,10 @@ static void sd_close(BlockDriverState *bs)
 
     DPRINTF("%s\n", s->name);
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, &local_err);
     if (fd < 0) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         return;
     }
 
@@ -1751,7 +1800,8 @@ 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);
 
@@ -1760,7 +1810,7 @@ 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);
 }
@@ -1774,6 +1824,7 @@ static int64_t sd_getlength(BlockDriverState *bs)
 
 static int sd_truncate(BlockDriverState *bs, int64_t offset)
 {
+    Error *local_err = NULL;
     BDRVSheepdogState *s = bs->opaque;
     int ret, fd;
     unsigned int datalen;
@@ -1786,16 +1837,19 @@ static int sd_truncate(BlockDriverState *bs, int64_t offset)
         return -EINVAL;
     }
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, &local_err);
     if (fd < 0) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         return fd;
     }
 
     /* 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) {
@@ -1831,9 +1885,9 @@ 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;
@@ -1846,6 +1900,7 @@ static void coroutine_fn sd_write_done(SheepdogAIOCB *acb)
 /* Delete current working VDI on the snapshot chain */
 static bool sd_delete(BDRVSheepdogState *s)
 {
+    Error *local_err = NULL;
     unsigned int wlen = SD_MAX_VDI_LEN, rlen = 0;
     SheepdogVdiReq hdr = {
         .opcode = SD_OP_DEL_VDI,
@@ -1856,12 +1911,15 @@ static bool sd_delete(BDRVSheepdogState *s)
     SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr;
     int fd, ret;
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, &local_err);
     if (fd < 0) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         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;
@@ -1885,6 +1943,7 @@ static bool sd_delete(BDRVSheepdogState *s)
  */
 static int sd_create_branch(BDRVSheepdogState *s)
 {
+    Error *local_err = NULL;
     int ret, fd;
     uint32_t vid;
     char *buf;
@@ -1900,21 +1959,25 @@ static int sd_create_branch(BDRVSheepdogState *s)
      * false bail out.
      */
     deleted = sd_delete(s);
-    ret = do_sd_create(s, &vid, !deleted);
+    ret = do_sd_create(s, &vid, !deleted, &local_err);
     if (ret) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         goto out;
     }
 
     DPRINTF("%" PRIx32 " is created.\n", vid);
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, &local_err);
     if (fd < 0) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         ret = fd;
         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);
 
@@ -2023,7 +2086,8 @@ 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) {
@@ -2032,7 +2096,7 @@ 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;
@@ -2112,9 +2176,9 @@ 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;
@@ -2122,6 +2186,7 @@ static int coroutine_fn sd_co_flush_to_disk(BlockDriverState *bs)
 
 static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
 {
+    Error *local_err = NULL;
     BDRVSheepdogState *s = bs->opaque;
     int ret, fd;
     uint32_t new_vid;
@@ -2149,32 +2214,37 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     strncpy(s->inode.tag, sn_info->name, sizeof(s->inode.tag));
     /* we don't need to update entire object */
     datalen = SD_INODE_SIZE - sizeof(s->inode.data_vdi_id);
+    inode = g_malloc(datalen);
 
     /* refresh inode. */
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, &local_err);
     if (fd < 0) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         ret = fd;
         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;
     }
 
-    ret = do_sd_create(s, &new_vid, 1);
+    ret = do_sd_create(s, &new_vid, 1, &local_err);
     if (ret < 0) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         error_report("failed to create inode for snapshot. %s",
                      strerror(errno));
         goto cleanup;
     }
 
-    inode = (SheepdogInode *)g_malloc(datalen);
-
-    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));
@@ -2186,6 +2256,7 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
             s->inode.name, s->inode.snap_id, s->inode.vdi_id);
 
 cleanup:
+    g_free(inode);
     closesocket(fd);
     return ret;
 }
@@ -2249,6 +2320,7 @@ static int sd_snapshot_delete(BlockDriverState *bs,
 
 static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
 {
+    Error *local_err = NULL;
     BDRVSheepdogState *s = bs->opaque;
     SheepdogReq req;
     int fd, nr = 1024, ret, max = BITS_TO_LONGS(SD_NR_VDIS) * sizeof(long);
@@ -2263,8 +2335,10 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
 
     vdi_inuse = g_malloc(max);
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, &local_err);
     if (fd < 0) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         ret = fd;
         goto out;
     }
@@ -2277,7 +2351,8 @@ 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) {
@@ -2290,8 +2365,10 @@ static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
     hval = fnv_64a_buf(s->name, strlen(s->name), FNV1A_64_INIT);
     start_nr = hval & (SD_NR_VDIS - 1);
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, &local_err);
     if (fd < 0) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         ret = fd;
         goto out;
     }
@@ -2302,7 +2379,8 @@ 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);
 
@@ -2341,6 +2419,7 @@ out:
 static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data,
                                 int64_t pos, int size, int load)
 {
+    Error *local_err = NULL;
     bool create;
     int fd, ret = 0, remaining = size;
     unsigned int data_len;
@@ -2349,8 +2428,10 @@ static int do_load_save_vmstate(BDRVSheepdogState *s, uint8_t *data,
     uint32_t vdi_index;
     uint32_t vdi_id = load ? s->inode.parent_vdi_id : s->inode.vdi_id;
 
-    fd = connect_to_sdog(s);
+    fd = connect_to_sdog(s, &local_err);
     if (fd < 0) {
+        error_report("%s", error_get_pretty(local_err));;
+        error_free(local_err);
         return fd;
     }
 
@@ -2364,11 +2445,11 @@ 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);
         }
@@ -2541,6 +2622,9 @@ static BlockDriver bdrv_sheepdog = {
     .bdrv_save_vmstate  = sd_save_vmstate,
     .bdrv_load_vmstate  = sd_load_vmstate,
 
+    .bdrv_detach_aio_context = sd_detach_aio_context,
+    .bdrv_attach_aio_context = sd_attach_aio_context,
+
     .create_options = sd_create_options,
 };
 
@@ -2571,6 +2655,9 @@ static BlockDriver bdrv_sheepdog_tcp = {
     .bdrv_save_vmstate  = sd_save_vmstate,
     .bdrv_load_vmstate  = sd_load_vmstate,
 
+    .bdrv_detach_aio_context = sd_detach_aio_context,
+    .bdrv_attach_aio_context = sd_attach_aio_context,
+
     .create_options = sd_create_options,
 };
 
@@ -2601,6 +2688,9 @@ static BlockDriver bdrv_sheepdog_unix = {
     .bdrv_save_vmstate  = sd_save_vmstate,
     .bdrv_load_vmstate  = sd_load_vmstate,
 
+    .bdrv_detach_aio_context = sd_detach_aio_context,
+    .bdrv_attach_aio_context = sd_attach_aio_context,
+
     .create_options = sd_create_options,
 };
 

block/ssh.c

@@ -106,30 +106,59 @@ static void ssh_state_free(BDRVSSHState *s)
     }
 }
 
-/* Wrappers around error_report which make sure to dump as much
- * information from libssh2 as possible.
- */
-static void GCC_FMT_ATTR(2, 3)
-session_error_report(BDRVSSHState *s, const char *fs, ...)
+static void GCC_FMT_ATTR(3, 4)
+session_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
 {
     va_list args;
+    char *msg;
 
     va_start(args, fs);
-    error_vprintf(fs, args);
+    msg = g_strdup_vprintf(fs, args);
+    va_end(args);
 
-    if ((s)->session) {
+    if (s->session) {
         char *ssh_err;
         int ssh_err_code;
 
-        libssh2_session_last_error((s)->session, &ssh_err, NULL, 0);
         /* This is not an errno.  See <libssh2.h>. */
-        ssh_err_code = libssh2_session_last_errno((s)->session);
-
-        error_printf(": %s (libssh2 error code: %d)", ssh_err, ssh_err_code);
+        ssh_err_code = libssh2_session_last_error(s->session,
+                                                  &ssh_err, NULL, 0);
+        error_setg(errp, "%s: %s (libssh2 error code: %d)",
+                   msg, ssh_err, ssh_err_code);
+    } else {
+        error_setg(errp, "%s", msg);
     }
+    g_free(msg);
+}
 
+static void GCC_FMT_ATTR(3, 4)
+sftp_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
+{
+    va_list args;
+    char *msg;
+
+    va_start(args, fs);
+    msg = g_strdup_vprintf(fs, args);
     va_end(args);
-    error_printf("\n");
+
+    if (s->sftp) {
+        char *ssh_err;
+        int ssh_err_code;
+        unsigned long sftp_err_code;
+
+        /* This is not an errno.  See <libssh2.h>. */
+        ssh_err_code = libssh2_session_last_error(s->session,
+                                                  &ssh_err, NULL, 0);
+        /* See <libssh2_sftp.h>. */
+        sftp_err_code = libssh2_sftp_last_error((s)->sftp);
+
+        error_setg(errp,
+                   "%s: %s (libssh2 error code: %d, sftp error code: %lu)",
+                   msg, ssh_err, ssh_err_code, sftp_err_code);
+    } else {
+        error_setg(errp, "%s", msg);
+    }
+    g_free(msg);
 }
 
 static void GCC_FMT_ATTR(2, 3)
@@ -145,9 +174,9 @@ sftp_error_report(BDRVSSHState *s, const char *fs, ...)
         int ssh_err_code;
         unsigned long sftp_err_code;
 
-        libssh2_session_last_error((s)->session, &ssh_err, NULL, 0);
         /* This is not an errno.  See <libssh2.h>. */
-        ssh_err_code = libssh2_session_last_errno((s)->session);
+        ssh_err_code = libssh2_session_last_error(s->session,
+                                                  &ssh_err, NULL, 0);
         /* See <libssh2_sftp.h>. */
         sftp_err_code = libssh2_sftp_last_error((s)->sftp);
 
@@ -243,7 +272,7 @@ static void ssh_parse_filename(const char *filename, QDict *options,
 }
 
 static int check_host_key_knownhosts(BDRVSSHState *s,
-                                     const char *host, int port)
+                                     const char *host, int port, Error **errp)
 {
     const char *home;
     char *knh_file = NULL;
@@ -257,14 +286,15 @@ static int check_host_key_knownhosts(BDRVSSHState *s,
     hostkey = libssh2_session_hostkey(s->session, &len, &type);
     if (!hostkey) {
         ret = -EINVAL;
-        session_error_report(s, "failed to read remote host key");
+        session_error_setg(errp, s, "failed to read remote host key");
         goto out;
     }
 
     knh = libssh2_knownhost_init(s->session);
     if (!knh) {
         ret = -EINVAL;
-        session_error_report(s, "failed to initialize known hosts support");
+        session_error_setg(errp, s,
+                           "failed to initialize known hosts support");
         goto out;
     }
 
@@ -289,21 +319,23 @@ static int check_host_key_knownhosts(BDRVSSHState *s,
         break;
     case LIBSSH2_KNOWNHOST_CHECK_MISMATCH:
         ret = -EINVAL;
-        session_error_report(s, "host key does not match the one in known_hosts (found key %s)",
-                             found->key);
+        session_error_setg(errp, s,
+                      "host key does not match the one in known_hosts"
+                      " (found key %s)", found->key);
         goto out;
     case LIBSSH2_KNOWNHOST_CHECK_NOTFOUND:
         ret = -EINVAL;
-        session_error_report(s, "no host key was found in known_hosts");
+        session_error_setg(errp, s, "no host key was found in known_hosts");
         goto out;
     case LIBSSH2_KNOWNHOST_CHECK_FAILURE:
         ret = -EINVAL;
-        session_error_report(s, "failure matching the host key with known_hosts");
+        session_error_setg(errp, s,
+                      "failure matching the host key with known_hosts");
         goto out;
     default:
         ret = -EINVAL;
-        session_error_report(s, "unknown error matching the host key with known_hosts (%d)",
-                             r);
+        session_error_setg(errp, s, "unknown error matching the host key"
+                      " with known_hosts (%d)", r);
         goto out;
     }
 
@@ -358,20 +390,20 @@ static int compare_fingerprint(const unsigned char *fingerprint, size_t len,
 
 static int
 check_host_key_hash(BDRVSSHState *s, const char *hash,
-                    int hash_type, size_t fingerprint_len)
+                    int hash_type, size_t fingerprint_len, Error **errp)
 {
     const char *fingerprint;
 
     fingerprint = libssh2_hostkey_hash(s->session, hash_type);
     if (!fingerprint) {
-        session_error_report(s, "failed to read remote host key");
+        session_error_setg(errp, s, "failed to read remote host key");
         return -EINVAL;
     }
 
     if(compare_fingerprint((unsigned char *) fingerprint, fingerprint_len,
                            hash) != 0) {
-        error_report("remote host key does not match host_key_check '%s'",
-                     hash);
+        error_setg(errp, "remote host key does not match host_key_check '%s'",
+                   hash);
         return -EPERM;
     }
 
@@ -379,7 +411,7 @@ check_host_key_hash(BDRVSSHState *s, const char *hash,
 }
 
 static int check_host_key(BDRVSSHState *s, const char *host, int port,
-                          const char *host_key_check)
+                          const char *host_key_check, Error **errp)
 {
     /* host_key_check=no */
     if (strcmp(host_key_check, "no") == 0) {
@@ -389,25 +421,25 @@ static int check_host_key(BDRVSSHState *s, const char *host, int port,
     /* host_key_check=md5:xx:yy:zz:... */
     if (strncmp(host_key_check, "md5:", 4) == 0) {
         return check_host_key_hash(s, &host_key_check[4],
-                                   LIBSSH2_HOSTKEY_HASH_MD5, 16);
+                                   LIBSSH2_HOSTKEY_HASH_MD5, 16, errp);
     }
 
     /* host_key_check=sha1:xx:yy:zz:... */
     if (strncmp(host_key_check, "sha1:", 5) == 0) {
         return check_host_key_hash(s, &host_key_check[5],
-                                   LIBSSH2_HOSTKEY_HASH_SHA1, 20);
+                                   LIBSSH2_HOSTKEY_HASH_SHA1, 20, errp);
     }
 
     /* host_key_check=yes */
     if (strcmp(host_key_check, "yes") == 0) {
-        return check_host_key_knownhosts(s, host, port);
+        return check_host_key_knownhosts(s, host, port, errp);
     }
 
-    error_report("unknown host_key_check setting (%s)", host_key_check);
+    error_setg(errp, "unknown host_key_check setting (%s)", host_key_check);
     return -EINVAL;
 }
 
-static int authenticate(BDRVSSHState *s, const char *user)
+static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
 {
     int r, ret;
     const char *userauthlist;
@@ -418,7 +450,8 @@ static int authenticate(BDRVSSHState *s, const char *user)
     userauthlist = libssh2_userauth_list(s->session, user, strlen(user));
     if (strstr(userauthlist, "publickey") == NULL) {
         ret = -EPERM;
-        error_report("remote server does not support \"publickey\" authentication");
+        error_setg(errp,
+                "remote server does not support \"publickey\" authentication");
         goto out;
     }
 
@@ -426,17 +459,18 @@ static int authenticate(BDRVSSHState *s, const char *user)
     agent = libssh2_agent_init(s->session);
     if (!agent) {
         ret = -EINVAL;
-        session_error_report(s, "failed to initialize ssh-agent support");
+        session_error_setg(errp, s, "failed to initialize ssh-agent support");
         goto out;
     }
     if (libssh2_agent_connect(agent)) {
         ret = -ECONNREFUSED;
-        session_error_report(s, "failed to connect to ssh-agent");
+        session_error_setg(errp, s, "failed to connect to ssh-agent");
         goto out;
     }
     if (libssh2_agent_list_identities(agent)) {
         ret = -EINVAL;
-        session_error_report(s, "failed requesting identities from ssh-agent");
+        session_error_setg(errp, s,
+                           "failed requesting identities from ssh-agent");
         goto out;
     }
 
@@ -447,7 +481,8 @@ static int authenticate(BDRVSSHState *s, const char *user)
         }
         if (r < 0) {
             ret = -EINVAL;
-            session_error_report(s, "failed to obtain identity from ssh-agent");
+            session_error_setg(errp, s,
+                               "failed to obtain identity from ssh-agent");
             goto out;
         }
         r = libssh2_agent_userauth(agent, user, identity);
@@ -461,8 +496,8 @@ static int authenticate(BDRVSSHState *s, const char *user)
     }
 
     ret = -EPERM;
-    error_report("failed to authenticate using publickey authentication "
-                 "and the identities held by your ssh-agent");
+    error_setg(errp, "failed to authenticate using publickey authentication "
+               "and the identities held by your ssh-agent");
 
  out:
     if (agent != NULL) {
@@ -476,10 +511,9 @@ static int authenticate(BDRVSSHState *s, const char *user)
 }
 
 static int connect_to_ssh(BDRVSSHState *s, QDict *options,
-                          int ssh_flags, int creat_mode)
+                          int ssh_flags, int creat_mode, Error **errp)
 {
     int r, ret;
-    Error *err = NULL;
     const char *host, *user, *path, *host_key_check;
     int port;
 
@@ -498,6 +532,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
     } else {
         user = g_get_user_name();
         if (!user) {
+            error_setg_errno(errp, errno, "Can't get user name");
             ret = -errno;
             goto err;
         }
@@ -514,11 +549,9 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
     s->hostport = g_strdup_printf("%s:%d", host, port);
 
     /* Open the socket and connect. */
-    s->sock = inet_connect(s->hostport, &err);
-    if (err != NULL) {
+    s->sock = inet_connect(s->hostport, errp);
+    if (s->sock < 0) {
         ret = -errno;
-        qerror_report_err(err);
-        error_free(err);
         goto err;
     }
 
@@ -526,7 +559,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
     s->session = libssh2_session_init();
     if (!s->session) {
         ret = -EINVAL;
-        session_error_report(s, "failed to initialize libssh2 session");
+        session_error_setg(errp, s, "failed to initialize libssh2 session");
         goto err;
     }
 
@@ -537,18 +570,18 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
     r = libssh2_session_handshake(s->session, s->sock);
     if (r != 0) {
         ret = -EINVAL;
-        session_error_report(s, "failed to establish SSH session");
+        session_error_setg(errp, s, "failed to establish SSH session");
         goto err;
     }
 
     /* Check the remote host's key against known_hosts. */
-    ret = check_host_key(s, host, port, host_key_check);
+    ret = check_host_key(s, host, port, host_key_check, errp);
     if (ret < 0) {
         goto err;
     }
 
     /* Authenticate. */
-    ret = authenticate(s, user);
+    ret = authenticate(s, user, errp);
     if (ret < 0) {
         goto err;
     }
@@ -556,7 +589,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
     /* Start SFTP. */
     s->sftp = libssh2_sftp_init(s->session);
     if (!s->sftp) {
-        session_error_report(s, "failed to initialize sftp handle");
+        session_error_setg(errp, s, "failed to initialize sftp handle");
         ret = -EINVAL;
         goto err;
     }
@@ -566,14 +599,14 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
             path, ssh_flags, creat_mode);
     s->sftp_handle = libssh2_sftp_open(s->sftp, path, ssh_flags, creat_mode);
     if (!s->sftp_handle) {
-        session_error_report(s, "failed to open remote file '%s'", path);
+        session_error_setg(errp, s, "failed to open remote file '%s'", path);
         ret = -EINVAL;
         goto err;
     }
 
     r = libssh2_sftp_fstat(s->sftp_handle, &s->attrs);
     if (r < 0) {
-        sftp_error_report(s, "failed to read file attributes");
+        sftp_error_setg(errp, s, "failed to read file attributes");
         return -EINVAL;
     }
 
@@ -623,7 +656,7 @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
     }
 
     /* Start up SSH. */
-    ret = connect_to_ssh(s, options, ssh_flags, 0);
+    ret = connect_to_ssh(s, options, ssh_flags, 0, errp);
     if (ret < 0) {
         goto err;
     }
@@ -655,7 +688,6 @@ static int ssh_create(const char *filename, QEMUOptionParameter *options,
                       Error **errp)
 {
     int r, ret;
-    Error *local_err = NULL;
     int64_t total_size = 0;
     QDict *uri_options = NULL;
     BDRVSSHState s;
@@ -674,17 +706,16 @@ static int ssh_create(const char *filename, QEMUOptionParameter *options,
     DPRINTF("total_size=%" PRIi64, total_size);
 
     uri_options = qdict_new();
-    r = parse_uri(filename, uri_options, &local_err);
+    r = parse_uri(filename, uri_options, errp);
     if (r < 0) {
-        qerror_report_err(local_err);
-        error_free(local_err);
         ret = r;
         goto out;
     }
 
     r = connect_to_ssh(&s, uri_options,
                        LIBSSH2_FXF_READ|LIBSSH2_FXF_WRITE|
-                       LIBSSH2_FXF_CREAT|LIBSSH2_FXF_TRUNC, 0644);
+                       LIBSSH2_FXF_CREAT|LIBSSH2_FXF_TRUNC,
+                       0644, errp);
     if (r < 0) {
         ret = r;
         goto out;
@@ -694,7 +725,7 @@ static int ssh_create(const char *filename, QEMUOptionParameter *options,
         libssh2_sftp_seek64(s.sftp_handle, total_size-1);
         r2 = libssh2_sftp_write(s.sftp_handle, c, 1);
         if (r2 < 0) {
-            sftp_error_report(&s, "truncate failed");
+            sftp_error_setg(errp, &s, "truncate failed");
             ret = -EINVAL;
             goto out;
         }
@@ -742,7 +773,7 @@ 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;
@@ -760,24 +791,26 @@ 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
@@ -807,7 +840,7 @@ 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)
 {
@@ -840,7 +873,7 @@ 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) {
@@ -875,14 +908,14 @@ 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)
 {
@@ -910,7 +943,7 @@ 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) {
@@ -929,7 +962,7 @@ 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;
         }
 
@@ -957,7 +990,7 @@ 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);
 
@@ -978,7 +1011,7 @@ 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;
 
@@ -986,7 +1019,7 @@ 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 &&
@@ -1008,7 +1041,7 @@ 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;

block/stream.c

@@ -60,7 +60,7 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
     /* Must assign before bdrv_delete() to prevent traversing dangling pointer
      * while we delete backing image instances.
      */
-    top->backing_hd = base;
+    bdrv_set_backing_hd(top, base);
 
     while (intermediate) {
         BlockDriverState *unused;
@@ -72,7 +72,7 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
 
         unused = intermediate;
         intermediate = intermediate->backing_hd;
-        unused->backing_hd = NULL;
+        bdrv_set_backing_hd(unused, NULL);
         bdrv_unref(unused);
     }
 

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);

block/vhdx.c

@@ -473,7 +473,14 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
         } else if (h2_seq > h1_seq) {
             s->curr_header = 1;
         } else {
-            goto fail;
+            /* The Microsoft Disk2VHD tool will create 2 identical
+             * headers, with identical sequence numbers.  If the headers are
+             * identical, don't consider the file corrupt */
+            if (!memcmp(header1, header2, sizeof(VHDXHeader))) {
+                s->curr_header = 0;
+            } else {
+                goto fail;
+            }
         }
     }
 

block/vmdk.c

@@ -1534,7 +1534,7 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
     int ret, i;
     BlockDriverState *bs = NULL;
     VMDK4Header header;
-    Error *local_err;
+    Error *local_err = NULL;
     uint32_t tmp, magic, grains, gd_sectors, gt_size, gt_count;
     uint32_t *gd_buf = NULL;
     int gd_buf_size;
@@ -1700,7 +1700,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
 {
     int idx = 0;
     BlockDriverState *new_bs = NULL;
-    Error *local_err;
+    Error *local_err = NULL;
     char *desc = NULL;
     int64_t total_size = 0, filesize;
     const char *adapter_type = NULL;
@@ -1881,7 +1881,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
     } else {
         ret = bdrv_create_file(filename, options, &local_err);
         if (ret < 0) {
-            error_setg_errno(errp, -ret, "Could not create image file");
+            error_propagate(errp, local_err);
             goto exit;
         }
     }
@@ -1889,7 +1889,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
     ret = bdrv_open(&new_bs, filename, NULL, NULL,
                     BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
     if (ret < 0) {
-        error_setg_errno(errp, -ret, "Could not write description");
+        error_propagate(errp, local_err);
         goto exit;
     }
     ret = bdrv_pwrite(new_bs, desc_offset, desc, desc_len);
@@ -2096,6 +2096,27 @@ static int vmdk_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
     return 0;
 }
 
+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 QEMUOptionParameter vmdk_create_options[] = {
     {
         .name = BLOCK_OPT_SIZE,
@@ -2153,6 +2174,8 @@ 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,
 };

block/vvfat.c

@@ -787,7 +787,9 @@ static int read_directory(BDRVVVFATState* s, int mapping_index)
 	    s->current_mapping->path=buffer;
 	    s->current_mapping->read_only =
 		(st.st_mode & (S_IWUSR | S_IWGRP | S_IWOTH)) == 0;
-	}
+        } else {
+            g_free(buffer);
+        }
     }
     closedir(dir);
 
@@ -831,7 +833,8 @@ static inline off_t cluster2sector(BDRVVVFATState* s, uint32_t cluster_num)
 }
 
 static int init_directories(BDRVVVFATState* s,
-                            const char *dirname, int heads, int secs)
+                            const char *dirname, int heads, int secs,
+                            Error **errp)
 {
     bootsector_t* bootsector;
     mapping_t* mapping;
@@ -892,8 +895,8 @@ static int init_directories(BDRVVVFATState* s,
         if (mapping->mode & MODE_DIRECTORY) {
 	    mapping->begin = cluster;
 	    if(read_directory(s, i)) {
-		fprintf(stderr, "Could not read directory %s\n",
-			mapping->path);
+                error_setg(errp, "Could not read directory %s",
+                           mapping->path);
 		return -1;
 	    }
 	    mapping = array_get(&(s->mapping), i);
@@ -919,9 +922,10 @@ static int init_directories(BDRVVVFATState* s,
 	cluster = mapping->end;
 
 	if(cluster > s->cluster_count) {
-	    fprintf(stderr,"Directory does not fit in FAT%d (capacity %.2f MB)\n",
-		    s->fat_type, s->sector_count / 2000.0);
-	    return -EINVAL;
+            error_setg(errp,
+                       "Directory does not fit in FAT%d (capacity %.2f MB)",
+                       s->fat_type, s->sector_count / 2000.0);
+            return -1;
 	}
 
 	/* fix fat for entry */
@@ -979,7 +983,7 @@ static int init_directories(BDRVVVFATState* s,
 static BDRVVVFATState *vvv = NULL;
 #endif
 
-static int enable_write_target(BDRVVVFATState *s);
+static int enable_write_target(BDRVVVFATState *s, Error **errp);
 static int is_consistent(BDRVVVFATState *s);
 
 static void vvfat_rebind(BlockDriverState *bs)
@@ -1160,7 +1164,7 @@ DLOG(if (stderr == NULL) {
     s->sector_count = cyls * heads * secs - (s->first_sectors_number - 1);
 
     if (qemu_opt_get_bool(opts, "rw", false)) {
-        ret = enable_write_target(s);
+        ret = enable_write_target(s, errp);
         if (ret < 0) {
             goto fail;
         }
@@ -1169,7 +1173,7 @@ DLOG(if (stderr == NULL) {
 
     bs->total_sectors = cyls * heads * secs;
 
-    if (init_directories(s, dirname, heads, secs)) {
+    if (init_directories(s, dirname, heads, secs, errp)) {
         ret = -EIO;
         goto fail;
     }
@@ -1864,7 +1868,7 @@ static int check_directory_consistency(BDRVVVFATState *s,
 
 	if (s->used_clusters[cluster_num] & USED_ANY) {
 	    fprintf(stderr, "cluster %d used more than once\n", (int)cluster_num);
-	    return 0;
+            goto fail;
 	}
 	s->used_clusters[cluster_num] = USED_DIRECTORY;
 
@@ -2904,11 +2908,10 @@ static BlockDriver vvfat_write_target = {
     .bdrv_close         = write_target_close,
 };
 
-static int enable_write_target(BDRVVVFATState *s)
+static int enable_write_target(BDRVVVFATState *s, Error **errp)
 {
     BlockDriver *bdrv_qcow;
     QEMUOptionParameter *options;
-    Error *local_err = NULL;
     int ret;
     int size = sector2cluster(s, s->sector_count);
     s->used_clusters = calloc(size, 1);
@@ -2918,6 +2921,7 @@ static int enable_write_target(BDRVVVFATState *s)
     s->qcow_filename = g_malloc(1024);
     ret = get_tmp_filename(s->qcow_filename, 1024);
     if (ret < 0) {
+        error_setg_errno(errp, -ret, "can't create temporary file");
         goto err;
     }
 
@@ -2926,20 +2930,17 @@ static int enable_write_target(BDRVVVFATState *s)
     set_option_parameter_int(options, BLOCK_OPT_SIZE, s->sector_count * 512);
     set_option_parameter(options, BLOCK_OPT_BACKING_FILE, "fat:");
 
-    ret = bdrv_create(bdrv_qcow, s->qcow_filename, options, &local_err);
+    ret = bdrv_create(bdrv_qcow, s->qcow_filename, options, errp);
+    free_option_parameters(options);
     if (ret < 0) {
-        qerror_report_err(local_err);
-        error_free(local_err);
         goto err;
     }
 
     s->qcow = NULL;
     ret = bdrv_open(&s->qcow, s->qcow_filename, NULL, NULL,
-            BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH, bdrv_qcow,
-            &local_err);
+                    BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH,
+                    bdrv_qcow, errp);
     if (ret < 0) {
-        qerror_report_err(local_err);
-        error_free(local_err);
         goto err;
     }
 
@@ -2947,7 +2948,7 @@ static int enable_write_target(BDRVVVFATState *s)
     unlink(s->qcow_filename);
 #endif
 
-    s->bs->backing_hd = bdrv_new("", &error_abort);
+    bdrv_set_backing_hd(s->bs, bdrv_new("", &error_abort));
     s->bs->backing_hd->drv = &vvfat_write_target;
     s->bs->backing_hd->opaque = g_malloc(sizeof(void*));
     *(void**)s->bs->backing_hd->opaque = s;

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-nbd.c

@@ -27,8 +27,8 @@ static void nbd_accept(void *opaque)
     socklen_t addr_len = sizeof(addr);
 
     int fd = accept(server_fd, (struct sockaddr *)&addr, &addr_len);
-    if (fd >= 0) {
-        nbd_client_new(NULL, fd, nbd_client_put);
+    if (fd >= 0 && !nbd_client_new(NULL, fd, nbd_client_put)) {
+        close(fd);
     }
 }
 

blockdev.c

@@ -34,7 +34,6 @@
 #include "hw/block/block.h"
 #include "block/blockjob.h"
 #include "monitor/monitor.h"
-#include "qapi/qmp/qerror.h"
 #include "qemu/option.h"
 #include "qemu/config-file.h"
 #include "qapi/qmp/types.h"
@@ -288,6 +287,25 @@ static int parse_block_error_action(const char *buf, bool is_read, Error **errp)
     }
 }
 
+static inline int parse_enum_option(const char *lookup[], const char *buf,
+                                    int max, int def, Error **errp)
+{
+    int i;
+
+    if (!buf) {
+        return def;
+    }
+
+    for (i = 0; i < max; i++) {
+        if (!strcmp(buf, lookup[i])) {
+            return i;
+        }
+    }
+
+    error_setg(errp, "invalid parameter value: %s", buf);
+    return def;
+}
+
 static bool check_throttle_config(ThrottleConfig *cfg, Error **errp)
 {
     if (throttle_conflicting(cfg)) {
@@ -324,6 +342,7 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     QemuOpts *opts;
     const char *id;
     bool has_driver_specific_opts;
+    BlockdevDetectZeroesOptions detect_zeroes;
     BlockDriver *drv = NULL;
 
     /* Check common options by copying from bs_opts to opts, all other options
@@ -332,7 +351,7 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
     opts = qemu_opts_create(&qemu_common_drive_opts, id, 1, &error);
     if (error) {
         error_propagate(errp, error);
-        return NULL;
+        goto err_no_opts;
     }
 
     qemu_opts_absorb_qdict(opts, bs_opts, &error);
@@ -452,6 +471,24 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts,
         }
     }
 
+    detect_zeroes =
+        parse_enum_option(BlockdevDetectZeroesOptions_lookup,
+                          qemu_opt_get(opts, "detect-zeroes"),
+                          BLOCKDEV_DETECT_ZEROES_OPTIONS_MAX,
+                          BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
+                          &error);
+    if (error) {
+        error_propagate(errp, error);
+        goto early_err;
+    }
+
+    if (detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP &&
+        !(bdrv_flags & BDRV_O_UNMAP)) {
+        error_setg(errp, "setting detect-zeroes to unmap is not allowed "
+                         "without setting discard operation to unmap");
+        goto early_err;
+    }
+
     /* init */
     dinfo = g_malloc0(sizeof(*dinfo));
     dinfo->id = g_strdup(qemu_opts_id(opts));
@@ -462,6 +499,7 @@ 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);
@@ -526,8 +564,9 @@ bdrv_new_err:
     g_free(dinfo->id);
     g_free(dinfo);
 early_err:
-    QDECREF(bs_opts);
     qemu_opts_del(opts);
+err_no_opts:
+    QDECREF(bs_opts);
     return NULL;
 }
 
@@ -691,7 +730,7 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
                                    &error_abort);
     qemu_opts_absorb_qdict(legacy_opts, bs_opts, &local_err);
     if (local_err) {
-        qerror_report_err(local_err);
+        error_report("%s", error_get_pretty(local_err));
         error_free(local_err);
         goto fail;
     }
@@ -901,9 +940,10 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
 
     /* Actual block device init: Functionality shared with blockdev-add */
     dinfo = blockdev_init(filename, bs_opts, &local_err);
+    bs_opts = NULL;
     if (dinfo == NULL) {
         if (local_err) {
-            qerror_report_err(local_err);
+            error_report("%s", error_get_pretty(local_err));
             error_free(local_err);
         }
         goto fail;
@@ -938,6 +978,7 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
 
 fail:
     qemu_opts_del(legacy_opts);
+    QDECREF(bs_opts);
     return dinfo;
 }
 
@@ -1295,8 +1336,8 @@ static void external_snapshot_prepare(BlkTransactionState *common,
         return;
     }
 
-    if (bdrv_in_use(state->old_bs)) {
-        error_set(errp, QERR_DEVICE_IN_USE, device);
+    if (bdrv_op_is_blocked(state->old_bs,
+                           BLOCK_OP_TYPE_EXTERNAL_SNAPSHOT, errp)) {
         return;
     }
 
@@ -1518,8 +1559,7 @@ exit:
 
 static void eject_device(BlockDriverState *bs, int force, Error **errp)
 {
-    if (bdrv_in_use(bs)) {
-        error_set(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
+    if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_EJECT, errp)) {
         return;
     }
     if (!bdrv_dev_has_removable_media(bs)) {
@@ -1663,6 +1703,7 @@ 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) {
@@ -1706,6 +1747,9 @@ 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)) {
@@ -1715,20 +1759,24 @@ 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)
 {
     const char *id = qdict_get_str(qdict, "id");
     BlockDriverState *bs;
+    Error *local_err = NULL;
 
     bs = bdrv_find(id);
     if (!bs) {
-        qerror_report(QERR_DEVICE_NOT_FOUND, id);
+        error_report("Device '%s' not found", id);
         return -1;
     }
-    if (bdrv_in_use(bs)) {
-        qerror_report(QERR_DEVICE_IN_USE, id);
+    if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_DRIVE_DEL, &local_err)) {
+        error_report("%s", error_get_pretty(local_err));
+        error_free(local_err);
         return -1;
     }
 
@@ -1849,6 +1897,10 @@ void qmp_block_stream(const char *device, bool has_base,
         return;
     }
 
+    if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_STREAM, errp)) {
+        return;
+    }
+
     if (base) {
         base_bs = bdrv_find_backing_image(bs, base);
         if (base_bs == NULL) {
@@ -1893,6 +1945,10 @@ void qmp_block_commit(const char *device,
         return;
     }
 
+    if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT, errp)) {
+        return;
+    }
+
     /* default top_bs is the active layer */
     top_bs = bs;
 
@@ -1984,8 +2040,7 @@ void qmp_drive_backup(const char *device, const char *target,
         }
     }
 
-    if (bdrv_in_use(bs)) {
-        error_set(errp, QERR_DEVICE_IN_USE, device);
+    if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_BACKUP_SOURCE, errp)) {
         return;
     }
 
@@ -2118,8 +2173,7 @@ void qmp_drive_mirror(const char *device, const char *target,
         }
     }
 
-    if (bdrv_in_use(bs)) {
-        error_set(errp, QERR_DEVICE_IN_USE, device);
+    if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_MIRROR, errp)) {
         return;
     }
 
@@ -2455,6 +2509,10 @@ QemuOptsList qemu_common_drive_opts = {
             .name = "copy-on-read",
             .type = QEMU_OPT_BOOL,
             .help = "copy read data from backing file into image file",
+        },{
+            .name = "detect-zeroes",
+            .type = QEMU_OPT_STRING,
+            .help = "try to optimize zero writes (off, on, unmap)",
         },
         { /* end of list */ }
     },

blockjob.c

@@ -41,14 +41,16 @@ void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
 {
     BlockJob *job;
 
-    if (bs->job || bdrv_in_use(bs)) {
+    if (bs->job) {
         error_set(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
         return NULL;
     }
     bdrv_ref(bs);
-    bdrv_set_in_use(bs, 1);
-
     job = g_malloc0(driver->instance_size);
+    error_setg(&job->blocker, "block device is in use by block job: %s",
+               BlockJobType_lookup[driver->job_type]);
+    bdrv_op_block_all(bs, job->blocker);
+
     job->driver        = driver;
     job->bs            = bs;
     job->cb            = cb;
@@ -63,8 +65,9 @@ void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
         block_job_set_speed(job, speed, &local_err);
         if (local_err) {
             bs->job = NULL;
+            bdrv_op_unblock_all(bs, job->blocker);
+            error_free(job->blocker);
             g_free(job);
-            bdrv_set_in_use(bs, 0);
             error_propagate(errp, local_err);
             return NULL;
         }
@@ -79,8 +82,9 @@ void block_job_completed(BlockJob *job, int ret)
     assert(bs->job == job);
     job->cb(job->opaque, ret);
     bs->job = NULL;
+    bdrv_op_unblock_all(bs, job->blocker);
+    error_free(job->blocker);
     g_free(job);
-    bdrv_set_in_use(bs, 0);
 }
 
 void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)

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/qemu.h

@@ -5,6 +5,7 @@
 #include <string.h>
 
 #include "cpu.h"
+#include "exec/cpu_ldst.h"
 
 #undef DEBUG_REMAP
 #ifdef DEBUG_REMAP

configure

@@ -2,26 +2,28 @@
 #
 # qemu configure script (c) 2003 Fabrice Bellard
 #
-# set temporary file name
-if test ! -z "$TMPDIR" ; then
-    TMPDIR1="${TMPDIR}"
-elif test ! -z "$TEMPDIR" ; then
-    TMPDIR1="${TEMPDIR}"
-else
-    TMPDIR1="/tmp"
+
+# 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
+# (and we need not jump through hoops to try to delete
+# it when configure exits.)
+TMPDIR1="config-temp"
+rm -rf "${TMPDIR1}"
+mkdir -p "${TMPDIR1}"
+if [ $? -ne 0 ]; then
+    echo "ERROR: failed to create temporary directory"
+    exit 1
 fi
 
-TMPC="${TMPDIR1}/qemu-conf-${RANDOM}-$$-${RANDOM}.c"
-TMPB="qemu-conf-${RANDOM}-$$-${RANDOM}"
+TMPB="qemu-conf"
+TMPC="${TMPDIR1}/${TMPB}.c"
 TMPO="${TMPDIR1}/${TMPB}.o"
 TMPCXX="${TMPDIR1}/${TMPB}.cxx"
 TMPL="${TMPDIR1}/${TMPB}.lo"
 TMPA="${TMPDIR1}/lib${TMPB}.la"
-TMPE="${TMPDIR1}/qemu-conf-${RANDOM}-$$-${RANDOM}.exe"
+TMPE="${TMPDIR1}/${TMPB}.exe"
 
-# NB: do not call "exit" in the trap handler; this is buggy with some shells;
-# see <1285349658-3122-1-git-send-email-loic.minier@linaro.org>
-trap "rm -f $TMPC $TMPO $TMPCXX $TMPE" EXIT INT QUIT TERM
 rm -f config.log
 
 # Print a helpful header at the top of config.log
@@ -180,6 +182,10 @@ path_of() {
     return 1
 }
 
+have_backend () {
+    echo "$trace_backends" | grep "$1" >/dev/null
+}
+
 # default parameters
 source_path=`dirname "$0"`
 cpu=""
@@ -291,7 +297,7 @@ pkgversion=""
 pie=""
 zero_malloc=""
 qom_cast_debug="yes"
-trace_backend="nop"
+trace_backends="nop"
 trace_file="trace"
 spice=""
 rbd=""
@@ -317,7 +323,7 @@ glusterfs_discard="no"
 glusterfs_zerofill="no"
 virtio_blk_data_plane=""
 gtk=""
-gtkabi="2.0"
+gtkabi=""
 vte=""
 tpm="no"
 libssh2=""
@@ -751,7 +757,10 @@ for opt do
   ;;
   --target-list=*) target_list="$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"
   ;;
@@ -1318,7 +1327,7 @@ 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>
@@ -1970,8 +1979,21 @@ fi
 ##########################################
 # GTK probe
 
+if test "$gtkabi" = ""; then
+    # The GTK ABI was not specified explicitly, so try whether 2.0 is available.
+    # Use 3.0 as a fallback if that is available.
+    if $pkg_config --exists "gtk+-2.0 >= 2.18.0"; then
+        gtkabi=2.0
+    elif $pkg_config --exists "gtk+-3.0 >= 3.0.0"; then
+        gtkabi=3.0
+    else
+        gtkabi=2.0
+    fi
+fi
+
 if test "$gtk" != "no"; then
     gtkpackage="gtk+-$gtkabi"
+    gtkx11package="gtk+-x11-$gtkabi"
     if test "$gtkabi" = "3.0" ; then
       gtkversion="3.0.0"
     else
@@ -1980,10 +2002,13 @@ if test "$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
-        feature_not_found "gtk" "Install gtk2 or gtk3 (requires --with-gtkabi=3.0 option to configure) devel"
+        feature_not_found "gtk" "Install gtk2 or gtk3 devel"
     else
         gtk="no"
     fi
@@ -2006,7 +2031,11 @@ if test "$vte" != "no"; then
         libs_softmmu="$vte_libs $libs_softmmu"
         vte="yes"
     elif test "$vte" = "yes"; then
-        feature_not_found "vte" "Install libvte or libvte-2.90 (requires --with-gtkabi=3.0 option to configure) devel"
+        if test "$gtkabi" = "3.0"; then
+            feature_not_found "vte" "Install libvte-2.90 devel"
+        else
+            feature_not_found "vte" "Install libvte devel"
+        fi
     else
         vte="no"
     fi
@@ -3648,15 +3677,15 @@ 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; }
@@ -3682,7 +3711,7 @@ 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 $PATH"
   fi
@@ -4029,11 +4058,14 @@ fi
 if test "$pie" = "no" ; then
   textseg_addr=
   case "$cpu" in
-    arm | hppa | i386 | m68k | ppc | ppc64 | s390* | sparc | sparc64 | x86_64 | x32)
+    arm | i386 | ppc* | s390* | sparc* | x86_64 | x32)
+      # ??? Rationale for choosing this address
       textseg_addr=0x60000000
       ;;
     mips)
-      textseg_addr=0x400000
+      # A 256M aligned address, high in the address space, with enough
+      # room for the code_gen_buffer above it before the stack.
+      textseg_addr=0x60000000
       ;;
   esac
   if [ -n "$textseg_addr" ]; then
@@ -4149,7 +4181,7 @@ 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 $trace_file-<pid>"
 fi
@@ -4643,43 +4675,35 @@ if test "$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
@@ -5219,3 +5243,4 @@ printf " '%s'" "$0" "$@" >>config.status
 echo >>config.status
 chmod +x config.status
 
+rm -r "$TMPDIR1"

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/s390x-softmmu.mak

@@ -1,3 +1,4 @@
 CONFIG_VIRTIO=y
 CONFIG_SCLPCONSOLE=y
-CONFIG_S390_FLIC=$(CONFIG_KVM)
+CONFIG_S390_FLIC=y
+CONFIG_S390_FLIC_KVM=$(CONFIG_KVM)

dma-helpers.c

@@ -143,12 +143,12 @@ static void dma_bdrv_cb(void *opaque, int ret)
 
     dbs->acb = NULL;
     dbs->sector_num += dbs->iov.size / 512;
-    dma_bdrv_unmap(dbs);
 
     if (dbs->sg_cur_index == dbs->sg->nsg || ret < 0) {
         dma_complete(dbs, ret);
         return;
     }
+    dma_bdrv_unmap(dbs);
 
     while (dbs->sg_cur_index < dbs->sg->nsg) {
         cur_addr = dbs->sg->sg[dbs->sg_cur_index].base + dbs->sg_cur_byte;

docs/multiseat.txt

@@ -0,0 +1,102 @@
+
+multiseat howto (with some multihead coverage)
+==============================================
+
+host side
+---------
+
+First you must compile qemu with a user interface supporting
+multihead/multiseat and input event routing.  Right now this
+list includes sdl2 and gtk (both 2+3):
+
+  ./configure --enable-sdl --with-sdlabi=2.0
+
+or
+
+  ./configure --enable-gtk
+
+
+Next put together the qemu command line:
+
+qemu	-enable-kvm -usb $memory $disk $whatever \
+	-display [ sdl | gtk ] \
+	-vga std \
+	-device usb-tablet
+
+That is it for the first head, which will use the standard vga, the
+standard ps/2 keyboard (implicitly there) and the usb-tablet.  Now the
+additional switches for the second head:
+
+	-device pci-bridge,addr=12.0,chassis_nr=2,id=head.2 \
+	-device secondary-vga,bus=head.2,addr=02.0,id=video.2 \
+	-device nec-usb-xhci,bus=head.2,addr=0f.0,id=usb.2 \
+	-device usb-kbd,bus=usb.2.0,port=1,display=video.2 \
+	-device usb-tablet,bus=usb.2.0,port=2,display=video.2
+
+This places a pci bridge in slot 12, connects a display adapter and
+xhci (usb) controller to the bridge.  Then it adds a usb keyboard and
+usb mouse, both connected to the xhci and linked to the display.
+
+The "display=video2" sets up the input routing.  Any input coming from
+the window which belongs to the video.2 display adapter will be routed
+to these input devices.
+
+The sdl2 ui will start up with two windows, one for each display
+device.  The gtk ui will start with a single window and each display
+in a separate tab.  You can either simply switch tabs to switch heads,
+or use the "View / Detach tab" menu item to move one of the displays
+to its own window so you can see both display devices side-by-side.
+
+Note on spice: Spice handles multihead just fine.  But it can't do
+multiseat.  For tablet events the event source is sent to the spice
+agent.  But qemu can't figure it, so it can't do input routing.
+Fixing this needs a new or extended input interface between
+libspice-server and qemu.  For keyboard events it is even worse:  The
+event source isn't included in the spice protocol, so the wire
+protocol must be extended to support this.
+
+
+guest side
+----------
+
+You need a pretty recent linux guest.  systemd with loginctl.  kernel
+3.14+ with CONFIG_DRM_BOCHS enabled.  Fedora 20 will do.  Must be
+fully updated for the new kernel though, i.e. the live iso doesn't cut
+it.
+
+Now we'll have to configure the guest.  Boot and login.  "lspci -vt"
+should list the pci bridge with the display adapter and usb controller:
+
+    [root@fedora ~]# lspci -vt
+    -[0000:00]-+-00.0  Intel Corporation 440FX - 82441FX PMC [Natoma]
+               [ ... ]
+               \-12.0-[01]--+-02.0  Device 1234:1111
+                            \-0f.0  NEC Corporation USB 3.0 Host Controller
+
+Good.  Now lets tell the system that the pci bridge and all devices
+below it belong to a separate seat by dropping a file into
+/etc/udev/rules.d:
+
+    [root@fedora ~]# cat /etc/udev/rules.d/70-qemu-autoseat.rules
+    SUBSYSTEMS=="pci", DEVPATH=="*/0000:00:12.0", TAG+="seat", ENV{ID_AUTOSEAT}="1"
+
+Reboot.  System should come up with two seats.  With loginctl you can
+check the configuration:
+
+    [root@fedora ~]# loginctl list-seats
+    SEAT
+    seat0
+    seat-pci-pci-0000_00_12_0
+
+    2 seats listed.
+
+You can use "loginctl seat-status seat-pci-pci-0000_00_12_0" to list
+the devices attached to the seat.
+
+Background info is here:
+  http://www.freedesktop.org/wiki/Software/systemd/multiseat/
+
+Enjoy!
+
+--
+Gerd Hoffmann <kraxel@redhat.com>

docs/specs/qcow2.txt

@@ -107,8 +107,9 @@ in the description of a field.
 
          96 -  99:  refcount_order
                     Describes the width of a reference count block entry (width
-                    in bits = 1 << refcount_order). For version 2 images, the
-                    order is always assumed to be 4 (i.e. the width is 16 bits).
+                    in bits: refcount_bits = 1 << refcount_order). For version 2
+                    images, the order is always assumed to be 4
+                    (i.e. refcount_bits = 16).
 
         100 - 103:  header_length
                     Length of the header structure in bytes. For version 2

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

hmp.c

@@ -341,6 +341,11 @@ void hmp_info_block(Monitor *mon, const QDict *qdict)
                            info->value->inserted->backing_file_depth);
         }
 
+        if (info->value->inserted->detect_zeroes != BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF) {
+            monitor_printf(mon, "    Detect zeroes:    %s\n",
+                           BlockdevDetectZeroesOptions_lookup[info->value->inserted->detect_zeroes]);
+        }
+
         if (info->value->inserted->bps
             || info->value->inserted->bps_rd
             || info->value->inserted->bps_wr

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/alpha/dp264.c

@@ -43,13 +43,13 @@ static int clipper_pci_map_irq(PCIDevice *d, int irq_num)
     return (slot + 1) * 4 + irq_num;
 }
 
-static void clipper_init(QEMUMachineInitArgs *args)
+static void clipper_init(MachineState *machine)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
+    ram_addr_t ram_size = machine->ram_size;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
+    const char *kernel_cmdline = machine->kernel_cmdline;
+    const char *initrd_filename = machine->initrd_filename;
     AlphaCPU *cpus[4];
     PCIBus *pci_bus;
     ISABus *isa_bus;

hw/arm/collie.c

@@ -23,12 +23,12 @@ static struct arm_boot_info collie_binfo = {
     .ram_size = 0x20000000,
 };
 
-static void collie_init(QEMUMachineInitArgs *args)
+static void collie_init(MachineState *machine)
 {
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
+    const char *kernel_cmdline = machine->kernel_cmdline;
+    const char *initrd_filename = machine->initrd_filename;
     StrongARMState *s;
     DriveInfo *dinfo;
     MemoryRegion *sysmem = get_system_memory();

hw/arm/cubieboard.c

@@ -30,7 +30,7 @@ typedef struct CubieBoardState {
     MemoryRegion sdram;
 } CubieBoardState;
 
-static void cubieboard_init(QEMUMachineInitArgs *args)
+static void cubieboard_init(MachineState *machine)
 {
     CubieBoardState *s = g_new(CubieBoardState, 1);
     Error *err = NULL;
@@ -63,14 +63,15 @@ static void cubieboard_init(QEMUMachineInitArgs *args)
         exit(1);
     }
 
-    memory_region_init_ram(&s->sdram, NULL, "cubieboard.ram", args->ram_size);
+    memory_region_init_ram(&s->sdram, NULL, "cubieboard.ram",
+                           machine->ram_size);
     vmstate_register_ram_global(&s->sdram);
     memory_region_add_subregion(get_system_memory(), AW_A10_SDRAM_BASE,
                                 &s->sdram);
 
-    cubieboard_binfo.ram_size = args->ram_size;
-    cubieboard_binfo.kernel_filename = args->kernel_filename;
-    cubieboard_binfo.kernel_cmdline = args->kernel_cmdline;
+    cubieboard_binfo.ram_size = machine->ram_size;
+    cubieboard_binfo.kernel_filename = machine->kernel_filename;
+    cubieboard_binfo.kernel_cmdline = machine->kernel_cmdline;
     arm_load_kernel(&s->a10->cpu, &cubieboard_binfo);
 }
 

hw/arm/digic_boards.c

@@ -143,7 +143,7 @@ static DigicBoard digic4_board_canon_a1100 = {
     .rom1_def_filename = "canon-a1100-rom1.bin",
 };
 
-static void canon_a1100_init(QEMUMachineInitArgs *args)
+static void canon_a1100_init(MachineState *machine)
 {
     digic4_board_init(&digic4_board_canon_a1100);
 }

hw/arm/exynos4_boards.c

@@ -94,7 +94,7 @@ static void lan9215_init(uint32_t base, qemu_irq irq)
     }
 }
 
-static Exynos4210State *exynos4_boards_init_common(QEMUMachineInitArgs *args,
+static Exynos4210State *exynos4_boards_init_common(MachineState *machine,
                                                    Exynos4BoardType board_type)
 {
     if (smp_cpus != EXYNOS4210_NCPUS && !qtest_enabled()) {
@@ -108,9 +108,9 @@ static Exynos4210State *exynos4_boards_init_common(QEMUMachineInitArgs *args,
     exynos4_board_binfo.board_id = exynos4_board_id[board_type];
     exynos4_board_binfo.smp_bootreg_addr =
             exynos4_board_smp_bootreg_addr[board_type];
-    exynos4_board_binfo.kernel_filename = args->kernel_filename;
-    exynos4_board_binfo.initrd_filename = args->initrd_filename;
-    exynos4_board_binfo.kernel_cmdline = args->kernel_cmdline;
+    exynos4_board_binfo.kernel_filename = machine->kernel_filename;
+    exynos4_board_binfo.initrd_filename = machine->initrd_filename;
+    exynos4_board_binfo.kernel_cmdline = machine->kernel_cmdline;
     exynos4_board_binfo.gic_cpu_if_addr =
             EXYNOS4210_SMP_PRIVATE_BASE_ADDR + 0x100;
 
@@ -120,24 +120,24 @@ static Exynos4210State *exynos4_boards_init_common(QEMUMachineInitArgs *args,
             " initrd_filename: %s\n",
             exynos4_board_ram_size[board_type] / 1048576,
             exynos4_board_ram_size[board_type],
-            args->kernel_filename,
-            args->kernel_cmdline,
-            args->initrd_filename);
+            machine->kernel_filename,
+            machine->kernel_cmdline,
+            machine->initrd_filename);
 
     return exynos4210_init(get_system_memory(),
             exynos4_board_ram_size[board_type]);
 }
 
-static void nuri_init(QEMUMachineInitArgs *args)
+static void nuri_init(MachineState *machine)
 {
-    exynos4_boards_init_common(args, EXYNOS4_BOARD_NURI);
+    exynos4_boards_init_common(machine, EXYNOS4_BOARD_NURI);
 
     arm_load_kernel(ARM_CPU(first_cpu), &exynos4_board_binfo);
 }
 
-static void smdkc210_init(QEMUMachineInitArgs *args)
+static void smdkc210_init(MachineState *machine)
 {
-    Exynos4210State *s = exynos4_boards_init_common(args,
+    Exynos4210State *s = exynos4_boards_init_common(machine,
                                                     EXYNOS4_BOARD_SMDKC210);
 
     lan9215_init(SMDK_LAN9118_BASE_ADDR,

hw/arm/gumstix.c

@@ -46,7 +46,7 @@
 
 static const int sector_len = 128 * 1024;
 
-static void connex_init(QEMUMachineInitArgs *args)
+static void connex_init(MachineState *machine)
 {
     PXA2xxState *cpu;
     DriveInfo *dinfo;
@@ -83,9 +83,9 @@ static void connex_init(QEMUMachineInitArgs *args)
                     qdev_get_gpio_in(cpu->gpio, 36));
 }
 
-static void verdex_init(QEMUMachineInitArgs *args)
+static void verdex_init(MachineState *machine)
 {
-    const char *cpu_model = args->cpu_model;
+    const char *cpu_model = machine->cpu_model;
     PXA2xxState *cpu;
     DriveInfo *dinfo;
     int be;

hw/arm/highbank.c

@@ -199,13 +199,13 @@ enum cxmachines {
  * 32-bit host, set the reg value of memory to 0xf7ff00000 in the
  * device tree and pass -m 2047 to QEMU.
  */
-static void calxeda_init(QEMUMachineInitArgs *args, enum cxmachines machine)
+static void calxeda_init(MachineState *machine, enum cxmachines machine_id)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
+    ram_addr_t ram_size = machine->ram_size;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
+    const char *kernel_cmdline = machine->kernel_cmdline;
+    const char *initrd_filename = machine->initrd_filename;
     DeviceState *dev = NULL;
     SysBusDevice *busdev;
     qemu_irq pic[128];
@@ -217,7 +217,7 @@ static void calxeda_init(QEMUMachineInitArgs *args, enum cxmachines machine)
     char *sysboot_filename;
 
     if (!cpu_model) {
-        switch (machine) {
+        switch (machine_id) {
         case CALXEDA_HIGHBANK:
             cpu_model = "cortex-a9";
             break;
@@ -274,7 +274,7 @@ static void calxeda_init(QEMUMachineInitArgs *args, enum cxmachines machine)
         }
     }
 
-    switch (machine) {
+    switch (machine_id) {
     case CALXEDA_HIGHBANK:
         dev = qdev_create(NULL, "l2x0");
         qdev_init_nofail(dev);
@@ -359,14 +359,14 @@ static void calxeda_init(QEMUMachineInitArgs *args, enum cxmachines machine)
     arm_load_kernel(ARM_CPU(first_cpu), &highbank_binfo);
 }
 
-static void highbank_init(QEMUMachineInitArgs *args)
+static void highbank_init(MachineState *machine)
 {
-    calxeda_init(args, CALXEDA_HIGHBANK);
+    calxeda_init(machine, CALXEDA_HIGHBANK);
 }
 
-static void midway_init(QEMUMachineInitArgs *args)
+static void midway_init(MachineState *machine)
 {
-    calxeda_init(args, CALXEDA_MIDWAY);
+    calxeda_init(machine, CALXEDA_MIDWAY);
 }
 
 static QEMUMachine highbank_machine = {

hw/arm/integratorcp.c

@@ -461,13 +461,13 @@ static struct arm_boot_info integrator_binfo = {
     .board_id = 0x113,
 };
 
-static void integratorcp_init(QEMUMachineInitArgs *args)
+static void integratorcp_init(MachineState *machine)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
+    ram_addr_t ram_size = machine->ram_size;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
+    const char *kernel_cmdline = machine->kernel_cmdline;
+    const char *initrd_filename = machine->initrd_filename;
     ARMCPU *cpu;
     MemoryRegion *address_space_mem = get_system_memory();
     MemoryRegion *ram = g_new(MemoryRegion, 1);

hw/arm/kzm.c

@@ -70,13 +70,13 @@ static struct arm_boot_info kzm_binfo = {
     .board_id = 1722,
 };
 
-static void kzm_init(QEMUMachineInitArgs *args)
+static void kzm_init(MachineState *machine)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
+    ram_addr_t ram_size = machine->ram_size;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
+    const char *kernel_cmdline = machine->kernel_cmdline;
+    const char *initrd_filename = machine->initrd_filename;
     ARMCPU *cpu;
     MemoryRegion *address_space_mem = get_system_memory();
     MemoryRegion *ram = g_new(MemoryRegion, 1);

hw/arm/mainstone.c

@@ -105,7 +105,7 @@ static struct arm_boot_info mainstone_binfo = {
 };
 
 static void mainstone_common_init(MemoryRegion *address_space_mem,
-                                  QEMUMachineInitArgs *args,
+                                  MachineState *machine,
                                   enum mainstone_model_e model, int arm_id)
 {
     uint32_t sector_len = 256 * 1024;
@@ -116,7 +116,7 @@ static void mainstone_common_init(MemoryRegion *address_space_mem,
     int i;
     int be;
     MemoryRegion *rom = g_new(MemoryRegion, 1);
-    const char *cpu_model = args->cpu_model;
+    const char *cpu_model = machine->cpu_model;
 
     if (!cpu_model)
         cpu_model = "pxa270-c5";
@@ -175,16 +175,16 @@ static void mainstone_common_init(MemoryRegion *address_space_mem,
     smc91c111_init(&nd_table[0], MST_ETH_PHYS,
                     qdev_get_gpio_in(mst_irq, ETHERNET_IRQ));
 
-    mainstone_binfo.kernel_filename = args->kernel_filename;
-    mainstone_binfo.kernel_cmdline = args->kernel_cmdline;
-    mainstone_binfo.initrd_filename = args->initrd_filename;
+    mainstone_binfo.kernel_filename = machine->kernel_filename;
+    mainstone_binfo.kernel_cmdline = machine->kernel_cmdline;
+    mainstone_binfo.initrd_filename = machine->initrd_filename;
     mainstone_binfo.board_id = arm_id;
     arm_load_kernel(mpu->cpu, &mainstone_binfo);
 }
 
-static void mainstone_init(QEMUMachineInitArgs *args)
+static void mainstone_init(MachineState *machine)
 {
-    mainstone_common_init(get_system_memory(), args, mainstone, 0x196);
+    mainstone_common_init(get_system_memory(), machine, mainstone, 0x196);
 }
 
 static QEMUMachine mainstone2_machine = {

hw/arm/musicpal.c

@@ -1569,12 +1569,12 @@ static struct arm_boot_info musicpal_binfo = {
     .board_id = 0x20e,
 };
 
-static void musicpal_init(QEMUMachineInitArgs *args)
+static void musicpal_init(MachineState *machine)
 {
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
+    const char *kernel_cmdline = machine->kernel_cmdline;
+    const char *initrd_filename = machine->initrd_filename;
     ARMCPU *cpu;
     qemu_irq pic[32];
     DeviceState *dev;

hw/arm/nseries.c

@@ -239,8 +239,9 @@ static void n800_key_event(void *opaque, int keycode)
     int code = s->keymap[keycode & 0x7f];
 
     if (code == -1) {
-        if ((keycode & 0x7f) == RETU_KEYCODE)
+        if ((keycode & 0x7f) == RETU_KEYCODE) {
             retu_key_event(s->retu, !(keycode & 0x80));
+        }
         return;
     }
 
@@ -280,11 +281,14 @@ static void n800_tsc_kbd_setup(struct n800_s *s)
     s->ts.opaque = s->ts.chip->opaque;
     s->ts.txrx = tsc210x_txrx;
 
-    for (i = 0; i < 0x80; i ++)
+    for (i = 0; i < 0x80; i++) {
         s->keymap[i] = -1;
-    for (i = 0; i < 0x10; i ++)
-        if (n800_keys[i] >= 0)
+    }
+    for (i = 0; i < 0x10; i++) {
+        if (n800_keys[i] >= 0) {
             s->keymap[n800_keys[i]] = i;
+        }
+    }
 
     qemu_add_kbd_event_handler(n800_key_event, s);
 
@@ -308,8 +312,9 @@ static void n810_key_event(void *opaque, int keycode)
     int code = s->keymap[keycode & 0x7f];
 
     if (code == -1) {
-        if ((keycode & 0x7f) == RETU_KEYCODE)
+        if ((keycode & 0x7f) == RETU_KEYCODE) {
             retu_key_event(s->retu, !(keycode & 0x80));
+        }
         return;
     }
 
@@ -388,11 +393,14 @@ static void n810_kbd_setup(struct n800_s *s)
     qemu_irq kbd_irq = qdev_get_gpio_in(s->mpu->gpio, N810_KEYBOARD_GPIO);
     int i;
 
-    for (i = 0; i < 0x80; i ++)
+    for (i = 0; i < 0x80; i++) {
         s->keymap[i] = -1;
-    for (i = 0; i < 0x80; i ++)
-        if (n810_keys[i] > 0)
+    }
+    for (i = 0; i < 0x80; i++) {
+        if (n810_keys[i] > 0) {
             s->keymap[n810_keys[i]] = i;
+        }
+    }
 
     qemu_add_kbd_event_handler(n810_key_event, s);
 
@@ -449,17 +457,20 @@ static uint32_t mipid_txrx(void *opaque, uint32_t cmd, int len)
     struct mipid_s *s = (struct mipid_s *) opaque;
     uint8_t ret;
 
-    if (len > 9)
+    if (len > 9) {
         hw_error("%s: FIXME: bad SPI word width %i\n", __FUNCTION__, len);
+    }
 
-    if (s->p >= ARRAY_SIZE(s->resp))
+    if (s->p >= ARRAY_SIZE(s->resp)) {
         ret = 0;
-    else
-        ret = s->resp[s->p ++];
-    if (s->pm --> 0)
+    } else {
+        ret = s->resp[s->p++];
+    }
+    if (s->pm-- > 0) {
         s->param[s->pm] = cmd;
-    else
+    } else {
         s->cmd = cmd;
+    }
 
     switch (s->cmd) {
     case 0x00:	/* NOP */
@@ -560,15 +571,17 @@ static uint32_t mipid_txrx(void *opaque, uint32_t cmd, int len)
         goto bad_cmd;
 
     case 0x25:	/* WRCNTR */
-        if (s->pm < 0)
+        if (s->pm < 0) {
             s->pm = 1;
+        }
         goto bad_cmd;
 
     case 0x26:	/* GAMSET */
-        if (!s->pm)
+        if (!s->pm) {
             s->gamma = ffs(s->param[0] & 0xf) - 1;
-        else if (s->pm < 0)
+        } else if (s->pm < 0) {
             s->pm = 1;
+        }
         break;
 
     case 0x28:	/* DISPOFF */
@@ -591,10 +604,11 @@ static uint32_t mipid_txrx(void *opaque, uint32_t cmd, int len)
         s->te = 0;
         break;
     case 0x35:	/* TEON */
-        if (!s->pm)
+        if (!s->pm) {
             s->te = 1;
-        else if (s->pm < 0)
+        } else if (s->pm < 0) {
             s->pm = 1;
+        }
         break;
 
     case 0x36:	/* MADCTR */
@@ -613,8 +627,9 @@ static uint32_t mipid_txrx(void *opaque, uint32_t cmd, int len)
 
     case 0xb0:	/* CLKINT / DISCTL */
     case 0xb1:	/* CLKEXT */
-        if (s->pm < 0)
+        if (s->pm < 0) {
             s->pm = 2;
+        }
         break;
 
     case 0xb4:	/* FRMSEL */
@@ -635,8 +650,9 @@ static uint32_t mipid_txrx(void *opaque, uint32_t cmd, int len)
         break;
 
     case 0xc2:	/* IFMOD */
-        if (s->pm < 0)
+        if (s->pm < 0) {
             s->pm = 2;
+        }
         break;
 
     case 0xc6:	/* PWRCTL */
@@ -834,118 +850,119 @@ static void n800_setup_nolo_tags(void *sram_base)
 
     strcpy((void *) (p + 8), "F5");
 
-    stl_raw(p + 10, 0x04f70000);
+    stl_p(p + 10, 0x04f70000);
     strcpy((void *) (p + 9), "RX-34");
 
     /* RAM size in MB? */
-    stl_raw(p + 12, 0x80);
+    stl_p(p + 12, 0x80);
 
     /* Pointer to the list of tags */
-    stl_raw(p + 13, OMAP2_SRAM_BASE + 0x9000);
+    stl_p(p + 13, OMAP2_SRAM_BASE + 0x9000);
 
     /* The NOLO tags start here */
     p = sram_base + 0x9000;
 #define ADD_TAG(tag, len)				\
-    stw_raw((uint16_t *) p + 0, tag);			\
-    stw_raw((uint16_t *) p + 1, len); p ++;		\
-    stl_raw(p ++, OMAP2_SRAM_BASE | (((void *) v - sram_base) & 0xffff));
+    stw_p((uint16_t *) p + 0, tag);			\
+    stw_p((uint16_t *) p + 1, len); p++;		\
+    stl_p(p++, OMAP2_SRAM_BASE | (((void *) v - sram_base) & 0xffff));
 
     /* OMAP STI console? Pin out settings? */
     ADD_TAG(0x6e01, 414);
-    for (i = 0; i < ARRAY_SIZE(n800_pinout); i ++)
-        stl_raw(v ++, n800_pinout[i]);
+    for (i = 0; i < ARRAY_SIZE(n800_pinout); i++) {
+        stl_p(v++, n800_pinout[i]);
+    }
 
     /* Kernel memsize? */
     ADD_TAG(0x6e05, 1);
-    stl_raw(v ++, 2);
+    stl_p(v++, 2);
 
     /* NOLO serial console */
     ADD_TAG(0x6e02, 4);
-    stl_raw(v ++, XLDR_LL_UART);	/* UART number (1 - 3) */
+    stl_p(v++, XLDR_LL_UART);		/* UART number (1 - 3) */
 
 #if 0
     /* CBUS settings (Retu/AVilma) */
     ADD_TAG(0x6e03, 6);
-    stw_raw((uint16_t *) v + 0, 65);	/* CBUS GPIO0 */
-    stw_raw((uint16_t *) v + 1, 66);	/* CBUS GPIO1 */
-    stw_raw((uint16_t *) v + 2, 64);	/* CBUS GPIO2 */
+    stw_p((uint16_t *) v + 0, 65);	/* CBUS GPIO0 */
+    stw_p((uint16_t *) v + 1, 66);	/* CBUS GPIO1 */
+    stw_p((uint16_t *) v + 2, 64);	/* CBUS GPIO2 */
     v += 2;
 #endif
 
     /* Nokia ASIC BB5 (Retu/Tahvo) */
     ADD_TAG(0x6e0a, 4);
-    stw_raw((uint16_t *) v + 0, 111);	/* "Retu" interrupt GPIO */
-    stw_raw((uint16_t *) v + 1, 108);	/* "Tahvo" interrupt GPIO */
-    v ++;
+    stw_p((uint16_t *) v + 0, 111);	/* "Retu" interrupt GPIO */
+    stw_p((uint16_t *) v + 1, 108);	/* "Tahvo" interrupt GPIO */
+    v++;
 
     /* LCD console? */
     ADD_TAG(0x6e04, 4);
-    stw_raw((uint16_t *) v + 0, 30);	/* ??? */
-    stw_raw((uint16_t *) v + 1, 24);	/* ??? */
-    v ++;
+    stw_p((uint16_t *) v + 0, 30);	/* ??? */
+    stw_p((uint16_t *) v + 1, 24);	/* ??? */
+    v++;
 
 #if 0
     /* LCD settings */
     ADD_TAG(0x6e06, 2);
-    stw_raw((uint16_t *) (v ++), 15);	/* ??? */
+    stw_p((uint16_t *) (v++), 15);	/* ??? */
 #endif
 
     /* I^2C (Menelaus) */
     ADD_TAG(0x6e07, 4);
-    stl_raw(v ++, 0x00720000);		/* ??? */
+    stl_p(v++, 0x00720000);		/* ??? */
 
     /* Unknown */
     ADD_TAG(0x6e0b, 6);
-    stw_raw((uint16_t *) v + 0, 94);	/* ??? */
-    stw_raw((uint16_t *) v + 1, 23);	/* ??? */
-    stw_raw((uint16_t *) v + 2, 0);	/* ??? */
+    stw_p((uint16_t *) v + 0, 94);	/* ??? */
+    stw_p((uint16_t *) v + 1, 23);	/* ??? */
+    stw_p((uint16_t *) v + 2, 0);	/* ??? */
     v += 2;
 
     /* OMAP gpio switch info */
     ADD_TAG(0x6e0c, 80);
     strcpy((void *) v, "bat_cover");	v += 3;
-    stw_raw((uint16_t *) v + 0, 110);	/* GPIO num ??? */
-    stw_raw((uint16_t *) v + 1, 1);	/* GPIO num ??? */
+    stw_p((uint16_t *) v + 0, 110);	/* GPIO num ??? */
+    stw_p((uint16_t *) v + 1, 1);	/* GPIO num ??? */
     v += 2;
     strcpy((void *) v, "cam_act");	v += 3;
-    stw_raw((uint16_t *) v + 0, 95);	/* GPIO num ??? */
-    stw_raw((uint16_t *) v + 1, 32);	/* GPIO num ??? */
+    stw_p((uint16_t *) v + 0, 95);	/* GPIO num ??? */
+    stw_p((uint16_t *) v + 1, 32);	/* GPIO num ??? */
     v += 2;
     strcpy((void *) v, "cam_turn");	v += 3;
-    stw_raw((uint16_t *) v + 0, 12);	/* GPIO num ??? */
-    stw_raw((uint16_t *) v + 1, 33);	/* GPIO num ??? */
+    stw_p((uint16_t *) v + 0, 12);	/* GPIO num ??? */
+    stw_p((uint16_t *) v + 1, 33);	/* GPIO num ??? */
     v += 2;
     strcpy((void *) v, "headphone");	v += 3;
-    stw_raw((uint16_t *) v + 0, 107);	/* GPIO num ??? */
-    stw_raw((uint16_t *) v + 1, 17);	/* GPIO num ??? */
+    stw_p((uint16_t *) v + 0, 107);	/* GPIO num ??? */
+    stw_p((uint16_t *) v + 1, 17);	/* GPIO num ??? */
     v += 2;
 
     /* Bluetooth */
     ADD_TAG(0x6e0e, 12);
-    stl_raw(v ++, 0x5c623d01);		/* ??? */
-    stl_raw(v ++, 0x00000201);		/* ??? */
-    stl_raw(v ++, 0x00000000);		/* ??? */
+    stl_p(v++, 0x5c623d01);		/* ??? */
+    stl_p(v++, 0x00000201);		/* ??? */
+    stl_p(v++, 0x00000000);		/* ??? */
 
     /* CX3110x WLAN settings */
     ADD_TAG(0x6e0f, 8);
-    stl_raw(v ++, 0x00610025);		/* ??? */
-    stl_raw(v ++, 0xffff0057);		/* ??? */
+    stl_p(v++, 0x00610025);		/* ??? */
+    stl_p(v++, 0xffff0057);		/* ??? */
 
     /* MMC host settings */
     ADD_TAG(0x6e10, 12);
-    stl_raw(v ++, 0xffff000f);		/* ??? */
-    stl_raw(v ++, 0xffffffff);		/* ??? */
-    stl_raw(v ++, 0x00000060);		/* ??? */
+    stl_p(v++, 0xffff000f);		/* ??? */
+    stl_p(v++, 0xffffffff);		/* ??? */
+    stl_p(v++, 0x00000060);		/* ??? */
 
     /* OneNAND chip select */
     ADD_TAG(0x6e11, 10);
-    stl_raw(v ++, 0x00000401);		/* ??? */
-    stl_raw(v ++, 0x0002003a);		/* ??? */
-    stl_raw(v ++, 0x00000002);		/* ??? */
+    stl_p(v++, 0x00000401);		/* ??? */
+    stl_p(v++, 0x0002003a);		/* ??? */
+    stl_p(v++, 0x00000002);		/* ??? */
 
     /* TEA5761 sensor settings */
     ADD_TAG(0x6e12, 2);
-    stl_raw(v ++, 93);			/* GPIO num ??? */
+    stl_p(v++, 93);			/* GPIO num ??? */
 
 #if 0
     /* Unknown tag */
@@ -956,8 +973,8 @@ static void n800_setup_nolo_tags(void *sram_base)
 #endif
 
     /* End of the list */
-    stl_raw(p ++, 0x00000000);
-    stl_raw(p ++, 0x00000000);
+    stl_p(p++, 0x00000000);
+    stl_p(p++, 0x00000000);
 }
 
 /* This task is normally performed by the bootloader.  If we're loading
@@ -1032,8 +1049,9 @@ static void n8x0_boot_init(void *opaque)
     s->mpu->cpu->env.GE = 0x5;
 
     /* If the machine has a slided keyboard, open it */
-    if (s->kbd)
+    if (s->kbd) {
         qemu_irq_raise(qdev_get_gpio_in(s->mpu->gpio, N810_SLIDE_GPIO));
+    }
 }
 
 #define OMAP_TAG_NOKIA_BT	0x4e01
@@ -1119,112 +1137,112 @@ static int n8x0_atag_setup(void *p, int model)
 
     w = p;
 
-    stw_raw(w ++, OMAP_TAG_UART);		/* u16 tag */
-    stw_raw(w ++, 4);				/* u16 len */
-    stw_raw(w ++, (1 << 2) | (1 << 1) | (1 << 0)); /* uint enabled_uarts */
-    w ++;
+    stw_p(w++, OMAP_TAG_UART);			/* u16 tag */
+    stw_p(w++, 4);				/* u16 len */
+    stw_p(w++, (1 << 2) | (1 << 1) | (1 << 0)); /* uint enabled_uarts */
+    w++;
 
 #if 0
-    stw_raw(w ++, OMAP_TAG_SERIAL_CONSOLE);	/* u16 tag */
-    stw_raw(w ++, 4);				/* u16 len */
-    stw_raw(w ++, XLDR_LL_UART + 1);		/* u8 console_uart */
-    stw_raw(w ++, 115200);			/* u32 console_speed */
+    stw_p(w++, OMAP_TAG_SERIAL_CONSOLE);	/* u16 tag */
+    stw_p(w++, 4);				/* u16 len */
+    stw_p(w++, XLDR_LL_UART + 1);		/* u8 console_uart */
+    stw_p(w++, 115200);				/* u32 console_speed */
 #endif
 
-    stw_raw(w ++, OMAP_TAG_LCD);		/* u16 tag */
-    stw_raw(w ++, 36);				/* u16 len */
+    stw_p(w++, OMAP_TAG_LCD);			/* u16 tag */
+    stw_p(w++, 36);				/* u16 len */
     strcpy((void *) w, "QEMU LCD panel");	/* char panel_name[16] */
     w += 8;
     strcpy((void *) w, "blizzard");		/* char ctrl_name[16] */
     w += 8;
-    stw_raw(w ++, N810_BLIZZARD_RESET_GPIO);	/* TODO: n800 s16 nreset_gpio */
-    stw_raw(w ++, 24);				/* u8 data_lines */
+    stw_p(w++, N810_BLIZZARD_RESET_GPIO);	/* TODO: n800 s16 nreset_gpio */
+    stw_p(w++, 24);				/* u8 data_lines */
 
-    stw_raw(w ++, OMAP_TAG_CBUS);		/* u16 tag */
-    stw_raw(w ++, 8);				/* u16 len */
-    stw_raw(w ++, N8X0_CBUS_CLK_GPIO);		/* s16 clk_gpio */
-    stw_raw(w ++, N8X0_CBUS_DAT_GPIO);		/* s16 dat_gpio */
-    stw_raw(w ++, N8X0_CBUS_SEL_GPIO);		/* s16 sel_gpio */
-    w ++;
+    stw_p(w++, OMAP_TAG_CBUS);			/* u16 tag */
+    stw_p(w++, 8);				/* u16 len */
+    stw_p(w++, N8X0_CBUS_CLK_GPIO);		/* s16 clk_gpio */
+    stw_p(w++, N8X0_CBUS_DAT_GPIO);		/* s16 dat_gpio */
+    stw_p(w++, N8X0_CBUS_SEL_GPIO);		/* s16 sel_gpio */
+    w++;
 
-    stw_raw(w ++, OMAP_TAG_EM_ASIC_BB5);	/* u16 tag */
-    stw_raw(w ++, 4);				/* u16 len */
-    stw_raw(w ++, N8X0_RETU_GPIO);		/* s16 retu_irq_gpio */
-    stw_raw(w ++, N8X0_TAHVO_GPIO);		/* s16 tahvo_irq_gpio */
+    stw_p(w++, OMAP_TAG_EM_ASIC_BB5);		/* u16 tag */
+    stw_p(w++, 4);				/* u16 len */
+    stw_p(w++, N8X0_RETU_GPIO);			/* s16 retu_irq_gpio */
+    stw_p(w++, N8X0_TAHVO_GPIO);		/* s16 tahvo_irq_gpio */
 
     gpiosw = (model == 810) ? n810_gpiosw_info : n800_gpiosw_info;
-    for (; gpiosw->name; gpiosw ++) {
-        stw_raw(w ++, OMAP_TAG_GPIO_SWITCH);	/* u16 tag */
-        stw_raw(w ++, 20);			/* u16 len */
+    for (; gpiosw->name; gpiosw++) {
+        stw_p(w++, OMAP_TAG_GPIO_SWITCH);	/* u16 tag */
+        stw_p(w++, 20);				/* u16 len */
         strcpy((void *) w, gpiosw->name);	/* char name[12] */
         w += 6;
-        stw_raw(w ++, gpiosw->line);		/* u16 gpio */
-        stw_raw(w ++, gpiosw->type);
-        stw_raw(w ++, 0);
-        stw_raw(w ++, 0);
+        stw_p(w++, gpiosw->line);		/* u16 gpio */
+        stw_p(w++, gpiosw->type);
+        stw_p(w++, 0);
+        stw_p(w++, 0);
     }
 
-    stw_raw(w ++, OMAP_TAG_NOKIA_BT);		/* u16 tag */
-    stw_raw(w ++, 12);				/* u16 len */
+    stw_p(w++, OMAP_TAG_NOKIA_BT);		/* u16 tag */
+    stw_p(w++, 12);				/* u16 len */
     b = (void *) w;
-    stb_raw(b ++, 0x01);			/* u8 chip_type	(CSR) */
-    stb_raw(b ++, N8X0_BT_WKUP_GPIO);		/* u8 bt_wakeup_gpio */
-    stb_raw(b ++, N8X0_BT_HOST_WKUP_GPIO);	/* u8 host_wakeup_gpio */
-    stb_raw(b ++, N8X0_BT_RESET_GPIO);		/* u8 reset_gpio */
-    stb_raw(b ++, BT_UART + 1);			/* u8 bt_uart */
+    stb_p(b++, 0x01);				/* u8 chip_type	(CSR) */
+    stb_p(b++, N8X0_BT_WKUP_GPIO);		/* u8 bt_wakeup_gpio */
+    stb_p(b++, N8X0_BT_HOST_WKUP_GPIO);		/* u8 host_wakeup_gpio */
+    stb_p(b++, N8X0_BT_RESET_GPIO);		/* u8 reset_gpio */
+    stb_p(b++, BT_UART + 1);			/* u8 bt_uart */
     memcpy(b, &n8x0_bd_addr, 6);		/* u8 bd_addr[6] */
     b += 6;
-    stb_raw(b ++, 0x02);			/* u8 bt_sysclk (38.4) */
+    stb_p(b++, 0x02);				/* u8 bt_sysclk (38.4) */
     w = (void *) b;
 
-    stw_raw(w ++, OMAP_TAG_WLAN_CX3110X);	/* u16 tag */
-    stw_raw(w ++, 8);				/* u16 len */
-    stw_raw(w ++, 0x25);			/* u8 chip_type */
-    stw_raw(w ++, N8X0_WLAN_PWR_GPIO);		/* s16 power_gpio */
-    stw_raw(w ++, N8X0_WLAN_IRQ_GPIO);		/* s16 irq_gpio */
-    stw_raw(w ++, -1);				/* s16 spi_cs_gpio */
+    stw_p(w++, OMAP_TAG_WLAN_CX3110X);		/* u16 tag */
+    stw_p(w++, 8);				/* u16 len */
+    stw_p(w++, 0x25);				/* u8 chip_type */
+    stw_p(w++, N8X0_WLAN_PWR_GPIO);		/* s16 power_gpio */
+    stw_p(w++, N8X0_WLAN_IRQ_GPIO);		/* s16 irq_gpio */
+    stw_p(w++, -1);				/* s16 spi_cs_gpio */
 
-    stw_raw(w ++, OMAP_TAG_MMC);		/* u16 tag */
-    stw_raw(w ++, 16);				/* u16 len */
+    stw_p(w++, OMAP_TAG_MMC);			/* u16 tag */
+    stw_p(w++, 16);				/* u16 len */
     if (model == 810) {
-        stw_raw(w ++, 0x23f);			/* unsigned flags */
-        stw_raw(w ++, -1);			/* s16 power_pin */
-        stw_raw(w ++, -1);			/* s16 switch_pin */
-        stw_raw(w ++, -1);			/* s16 wp_pin */
-        stw_raw(w ++, 0x240);			/* unsigned flags */
-        stw_raw(w ++, 0xc000);			/* s16 power_pin */
-        stw_raw(w ++, 0x0248);			/* s16 switch_pin */
-        stw_raw(w ++, 0xc000);			/* s16 wp_pin */
+        stw_p(w++, 0x23f);			/* unsigned flags */
+        stw_p(w++, -1);				/* s16 power_pin */
+        stw_p(w++, -1);				/* s16 switch_pin */
+        stw_p(w++, -1);				/* s16 wp_pin */
+        stw_p(w++, 0x240);			/* unsigned flags */
+        stw_p(w++, 0xc000);			/* s16 power_pin */
+        stw_p(w++, 0x0248);			/* s16 switch_pin */
+        stw_p(w++, 0xc000);			/* s16 wp_pin */
     } else {
-        stw_raw(w ++, 0xf);			/* unsigned flags */
-        stw_raw(w ++, -1);			/* s16 power_pin */
-        stw_raw(w ++, -1);			/* s16 switch_pin */
-        stw_raw(w ++, -1);			/* s16 wp_pin */
-        stw_raw(w ++, 0);			/* unsigned flags */
-        stw_raw(w ++, 0);			/* s16 power_pin */
-        stw_raw(w ++, 0);			/* s16 switch_pin */
-        stw_raw(w ++, 0);			/* s16 wp_pin */
+        stw_p(w++, 0xf);			/* unsigned flags */
+        stw_p(w++, -1);				/* s16 power_pin */
+        stw_p(w++, -1);				/* s16 switch_pin */
+        stw_p(w++, -1);				/* s16 wp_pin */
+        stw_p(w++, 0);				/* unsigned flags */
+        stw_p(w++, 0);				/* s16 power_pin */
+        stw_p(w++, 0);				/* s16 switch_pin */
+        stw_p(w++, 0);				/* s16 wp_pin */
     }
 
-    stw_raw(w ++, OMAP_TAG_TEA5761);		/* u16 tag */
-    stw_raw(w ++, 4);				/* u16 len */
-    stw_raw(w ++, N8X0_TEA5761_CS_GPIO);	/* u16 enable_gpio */
-    w ++;
+    stw_p(w++, OMAP_TAG_TEA5761);		/* u16 tag */
+    stw_p(w++, 4);				/* u16 len */
+    stw_p(w++, N8X0_TEA5761_CS_GPIO);		/* u16 enable_gpio */
+    w++;
 
     partition = (model == 810) ? n810_part_info : n800_part_info;
-    for (; partition->name; partition ++) {
-        stw_raw(w ++, OMAP_TAG_PARTITION);	/* u16 tag */
-        stw_raw(w ++, 28);			/* u16 len */
+    for (; partition->name; partition++) {
+        stw_p(w++, OMAP_TAG_PARTITION);		/* u16 tag */
+        stw_p(w++, 28);				/* u16 len */
         strcpy((void *) w, partition->name);	/* char name[16] */
         l = (void *) (w + 8);
-        stl_raw(l ++, partition->size);		/* unsigned int size */
-        stl_raw(l ++, partition->offset);	/* unsigned int offset */
-        stl_raw(l ++, partition->mask);		/* unsigned int mask_flags */
+        stl_p(l++, partition->size);		/* unsigned int size */
+        stl_p(l++, partition->offset);		/* unsigned int offset */
+        stl_p(l++, partition->mask);		/* unsigned int mask_flags */
         w = (void *) l;
     }
 
-    stw_raw(w ++, OMAP_TAG_BOOT_REASON);	/* u16 tag */
-    stw_raw(w ++, 12);				/* u16 len */
+    stw_p(w++, OMAP_TAG_BOOT_REASON);		/* u16 tag */
+    stw_p(w++, 12);				/* u16 len */
 #if 0
     strcpy((void *) w, "por");			/* char reason_str[12] */
     strcpy((void *) w, "charger");		/* char reason_str[12] */
@@ -1242,15 +1260,15 @@ static int n8x0_atag_setup(void *p, int model)
     w += 6;
 
     tag = (model == 810) ? "RX-44" : "RX-34";
-    stw_raw(w ++, OMAP_TAG_VERSION_STR);	/* u16 tag */
-    stw_raw(w ++, 24);				/* u16 len */
+    stw_p(w++, OMAP_TAG_VERSION_STR);		/* u16 tag */
+    stw_p(w++, 24);				/* u16 len */
     strcpy((void *) w, "product");		/* char component[12] */
     w += 6;
     strcpy((void *) w, tag);			/* char version[12] */
     w += 6;
 
-    stw_raw(w ++, OMAP_TAG_VERSION_STR);	/* u16 tag */
-    stw_raw(w ++, 24);				/* u16 len */
+    stw_p(w++, OMAP_TAG_VERSION_STR);		/* u16 tag */
+    stw_p(w++, 24);				/* u16 len */
     strcpy((void *) w, "hw-build");		/* char component[12] */
     w += 6;
     strcpy((void *) w, "QEMU ");
@@ -1258,8 +1276,8 @@ static int n8x0_atag_setup(void *p, int model)
     w += 6;
 
     tag = (model == 810) ? "1.1.10-qemu" : "1.1.6-qemu";
-    stw_raw(w ++, OMAP_TAG_VERSION_STR);	/* u16 tag */
-    stw_raw(w ++, 24);				/* u16 len */
+    stw_p(w++, OMAP_TAG_VERSION_STR);		/* u16 tag */
+    stw_p(w++, 24);				/* u16 len */
     strcpy((void *) w, "nolo");			/* char component[12] */
     w += 6;
     strcpy((void *) w, tag);			/* char version[12] */
@@ -1278,14 +1296,14 @@ static int n810_atag_setup(const struct arm_boot_info *info, void *p)
     return n8x0_atag_setup(p, 810);
 }
 
-static void n8x0_init(QEMUMachineInitArgs *args,
+static void n8x0_init(MachineState *machine,
                       struct arm_boot_info *binfo, int model)
 {
     MemoryRegion *sysmem = get_system_memory();
     struct n800_s *s = (struct n800_s *) g_malloc0(sizeof(*s));
     int sdram_size = binfo->ram_size;
 
-    s->mpu = omap2420_mpu_init(sysmem, sdram_size, args->cpu_model);
+    s->mpu = omap2420_mpu_init(sysmem, sdram_size, machine->cpu_model);
 
     /* Setup peripherals
      *
@@ -1315,9 +1333,9 @@ static void n8x0_init(QEMUMachineInitArgs *args,
     n8x0_gpio_setup(s);
     n8x0_nand_setup(s);
     n8x0_i2c_setup(s);
-    if (model == 800)
+    if (model == 800) {
         n800_tsc_kbd_setup(s);
-    else if (model == 810) {
+    } else if (model == 810) {
         n810_tsc_setup(s);
         n810_kbd_setup(s);
     }
@@ -1329,18 +1347,18 @@ static void n8x0_init(QEMUMachineInitArgs *args,
         n8x0_usb_setup(s);
     }
 
-    if (args->kernel_filename) {
+    if (machine->kernel_filename) {
         /* Or at the linux loader.  */
-        binfo->kernel_filename = args->kernel_filename;
-        binfo->kernel_cmdline = args->kernel_cmdline;
-        binfo->initrd_filename = args->initrd_filename;
+        binfo->kernel_filename = machine->kernel_filename;
+        binfo->kernel_cmdline = machine->kernel_cmdline;
+        binfo->initrd_filename = machine->initrd_filename;
         arm_load_kernel(s->mpu->cpu, binfo);
 
         qemu_register_reset(n8x0_boot_init, s);
     }
 
     if (option_rom[0].name &&
-        (args->boot_order[0] == 'n' || !args->kernel_filename)) {
+        (machine->boot_order[0] == 'n' || !machine->kernel_filename)) {
         uint8_t nolo_tags[0x10000];
         /* No, wait, better start at the ROM.  */
         s->mpu->cpu->env.regs[15] = OMAP2_Q2_BASE + 0x400000;
@@ -1382,14 +1400,14 @@ static struct arm_boot_info n810_binfo = {
     .atag_board = n810_atag_setup,
 };
 
-static void n800_init(QEMUMachineInitArgs *args)
+static void n800_init(MachineState *machine)
 {
-    return n8x0_init(args, &n800_binfo, 800);
+    return n8x0_init(machine, &n800_binfo, 800);
 }
 
-static void n810_init(QEMUMachineInitArgs *args)
+static void n810_init(MachineState *machine)
 {
-    return n8x0_init(args, &n810_binfo, 810);
+    return n8x0_init(machine, &n810_binfo, 810);
 }
 
 static QEMUMachine n800_machine = {

hw/arm/omap_sx1.c

@@ -98,7 +98,7 @@ static struct arm_boot_info sx1_binfo = {
     .board_id = 0x265,
 };
 
-static void sx1_init(QEMUMachineInitArgs *args, const int version)
+static void sx1_init(MachineState *machine, const int version)
 {
     struct omap_mpu_state_s *mpu;
     MemoryRegion *address_space = get_system_memory();
@@ -118,7 +118,8 @@ static void sx1_init(QEMUMachineInitArgs *args, const int version)
         flash_size = flash2_size;
     }
 
-    mpu = omap310_mpu_init(address_space, sx1_binfo.ram_size, args->cpu_model);
+    mpu = omap310_mpu_init(address_space, sx1_binfo.ram_size,
+                           machine->cpu_model);
 
     /* External Flash (EMIFS) */
     memory_region_init_ram(flash, NULL, "omap_sx1.flash0-0", flash_size);
@@ -189,29 +190,29 @@ static void sx1_init(QEMUMachineInitArgs *args, const int version)
                                 OMAP_CS1_BASE, &cs[1]);
     }
 
-    if (!args->kernel_filename && !fl_idx && !qtest_enabled()) {
+    if (!machine->kernel_filename && !fl_idx && !qtest_enabled()) {
         fprintf(stderr, "Kernel or Flash image must be specified\n");
         exit(1);
     }
 
     /* Load the kernel.  */
-    sx1_binfo.kernel_filename = args->kernel_filename;
-    sx1_binfo.kernel_cmdline = args->kernel_cmdline;
-    sx1_binfo.initrd_filename = args->initrd_filename;
+    sx1_binfo.kernel_filename = machine->kernel_filename;
+    sx1_binfo.kernel_cmdline = machine->kernel_cmdline;
+    sx1_binfo.initrd_filename = machine->initrd_filename;
     arm_load_kernel(mpu->cpu, &sx1_binfo);
 
     /* TODO: fix next line */
     //~ qemu_console_resize(ds, 640, 480);
 }
 
-static void sx1_init_v1(QEMUMachineInitArgs *args)
+static void sx1_init_v1(MachineState *machine)
 {
-    sx1_init(args, 1);
+    sx1_init(machine, 1);
 }
 
-static void sx1_init_v2(QEMUMachineInitArgs *args)
+static void sx1_init_v2(MachineState *machine)
 {
-    sx1_init(args, 2);
+    sx1_init(machine, 2);
 }
 
 static QEMUMachine sx1_machine_v2 = {

hw/arm/palm.c

@@ -191,12 +191,12 @@ static struct arm_boot_info palmte_binfo = {
     .board_id = 0x331,
 };
 
-static void palmte_init(QEMUMachineInitArgs *args)
+static void palmte_init(MachineState *machine)
 {
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
+    const char *kernel_cmdline = machine->kernel_cmdline;
+    const char *initrd_filename = machine->initrd_filename;
     MemoryRegion *address_space_mem = get_system_memory();
     struct omap_mpu_state_s *mpu;
     int flash_size = 0x00800000;

hw/arm/realview.c

@@ -45,7 +45,7 @@ static const int realview_board_id[] = {
     0x76d
 };
 
-static void realview_init(QEMUMachineInitArgs *args,
+static void realview_init(MachineState *machine,
                           enum realview_board_type board_type)
 {
     ARMCPU *cpu = NULL;
@@ -71,7 +71,7 @@ static void realview_init(QEMUMachineInitArgs *args,
     uint32_t proc_id = 0;
     uint32_t sys_id;
     ram_addr_t low_ram_size;
-    ram_addr_t ram_size = args->ram_size;
+    ram_addr_t ram_size = machine->ram_size;
     hwaddr periphbase = 0;
 
     switch (board_type) {
@@ -91,7 +91,7 @@ static void realview_init(QEMUMachineInitArgs *args,
         break;
     }
 
-    cpu_oc = cpu_class_by_name(TYPE_ARM_CPU, args->cpu_model);
+    cpu_oc = cpu_class_by_name(TYPE_ARM_CPU, machine->cpu_model);
     if (!cpu_oc) {
         fprintf(stderr, "Unable to find CPU definition\n");
         exit(1);
@@ -342,45 +342,45 @@ static void realview_init(QEMUMachineInitArgs *args,
     memory_region_add_subregion(sysmem, SMP_BOOT_ADDR, ram_hack);
 
     realview_binfo.ram_size = ram_size;
-    realview_binfo.kernel_filename = args->kernel_filename;
-    realview_binfo.kernel_cmdline = args->kernel_cmdline;
-    realview_binfo.initrd_filename = args->initrd_filename;
+    realview_binfo.kernel_filename = machine->kernel_filename;
+    realview_binfo.kernel_cmdline = machine->kernel_cmdline;
+    realview_binfo.initrd_filename = machine->initrd_filename;
     realview_binfo.nb_cpus = smp_cpus;
     realview_binfo.board_id = realview_board_id[board_type];
     realview_binfo.loader_start = (board_type == BOARD_PB_A8 ? 0x70000000 : 0);
     arm_load_kernel(ARM_CPU(first_cpu), &realview_binfo);
 }
 
-static void realview_eb_init(QEMUMachineInitArgs *args)
+static void realview_eb_init(MachineState *machine)
 {
-    if (!args->cpu_model) {
-        args->cpu_model = "arm926";
+    if (!machine->cpu_model) {
+        machine->cpu_model = "arm926";
     }
-    realview_init(args, BOARD_EB);
+    realview_init(machine, BOARD_EB);
 }
 
-static void realview_eb_mpcore_init(QEMUMachineInitArgs *args)
+static void realview_eb_mpcore_init(MachineState *machine)
 {
-    if (!args->cpu_model) {
-        args->cpu_model = "arm11mpcore";
+    if (!machine->cpu_model) {
+        machine->cpu_model = "arm11mpcore";
     }
-    realview_init(args, BOARD_EB_MPCORE);
+    realview_init(machine, BOARD_EB_MPCORE);
 }
 
-static void realview_pb_a8_init(QEMUMachineInitArgs *args)
+static void realview_pb_a8_init(MachineState *machine)
 {
-    if (!args->cpu_model) {
-        args->cpu_model = "cortex-a8";
+    if (!machine->cpu_model) {
+        machine->cpu_model = "cortex-a8";
     }
-    realview_init(args, BOARD_PB_A8);
+    realview_init(machine, BOARD_PB_A8);
 }
 
-static void realview_pbx_a9_init(QEMUMachineInitArgs *args)
+static void realview_pbx_a9_init(MachineState *machine)
 {
-    if (!args->cpu_model) {
-        args->cpu_model = "cortex-a9";
+    if (!machine->cpu_model) {
+        machine->cpu_model = "cortex-a9";
     }
-    realview_init(args, BOARD_PBX_A9);
+    realview_init(machine, BOARD_PBX_A9);
 }
 
 static QEMUMachine realview_eb_machine = {

hw/arm/spitz.c

@@ -887,14 +887,14 @@ static struct arm_boot_info spitz_binfo = {
     .ram_size = 0x04000000,
 };
 
-static void spitz_common_init(QEMUMachineInitArgs *args,
+static void spitz_common_init(MachineState *machine,
                               enum spitz_model_e model, int arm_id)
 {
     PXA2xxState *mpu;
     DeviceState *scp0, *scp1 = NULL;
     MemoryRegion *address_space_mem = get_system_memory();
     MemoryRegion *rom = g_new(MemoryRegion, 1);
-    const char *cpu_model = args->cpu_model;
+    const char *cpu_model = machine->cpu_model;
 
     if (!cpu_model)
         cpu_model = (model == terrier) ? "pxa270-c5" : "pxa270-c0";
@@ -935,32 +935,32 @@ static void spitz_common_init(QEMUMachineInitArgs *args,
         /* A 4.0 GB microdrive is permanently sitting in CF slot 0.  */
         spitz_microdrive_attach(mpu, 0);
 
-    spitz_binfo.kernel_filename = args->kernel_filename;
-    spitz_binfo.kernel_cmdline = args->kernel_cmdline;
-    spitz_binfo.initrd_filename = args->initrd_filename;
+    spitz_binfo.kernel_filename = machine->kernel_filename;
+    spitz_binfo.kernel_cmdline = machine->kernel_cmdline;
+    spitz_binfo.initrd_filename = machine->initrd_filename;
     spitz_binfo.board_id = arm_id;
     arm_load_kernel(mpu->cpu, &spitz_binfo);
     sl_bootparam_write(SL_PXA_PARAM_BASE);
 }
 
-static void spitz_init(QEMUMachineInitArgs *args)
+static void spitz_init(MachineState *machine)
 {
-    spitz_common_init(args, spitz, 0x2c9);
+    spitz_common_init(machine, spitz, 0x2c9);
 }
 
-static void borzoi_init(QEMUMachineInitArgs *args)
+static void borzoi_init(MachineState *machine)
 {
-    spitz_common_init(args, borzoi, 0x33f);
+    spitz_common_init(machine, borzoi, 0x33f);
 }
 
-static void akita_init(QEMUMachineInitArgs *args)
+static void akita_init(MachineState *machine)
 {
-    spitz_common_init(args, akita, 0x2e8);
+    spitz_common_init(machine, akita, 0x2e8);
 }
 
-static void terrier_init(QEMUMachineInitArgs *args)
+static void terrier_init(MachineState *machine)
 {
-    spitz_common_init(args, terrier, 0x33f);
+    spitz_common_init(machine, terrier, 0x33f);
 }
 
 static QEMUMachine akitapda_machine = {

hw/arm/stellaris.c

@@ -1290,9 +1290,10 @@ static void stellaris_init(const char *kernel_filename, const char *cpu_model,
 
             sddev = ssi_create_slave(bus, "ssi-sd");
             ssddev = ssi_create_slave(bus, "ssd0323");
-            gpio_out[GPIO_D][0] = qemu_irq_split(qdev_get_gpio_in(sddev, 0),
-                                                 qdev_get_gpio_in(ssddev, 0));
-            gpio_out[GPIO_C][7] = qdev_get_gpio_in(ssddev, 1);
+            gpio_out[GPIO_D][0] = qemu_irq_split(
+                    qdev_get_gpio_in_named(sddev, SSI_GPIO_CS, 0),
+                    qdev_get_gpio_in_named(ssddev, SSI_GPIO_CS, 0));
+            gpio_out[GPIO_C][7] = qdev_get_gpio_in(ssddev, 0);
 
             /* Make sure the select pin is high.  */
             qemu_irq_raise(gpio_out[GPIO_D][0]);
@@ -1333,17 +1334,17 @@ static void stellaris_init(const char *kernel_filename, const char *cpu_model,
 }
 
 /* FIXME: Figure out how to generate these from stellaris_boards.  */
-static void lm3s811evb_init(QEMUMachineInitArgs *args)
+static void lm3s811evb_init(MachineState *machine)
 {
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
     stellaris_init(kernel_filename, cpu_model, &stellaris_boards[0]);
 }
 
-static void lm3s6965evb_init(QEMUMachineInitArgs *args)
+static void lm3s6965evb_init(MachineState *machine)
 {
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
     stellaris_init(kernel_filename, cpu_model, &stellaris_boards[1]);
 }
 

hw/arm/tosa.c

@@ -211,12 +211,12 @@ static struct arm_boot_info tosa_binfo = {
     .ram_size = 0x04000000,
 };
 
-static void tosa_init(QEMUMachineInitArgs *args)
+static void tosa_init(MachineState *machine)
 {
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
+    const char *kernel_cmdline = machine->kernel_cmdline;
+    const char *initrd_filename = machine->initrd_filename;
     MemoryRegion *address_space_mem = get_system_memory();
     MemoryRegion *rom = g_new(MemoryRegion, 1);
     PXA2xxState *mpu;

hw/arm/versatilepb.c

@@ -173,7 +173,7 @@ static int vpb_sic_init(SysBusDevice *sbd)
 
 static struct arm_boot_info versatile_binfo;
 
-static void versatile_init(QEMUMachineInitArgs *args, int board_id)
+static void versatile_init(MachineState *machine, int board_id)
 {
     ARMCPU *cpu;
     MemoryRegion *sysmem = get_system_memory();
@@ -190,15 +190,15 @@ static void versatile_init(QEMUMachineInitArgs *args, int board_id)
     int done_smc = 0;
     DriveInfo *dinfo;
 
-    if (!args->cpu_model) {
-        args->cpu_model = "arm926";
+    if (!machine->cpu_model) {
+        machine->cpu_model = "arm926";
     }
-    cpu = cpu_arm_init(args->cpu_model);
+    cpu = cpu_arm_init(machine->cpu_model);
     if (!cpu) {
         fprintf(stderr, "Unable to find CPU definition\n");
         exit(1);
     }
-    memory_region_init_ram(ram, NULL, "versatile.ram", args->ram_size);
+    memory_region_init_ram(ram, NULL, "versatile.ram", machine->ram_size);
     vmstate_register_ram_global(ram);
     /* ??? RAM should repeat to fill physical memory space.  */
     /* SDRAM at address zero.  */
@@ -344,22 +344,22 @@ static void versatile_init(QEMUMachineInitArgs *args, int board_id)
         fprintf(stderr, "qemu: Error registering flash memory.\n");
     }
 
-    versatile_binfo.ram_size = args->ram_size;
-    versatile_binfo.kernel_filename = args->kernel_filename;
-    versatile_binfo.kernel_cmdline = args->kernel_cmdline;
-    versatile_binfo.initrd_filename = args->initrd_filename;
+    versatile_binfo.ram_size = machine->ram_size;
+    versatile_binfo.kernel_filename = machine->kernel_filename;
+    versatile_binfo.kernel_cmdline = machine->kernel_cmdline;
+    versatile_binfo.initrd_filename = machine->initrd_filename;
     versatile_binfo.board_id = board_id;
     arm_load_kernel(cpu, &versatile_binfo);
 }
 
-static void vpb_init(QEMUMachineInitArgs *args)
+static void vpb_init(MachineState *machine)
 {
-    versatile_init(args, 0x183);
+    versatile_init(machine, 0x183);
 }
 
-static void vab_init(QEMUMachineInitArgs *args)
+static void vab_init(MachineState *machine)
 {
-    versatile_init(args, 0x25e);
+    versatile_init(machine, 0x25e);
 }
 
 static QEMUMachine versatilepb_machine = {

hw/arm/vexpress.c

@@ -28,6 +28,7 @@
 #include "net/net.h"
 #include "sysemu/sysemu.h"
 #include "hw/boards.h"
+#include "hw/loader.h"
 #include "exec/address-spaces.h"
 #include "sysemu/blockdev.h"
 #include "hw/block/flash.h"
@@ -509,7 +510,7 @@ static pflash_t *ve_pflash_cfi01_register(hwaddr base, const char *name,
 }
 
 static void vexpress_common_init(VEDBoardInfo *daughterboard,
-                                 QEMUMachineInitArgs *args)
+                                 MachineState *machine)
 {
     DeviceState *dev, *sysctl, *pl041;
     qemu_irq pic[64];
@@ -525,7 +526,20 @@ static void vexpress_common_init(VEDBoardInfo *daughterboard,
     const hwaddr *map = daughterboard->motherboard_map;
     int i;
 
-    daughterboard->init(daughterboard, args->ram_size, args->cpu_model, pic);
+    daughterboard->init(daughterboard, machine->ram_size, machine->cpu_model,
+                        pic);
+
+    /*
+     * If a bios file was provided, attempt to map it into memory
+     */
+    if (bios_name) {
+        const char *fn = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name);
+        if (!fn || load_image_targphys(fn, map[VE_NORFLASH0],
+                                       VEXPRESS_FLASH_SIZE) < 0) {
+            error_report("Could not load ROM image '%s'", bios_name);
+            exit(1);
+        }
+    }
 
     /* Motherboard peripherals: the wiring is the same but the
      * addresses vary between the legacy and A-Series memory maps.
@@ -639,10 +653,10 @@ static void vexpress_common_init(VEDBoardInfo *daughterboard,
                              pic[40 + i]);
     }
 
-    daughterboard->bootinfo.ram_size = args->ram_size;
-    daughterboard->bootinfo.kernel_filename = args->kernel_filename;
-    daughterboard->bootinfo.kernel_cmdline = args->kernel_cmdline;
-    daughterboard->bootinfo.initrd_filename = args->initrd_filename;
+    daughterboard->bootinfo.ram_size = machine->ram_size;
+    daughterboard->bootinfo.kernel_filename = machine->kernel_filename;
+    daughterboard->bootinfo.kernel_cmdline = machine->kernel_cmdline;
+    daughterboard->bootinfo.initrd_filename = machine->initrd_filename;
     daughterboard->bootinfo.nb_cpus = smp_cpus;
     daughterboard->bootinfo.board_id = VEXPRESS_BOARD_ID;
     daughterboard->bootinfo.loader_start = daughterboard->loader_start;
@@ -653,14 +667,14 @@ static void vexpress_common_init(VEDBoardInfo *daughterboard,
     arm_load_kernel(ARM_CPU(first_cpu), &daughterboard->bootinfo);
 }
 
-static void vexpress_a9_init(QEMUMachineInitArgs *args)
+static void vexpress_a9_init(MachineState *machine)
 {
-    vexpress_common_init(&a9_daughterboard, args);
+    vexpress_common_init(&a9_daughterboard, machine);
 }
 
-static void vexpress_a15_init(QEMUMachineInitArgs *args)
+static void vexpress_a15_init(MachineState *machine)
 {
-    vexpress_common_init(&a15_daughterboard, args);
+    vexpress_common_init(&a15_daughterboard, machine);
 }
 
 static QEMUMachine vexpress_a9_machine = {

hw/arm/virt.c

@@ -383,13 +383,13 @@ static void *machvirt_dtb(const struct arm_boot_info *binfo, int *fdt_size)
     return board->fdt;
 }
 
-static void machvirt_init(QEMUMachineInitArgs *args)
+static void machvirt_init(MachineState *machine)
 {
     qemu_irq pic[NUM_IRQS];
     MemoryRegion *sysmem = get_system_memory();
     int n;
     MemoryRegion *ram = g_new(MemoryRegion, 1);
-    const char *cpu_model = args->cpu_model;
+    const char *cpu_model = machine->cpu_model;
     VirtBoardInfo *vbi;
 
     if (!cpu_model) {
@@ -415,7 +415,7 @@ static void machvirt_init(QEMUMachineInitArgs *args)
         exit(1);
     }
 
-    if (args->ram_size > vbi->memmap[VIRT_MEM].size) {
+    if (machine->ram_size > vbi->memmap[VIRT_MEM].size) {
         error_report("mach-virt: cannot model more than 30GB RAM");
         exit(1);
     }
@@ -447,7 +447,7 @@ static void machvirt_init(QEMUMachineInitArgs *args)
     }
     fdt_add_cpu_nodes(vbi);
 
-    memory_region_init_ram(ram, NULL, "mach-virt.ram", args->ram_size);
+    memory_region_init_ram(ram, NULL, "mach-virt.ram", machine->ram_size);
     vmstate_register_ram_global(ram);
     memory_region_add_subregion(sysmem, vbi->memmap[VIRT_MEM].base, ram);
 
@@ -461,10 +461,10 @@ static void machvirt_init(QEMUMachineInitArgs *args)
      */
     create_virtio_devices(vbi, pic);
 
-    vbi->bootinfo.ram_size = args->ram_size;
-    vbi->bootinfo.kernel_filename = args->kernel_filename;
-    vbi->bootinfo.kernel_cmdline = args->kernel_cmdline;
-    vbi->bootinfo.initrd_filename = args->initrd_filename;
+    vbi->bootinfo.ram_size = machine->ram_size;
+    vbi->bootinfo.kernel_filename = machine->kernel_filename;
+    vbi->bootinfo.kernel_cmdline = machine->kernel_cmdline;
+    vbi->bootinfo.initrd_filename = machine->initrd_filename;
     vbi->bootinfo.nb_cpus = smp_cpus;
     vbi->bootinfo.board_id = -1;
     vbi->bootinfo.loader_start = vbi->memmap[VIRT_MEM].base;

hw/arm/xilinx_zynq.c

@@ -94,20 +94,20 @@ static inline void zynq_init_spi_flashes(uint32_t base_addr, qemu_irq irq,
         for (j = 0; j < num_ss; ++j) {
             flash_dev = ssi_create_slave(spi, "n25q128");
 
-            cs_line = qdev_get_gpio_in(flash_dev, 0);
+            cs_line = qdev_get_gpio_in_named(flash_dev, SSI_GPIO_CS, 0);
             sysbus_connect_irq(busdev, i * num_ss + j + 1, cs_line);
         }
     }
 
 }
 
-static void zynq_init(QEMUMachineInitArgs *args)
+static void zynq_init(MachineState *machine)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
+    ram_addr_t ram_size = machine->ram_size;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
+    const char *kernel_cmdline = machine->kernel_cmdline;
+    const char *initrd_filename = machine->initrd_filename;
     ObjectClass *cpu_oc;
     ARMCPU *cpu;
     MemoryRegion *address_space_mem = get_system_memory();

hw/arm/z2.c

@@ -300,12 +300,12 @@ static const TypeInfo aer915_info = {
     .class_init    = aer915_class_init,
 };
 
-static void z2_init(QEMUMachineInitArgs *args)
+static void z2_init(MachineState *machine)
 {
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
-    const char *initrd_filename = args->initrd_filename;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
+    const char *kernel_cmdline = machine->kernel_cmdline;
+    const char *initrd_filename = machine->initrd_filename;
     MemoryRegion *address_space_mem = get_system_memory();
     uint32_t sector_len = 0x10000;
     PXA2xxState *mpu;

hw/audio/intel-hda.c

@@ -245,7 +245,7 @@ static void intel_hda_update_int_sts(IntelHDAState *d)
 
     /* update global status */
     if (sts & d->int_ctl) {
-        sts |= (1 << 31);
+        sts |= (1U << 31);
     }
 
     d->int_sts = sts;
@@ -257,7 +257,7 @@ static void intel_hda_update_irq(IntelHDAState *d)
     int level;
 
     intel_hda_update_int_sts(d);
-    if (d->int_sts & (1 << 31) && d->int_ctl & (1 << 31)) {
+    if (d->int_sts & (1U << 31) && d->int_ctl & (1U << 31)) {
         level = 1;
     } else {
         level = 0;
@@ -574,7 +574,7 @@ static void intel_hda_set_st_ctl(IntelHDAState *d, const IntelHDAReg *reg, uint3
     if (st->ctl & 0x01) {
         /* reset */
         dprint(d, 1, "st #%d: reset\n", reg->stream);
-        st->ctl = 0;
+        st->ctl = SD_STS_FIFO_READY << 24;
     }
     if ((st->ctl & 0x02) != (old & 0x02)) {
         uint32_t stnr = (st->ctl >> 20) & 0x0f;
@@ -829,6 +829,7 @@ static const struct IntelHDAReg regtab[] = {
         .wclear   = 0x1c000000,                                       \
         .offset   = offsetof(IntelHDAState, st[_i].ctl),              \
         .whandler = intel_hda_set_st_ctl,                             \
+        .reset    = SD_STS_FIFO_READY << 24                           \
     },                                                                \
     [ ST_REG(_i, ICH6_REG_SD_LPIB) ] = {                              \
         .stream   = _i,                                               \

hw/block/dataplane/Makefile.objs

@@ -1 +1 @@
-obj-y += ioq.o virtio-blk.o
+obj-y += virtio-blk.o

hw/block/dataplane/ioq.c

@@ -1,117 +0,0 @@
-/*
- * Linux AIO request queue
- *
- * Copyright 2012 IBM, Corp.
- * Copyright 2012 Red Hat, Inc. and/or its affiliates
- *
- * Authors:
- *   Stefan Hajnoczi <stefanha@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 "ioq.h"
-
-void ioq_init(IOQueue *ioq, int fd, unsigned int max_reqs)
-{
-    int rc;
-
-    ioq->fd = fd;
-    ioq->max_reqs = max_reqs;
-
-    memset(&ioq->io_ctx, 0, sizeof ioq->io_ctx);
-    rc = io_setup(max_reqs, &ioq->io_ctx);
-    if (rc != 0) {
-        fprintf(stderr, "ioq io_setup failed %d\n", rc);
-        exit(1);
-    }
-
-    rc = event_notifier_init(&ioq->io_notifier, 0);
-    if (rc != 0) {
-        fprintf(stderr, "ioq io event notifier creation failed %d\n", rc);
-        exit(1);
-    }
-
-    ioq->freelist = g_malloc0(sizeof ioq->freelist[0] * max_reqs);
-    ioq->freelist_idx = 0;
-
-    ioq->queue = g_malloc0(sizeof ioq->queue[0] * max_reqs);
-    ioq->queue_idx = 0;
-}
-
-void ioq_cleanup(IOQueue *ioq)
-{
-    g_free(ioq->freelist);
-    g_free(ioq->queue);
-
-    event_notifier_cleanup(&ioq->io_notifier);
-    io_destroy(ioq->io_ctx);
-}
-
-EventNotifier *ioq_get_notifier(IOQueue *ioq)
-{
-    return &ioq->io_notifier;
-}
-
-struct iocb *ioq_get_iocb(IOQueue *ioq)
-{
-    /* Underflow cannot happen since ioq is sized for max_reqs */
-    assert(ioq->freelist_idx != 0);
-
-    struct iocb *iocb = ioq->freelist[--ioq->freelist_idx];
-    ioq->queue[ioq->queue_idx++] = iocb;
-    return iocb;
-}
-
-void ioq_put_iocb(IOQueue *ioq, struct iocb *iocb)
-{
-    /* Overflow cannot happen since ioq is sized for max_reqs */
-    assert(ioq->freelist_idx != ioq->max_reqs);
-
-    ioq->freelist[ioq->freelist_idx++] = iocb;
-}
-
-struct iocb *ioq_rdwr(IOQueue *ioq, bool read, struct iovec *iov,
-                      unsigned int count, long long offset)
-{
-    struct iocb *iocb = ioq_get_iocb(ioq);
-
-    if (read) {
-        io_prep_preadv(iocb, ioq->fd, iov, count, offset);
-    } else {
-        io_prep_pwritev(iocb, ioq->fd, iov, count, offset);
-    }
-    io_set_eventfd(iocb, event_notifier_get_fd(&ioq->io_notifier));
-    return iocb;
-}
-
-int ioq_submit(IOQueue *ioq)
-{
-    int rc = io_submit(ioq->io_ctx, ioq->queue_idx, ioq->queue);
-    ioq->queue_idx = 0; /* reset */
-    return rc;
-}
-
-int ioq_run_completion(IOQueue *ioq, IOQueueCompletion *completion,
-                       void *opaque)
-{
-    struct io_event events[ioq->max_reqs];
-    int nevents, i;
-
-    do {
-        nevents = io_getevents(ioq->io_ctx, 0, ioq->max_reqs, events, NULL);
-    } while (nevents < 0 && errno == EINTR);
-    if (nevents < 0) {
-        return nevents;
-    }
-
-    for (i = 0; i < nevents; i++) {
-        ssize_t ret = ((uint64_t)events[i].res2 << 32) | events[i].res;
-
-        completion(events[i].obj, ret, opaque);
-        ioq_put_iocb(ioq, events[i].obj);
-    }
-    return nevents;
-}

hw/block/dataplane/ioq.h

@@ -1,57 +0,0 @@
-/*
- * Linux AIO request queue
- *
- * Copyright 2012 IBM, Corp.
- * Copyright 2012 Red Hat, Inc. and/or its affiliates
- *
- * Authors:
- *   Stefan Hajnoczi <stefanha@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.
- *
- */
-
-#ifndef IOQ_H
-#define IOQ_H
-
-#include <libaio.h>
-#include "qemu/event_notifier.h"
-
-typedef struct {
-    int fd;                         /* file descriptor */
-    unsigned int max_reqs;          /* max length of freelist and queue */
-
-    io_context_t io_ctx;            /* Linux AIO context */
-    EventNotifier io_notifier;      /* Linux AIO eventfd */
-
-    /* Requests can complete in any order so a free list is necessary to manage
-     * available iocbs.
-     */
-    struct iocb **freelist;         /* free iocbs */
-    unsigned int freelist_idx;
-
-    /* Multiple requests are queued up before submitting them all in one go */
-    struct iocb **queue;            /* queued iocbs */
-    unsigned int queue_idx;
-} IOQueue;
-
-void ioq_init(IOQueue *ioq, int fd, unsigned int max_reqs);
-void ioq_cleanup(IOQueue *ioq);
-EventNotifier *ioq_get_notifier(IOQueue *ioq);
-struct iocb *ioq_get_iocb(IOQueue *ioq);
-void ioq_put_iocb(IOQueue *ioq, struct iocb *iocb);
-struct iocb *ioq_rdwr(IOQueue *ioq, bool read, struct iovec *iov,
-                      unsigned int count, long long offset);
-int ioq_submit(IOQueue *ioq);
-
-static inline unsigned int ioq_num_queued(IOQueue *ioq)
-{
-    return ioq->queue_idx;
-}
-
-typedef void IOQueueCompletion(struct iocb *iocb, ssize_t ret, void *opaque);
-int ioq_run_completion(IOQueue *ioq, IOQueueCompletion *completion,
-                       void *opaque);
-
-#endif /* IOQ_H */

hw/block/dataplane/virtio-blk.c

@@ -17,7 +17,6 @@
 #include "qemu/thread.h"
 #include "qemu/error-report.h"
 #include "hw/virtio/dataplane/vring.h"
-#include "ioq.h"
 #include "block/block.h"
 #include "hw/virtio/virtio-blk.h"
 #include "virtio-blk.h"
@@ -25,20 +24,14 @@
 #include "hw/virtio/virtio-bus.h"
 #include "qom/object_interfaces.h"
 
-enum {
-    SEG_MAX = 126,                  /* maximum number of I/O segments */
-    VRING_MAX = SEG_MAX + 2,        /* maximum number of vring descriptors */
-    REQ_MAX = VRING_MAX,            /* maximum number of requests in the vring,
-                                     * is VRING_MAX / 2 with traditional and
-                                     * VRING_MAX with indirect descriptors */
-};
-
 typedef struct {
-    struct iocb iocb;               /* Linux AIO control block */
+    VirtIOBlockDataPlane *s;
     QEMUIOVector *inhdr;            /* iovecs for virtio_blk_inhdr */
     VirtQueueElement *elem;         /* saved data from the virtqueue */
-    struct iovec *bounce_iov;       /* used if guest buffers are unaligned */
-    QEMUIOVector *read_qiov;        /* for read completion /w bounce buffer */
+    QEMUIOVector qiov;              /* original request iovecs */
+    struct iovec bounce_iov;        /* used if guest buffers are unaligned */
+    QEMUIOVector bounce_qiov;       /* bounce buffer iovecs */
+    bool read;                      /* read or write? */
 } VirtIOBlockRequest;
 
 struct VirtIOBlockDataPlane {
@@ -47,7 +40,6 @@ struct VirtIOBlockDataPlane {
     bool stopping;
 
     VirtIOBlkConf *blk;
-    int fd;                         /* image file descriptor */
 
     VirtIODevice *vdev;
     Vring vring;                    /* virtqueue vring */
@@ -61,15 +53,10 @@ struct VirtIOBlockDataPlane {
     IOThread *iothread;
     IOThread internal_iothread_obj;
     AioContext *ctx;
-    EventNotifier io_notifier;      /* Linux AIO completion */
     EventNotifier host_notifier;    /* doorbell */
 
-    IOQueue ioqueue;                /* Linux AIO queue (should really be per
-                                       IOThread) */
-    VirtIOBlockRequest requests[REQ_MAX]; /* pool of requests, managed by the
-                                             queue */
-
-    unsigned int num_reqs;
+    /* Operation blocker on BDS */
+    Error *blocker;
 };
 
 /* Raise an interrupt to signal guest, if necessary */
@@ -82,33 +69,28 @@ static void notify_guest(VirtIOBlockDataPlane *s)
     event_notifier_set(s->guest_notifier);
 }
 
-static void complete_request(struct iocb *iocb, ssize_t ret, void *opaque)
+static void complete_rdwr(void *opaque, int ret)
 {
-    VirtIOBlockDataPlane *s = opaque;
-    VirtIOBlockRequest *req = container_of(iocb, VirtIOBlockRequest, iocb);
+    VirtIOBlockRequest *req = opaque;
     struct virtio_blk_inhdr hdr;
     int len;
 
-    if (likely(ret >= 0)) {
+    if (likely(ret == 0)) {
         hdr.status = VIRTIO_BLK_S_OK;
-        len = ret;
+        len = req->qiov.size;
     } else {
         hdr.status = VIRTIO_BLK_S_IOERR;
         len = 0;
     }
 
-    trace_virtio_blk_data_plane_complete_request(s, req->elem->index, ret);
+    trace_virtio_blk_data_plane_complete_request(req->s, req->elem->index, ret);
 
-    if (req->read_qiov) {
-        assert(req->bounce_iov);
-        qemu_iovec_from_buf(req->read_qiov, 0, req->bounce_iov->iov_base, len);
-        qemu_iovec_destroy(req->read_qiov);
-        g_slice_free(QEMUIOVector, req->read_qiov);
+    if (req->read && req->bounce_iov.iov_base) {
+        qemu_iovec_from_buf(&req->qiov, 0, req->bounce_iov.iov_base, len);
     }
 
-    if (req->bounce_iov) {
-        qemu_vfree(req->bounce_iov->iov_base);
-        g_slice_free(struct iovec, req->bounce_iov);
+    if (req->bounce_iov.iov_base) {
+        qemu_vfree(req->bounce_iov.iov_base);
     }
 
     qemu_iovec_from_buf(req->inhdr, 0, &hdr, sizeof(hdr));
@@ -119,9 +101,9 @@ static void complete_request(struct iocb *iocb, ssize_t ret, void *opaque)
      * written to, but for virtio-blk it seems to be the number of bytes
      * transferred plus the status bytes.
      */
-    vring_push(&s->vring, req->elem, len + sizeof(hdr));
-    req->elem = NULL;
-    s->num_reqs--;
+    vring_push(&req->s->vring, req->elem, len + sizeof(hdr));
+    notify_guest(req->s);
+    g_slice_free(VirtIOBlockRequest, req);
 }
 
 static void complete_request_early(VirtIOBlockDataPlane *s, VirtQueueElement *elem,
@@ -152,51 +134,87 @@ static void do_get_id_cmd(VirtIOBlockDataPlane *s,
     complete_request_early(s, elem, inhdr, VIRTIO_BLK_S_OK);
 }
 
-static int do_rdwr_cmd(VirtIOBlockDataPlane *s, bool read,
-                       struct iovec *iov, unsigned iov_cnt,
-                       long long offset, VirtQueueElement *elem,
-                       QEMUIOVector *inhdr)
+static void do_rdwr_cmd(VirtIOBlockDataPlane *s, bool read,
+                        struct iovec *iov, unsigned iov_cnt,
+                        int64_t sector_num, VirtQueueElement *elem,
+                        QEMUIOVector *inhdr)
 {
-    struct iocb *iocb;
-    QEMUIOVector qiov;
-    struct iovec *bounce_iov = NULL;
-    QEMUIOVector *read_qiov = NULL;
+    VirtIOBlockRequest *req = g_slice_new0(VirtIOBlockRequest);
+    QEMUIOVector *qiov;
+    int nb_sectors;
 
-    qemu_iovec_init_external(&qiov, iov, iov_cnt);
-    if (!bdrv_qiov_is_aligned(s->blk->conf.bs, &qiov)) {
-        void *bounce_buffer = qemu_blockalign(s->blk->conf.bs, qiov.size);
+    /* Fill in virtio block metadata needed for completion */
+    req->s = s;
+    req->elem = elem;
+    req->inhdr = inhdr;
+    req->read = read;
+    qemu_iovec_init_external(&req->qiov, iov, iov_cnt);
 
-        if (read) {
-            /* Need to copy back from bounce buffer on completion */
-            read_qiov = g_slice_new(QEMUIOVector);
-            qemu_iovec_init(read_qiov, iov_cnt);
-            qemu_iovec_concat_iov(read_qiov, iov, iov_cnt, 0, qiov.size);
-        } else {
-            qemu_iovec_to_buf(&qiov, 0, bounce_buffer, qiov.size);
+    qiov = &req->qiov;
+
+    if (!bdrv_qiov_is_aligned(s->blk->conf.bs, qiov)) {
+        void *bounce_buffer = qemu_blockalign(s->blk->conf.bs, qiov->size);
+
+        /* Populate bounce buffer with data for writes */
+        if (!read) {
+            qemu_iovec_to_buf(qiov, 0, bounce_buffer, qiov->size);
         }
 
         /* Redirect I/O to aligned bounce buffer */
-        bounce_iov = g_slice_new(struct iovec);
-        bounce_iov->iov_base = bounce_buffer;
-        bounce_iov->iov_len = qiov.size;
-        iov = bounce_iov;
-        iov_cnt = 1;
+        req->bounce_iov.iov_base = bounce_buffer;
+        req->bounce_iov.iov_len = qiov->size;
+        qemu_iovec_init_external(&req->bounce_qiov, &req->bounce_iov, 1);
+        qiov = &req->bounce_qiov;
     }
 
-    iocb = ioq_rdwr(&s->ioqueue, read, iov, iov_cnt, offset);
+    nb_sectors = qiov->size / BDRV_SECTOR_SIZE;
 
-    /* Fill in virtio block metadata needed for completion */
-    VirtIOBlockRequest *req = container_of(iocb, VirtIOBlockRequest, iocb);
-    req->elem = elem;
-    req->inhdr = inhdr;
-    req->bounce_iov = bounce_iov;
-    req->read_qiov = read_qiov;
-    return 0;
+    if (read) {
+        bdrv_aio_readv(s->blk->conf.bs, sector_num, qiov, nb_sectors,
+                       complete_rdwr, req);
+    } else {
+        bdrv_aio_writev(s->blk->conf.bs, sector_num, qiov, nb_sectors,
+                        complete_rdwr, req);
+    }
 }
 
-static int process_request(IOQueue *ioq, VirtQueueElement *elem)
+static void complete_flush(void *opaque, int ret)
+{
+    VirtIOBlockRequest *req = opaque;
+    unsigned char status;
+
+    if (ret == 0) {
+        status = VIRTIO_BLK_S_OK;
+    } else {
+        status = VIRTIO_BLK_S_IOERR;
+    }
+
+    complete_request_early(req->s, req->elem, req->inhdr, status);
+    g_slice_free(VirtIOBlockRequest, req);
+}
+
+static void do_flush_cmd(VirtIOBlockDataPlane *s, VirtQueueElement *elem,
+                         QEMUIOVector *inhdr)
+{
+    VirtIOBlockRequest *req = g_slice_new(VirtIOBlockRequest);
+    req->s = s;
+    req->elem = elem;
+    req->inhdr = inhdr;
+
+    bdrv_aio_flush(s->blk->conf.bs, complete_flush, req);
+}
+
+static void do_scsi_cmd(VirtIOBlockDataPlane *s, VirtQueueElement *elem,
+                        QEMUIOVector *inhdr)
+{
+    int status;
+
+    status = virtio_blk_handle_scsi_req(VIRTIO_BLK(s->vdev), elem);
+    complete_request_early(s, elem, inhdr, status);
+}
+
+static int process_request(VirtIOBlockDataPlane *s, VirtQueueElement *elem)
 {
-    VirtIOBlockDataPlane *s = container_of(ioq, VirtIOBlockDataPlane, ioqueue);
     struct iovec *iov = elem->out_sg;
     struct iovec *in_iov = elem->in_sg;
     unsigned out_num = elem->out_num;
@@ -231,25 +249,23 @@ static int process_request(IOQueue *ioq, VirtQueueElement *elem)
 
     switch (outhdr.type) {
     case VIRTIO_BLK_T_IN:
-        do_rdwr_cmd(s, true, in_iov, in_num, outhdr.sector * 512, elem, inhdr);
+        do_rdwr_cmd(s, true, in_iov, in_num,
+                    outhdr.sector * 512 / BDRV_SECTOR_SIZE,
+                    elem, inhdr);
         return 0;
 
     case VIRTIO_BLK_T_OUT:
-        do_rdwr_cmd(s, false, iov, out_num, outhdr.sector * 512, elem, inhdr);
+        do_rdwr_cmd(s, false, iov, out_num,
+                    outhdr.sector * 512 / BDRV_SECTOR_SIZE,
+                    elem, inhdr);
         return 0;
 
     case VIRTIO_BLK_T_SCSI_CMD:
-        /* TODO support SCSI commands */
-        complete_request_early(s, elem, inhdr, VIRTIO_BLK_S_UNSUPP);
+        do_scsi_cmd(s, elem, inhdr);
         return 0;
 
     case VIRTIO_BLK_T_FLUSH:
-        /* TODO fdsync not supported by Linux AIO, do it synchronously here! */
-        if (qemu_fdatasync(s->fd) < 0) {
-            complete_request_early(s, elem, inhdr, VIRTIO_BLK_S_IOERR);
-        } else {
-            complete_request_early(s, elem, inhdr, VIRTIO_BLK_S_OK);
-        }
+        do_flush_cmd(s, elem, inhdr);
         return 0;
 
     case VIRTIO_BLK_T_GET_ID:
@@ -271,7 +287,6 @@ static void handle_notify(EventNotifier *e)
 
     VirtQueueElement *elem;
     int ret;
-    unsigned int num_queued;
 
     event_notifier_test_and_clear(&s->host_notifier);
     for (;;) {
@@ -288,7 +303,7 @@ static void handle_notify(EventNotifier *e)
             trace_virtio_blk_data_plane_process_request(s, elem->out_num,
                                                         elem->in_num, elem->index);
 
-            if (process_request(&s->ioqueue, elem) < 0) {
+            if (process_request(s, elem) < 0) {
                 vring_set_broken(&s->vring);
                 vring_free_element(elem);
                 ret = -EFAULT;
@@ -303,44 +318,10 @@ static void handle_notify(EventNotifier *e)
             if (vring_enable_notification(s->vdev, &s->vring)) {
                 break;
             }
-        } else { /* ret == -ENOBUFS or fatal error, iovecs[] is depleted */
-            /* Since there are no iovecs[] left, stop processing for now.  Do
-             * not re-enable guest->host notifies since the I/O completion
-             * handler knows to check for more vring descriptors anyway.
-             */
+        } else { /* fatal error */
             break;
         }
     }
-
-    num_queued = ioq_num_queued(&s->ioqueue);
-    if (num_queued > 0) {
-        s->num_reqs += num_queued;
-
-        int rc = ioq_submit(&s->ioqueue);
-        if (unlikely(rc < 0)) {
-            fprintf(stderr, "ioq_submit failed %d\n", rc);
-            exit(1);
-        }
-    }
-}
-
-static void handle_io(EventNotifier *e)
-{
-    VirtIOBlockDataPlane *s = container_of(e, VirtIOBlockDataPlane,
-                                           io_notifier);
-
-    event_notifier_test_and_clear(&s->io_notifier);
-    if (ioq_run_completion(&s->ioqueue, complete_request, s) > 0) {
-        notify_guest(s);
-    }
-
-    /* If there were more requests than iovecs, the vring will not be empty yet
-     * so check again.  There should now be enough resources to process more
-     * requests.
-     */
-    if (unlikely(vring_more_avail(&s->vring))) {
-        handle_notify(&s->host_notifier);
-    }
 }
 
 /* Context: QEMU global mutex held */
@@ -349,7 +330,7 @@ void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
                                   Error **errp)
 {
     VirtIOBlockDataPlane *s;
-    int fd;
+    Error *local_err = NULL;
 
     *dataplane = NULL;
 
@@ -357,37 +338,18 @@ void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
         return;
     }
 
-    if (blk->scsi) {
-        error_setg(errp,
-                   "device is incompatible with x-data-plane, use scsi=off");
-        return;
-    }
-
-    if (blk->config_wce) {
-        error_setg(errp, "device is incompatible with x-data-plane, "
-                         "use config-wce=off");
-        return;
-    }
-
     /* If dataplane is (re-)enabled while the guest is running there could be
      * block jobs that can conflict.
      */
-    if (bdrv_in_use(blk->conf.bs)) {
-        error_setg(errp,
-                   "cannot start dataplane thread while device is in use");
-        return;
-    }
-
-    fd = raw_get_aio_fd(blk->conf.bs);
-    if (fd < 0) {
-        error_setg(errp, "drive is incompatible with x-data-plane, "
-                         "use format=raw,cache=none,aio=native");
+    if (bdrv_op_is_blocked(blk->conf.bs, BLOCK_OP_TYPE_DATAPLANE, &local_err)) {
+        error_report("cannot start dataplane thread: %s",
+                      error_get_pretty(local_err));
+        error_free(local_err);
         return;
     }
 
     s = g_new0(VirtIOBlockDataPlane, 1);
     s->vdev = vdev;
-    s->fd = fd;
     s->blk = blk;
 
     if (blk->iothread) {
@@ -406,8 +368,8 @@ void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
     }
     s->ctx = iothread_get_aio_context(s->iothread);
 
-    /* Prevent block operations that conflict with data plane thread */
-    bdrv_set_in_use(blk->conf.bs, 1);
+    error_setg(&s->blocker, "block device is in use by data plane");
+    bdrv_op_block_all(blk->conf.bs, s->blocker);
 
     *dataplane = s;
 }
@@ -420,7 +382,8 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
     }
 
     virtio_blk_data_plane_stop(s);
-    bdrv_set_in_use(s->blk->conf.bs, 0);
+    bdrv_op_unblock_all(s->blk->conf.bs, s->blocker);
+    error_free(s->blocker);
     object_unref(OBJECT(s->iothread));
     g_free(s);
 }
@@ -431,7 +394,6 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s->vdev)));
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
     VirtQueue *vq;
-    int i;
 
     if (s->started) {
         return;
@@ -464,24 +426,18 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
     }
     s->host_notifier = *virtio_queue_get_host_notifier(vq);
 
-    /* Set up ioqueue */
-    ioq_init(&s->ioqueue, s->fd, REQ_MAX);
-    for (i = 0; i < ARRAY_SIZE(s->requests); i++) {
-        ioq_put_iocb(&s->ioqueue, &s->requests[i].iocb);
-    }
-    s->io_notifier = *ioq_get_notifier(&s->ioqueue);
-
     s->starting = false;
     s->started = true;
     trace_virtio_blk_data_plane_start(s);
 
+    bdrv_set_aio_context(s->blk->conf.bs, s->ctx);
+
     /* Kick right away to begin processing requests already in vring */
     event_notifier_set(virtio_queue_get_host_notifier(vq));
 
     /* Get this show started by hooking up our callbacks */
     aio_context_acquire(s->ctx);
     aio_set_event_notifier(s->ctx, &s->host_notifier, handle_notify);
-    aio_set_event_notifier(s->ctx, &s->io_notifier, handle_io);
     aio_context_release(s->ctx);
 }
 
@@ -501,13 +457,8 @@ void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
     /* Stop notifications for new requests from guest */
     aio_set_event_notifier(s->ctx, &s->host_notifier, NULL);
 
-    /* Complete pending requests */
-    while (s->num_reqs > 0) {
-        aio_poll(s->ctx, true);
-    }
-
-    /* Stop ioq callbacks (there are no pending requests left) */
-    aio_set_event_notifier(s->ctx, &s->io_notifier, NULL);
+    /* Drain and switch bs back to the QEMU main loop */
+    bdrv_set_aio_context(s->blk->conf.bs, qemu_get_aio_context());
 
     aio_context_release(s->ctx);
 
@@ -516,7 +467,6 @@ void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
      */
     vring_teardown(&s->vring, s->vdev, 0);
 
-    ioq_cleanup(&s->ioqueue);
     k->set_host_notifier(qbus->parent, 0, false);
 
     /* Clean up guest notifier (irq) */

hw/block/virtio-blk.c

@@ -33,7 +33,6 @@ typedef struct VirtIOBlockReq
     VirtQueueElement elem;
     struct virtio_blk_inhdr *in;
     struct virtio_blk_outhdr *out;
-    struct virtio_scsi_inhdr *scsi;
     QEMUIOVector qiov;
     struct VirtIOBlockReq *next;
     BlockAcctCookie acct;
@@ -125,13 +124,15 @@ static VirtIOBlockReq *virtio_blk_get_request(VirtIOBlock *s)
     return req;
 }
 
-static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
+int virtio_blk_handle_scsi_req(VirtIOBlock *blk,
+                               VirtQueueElement *elem)
 {
-#ifdef __linux__
-    int ret;
-    int i;
-#endif
     int status = VIRTIO_BLK_S_OK;
+    struct virtio_scsi_inhdr *scsi = NULL;
+#ifdef __linux__
+    int i;
+    struct sg_io_hdr hdr;
+#endif
 
     /*
      * We require at least one output segment each for the virtio_blk_outhdr
@@ -140,19 +141,18 @@ static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
      * We also at least require the virtio_blk_inhdr, the virtio_scsi_inhdr
      * and the sense buffer pointer in the input segments.
      */
-    if (req->elem.out_num < 2 || req->elem.in_num < 3) {
-        virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
-        g_free(req);
-        return;
+    if (elem->out_num < 2 || elem->in_num < 3) {
+        status = VIRTIO_BLK_S_IOERR;
+        goto fail;
     }
 
     /*
      * The scsi inhdr is placed in the second-to-last input segment, just
      * before the regular inhdr.
      */
-    req->scsi = (void *)req->elem.in_sg[req->elem.in_num - 2].iov_base;
+    scsi = (void *)elem->in_sg[elem->in_num - 2].iov_base;
 
-    if (!req->dev->blk.scsi) {
+    if (!blk->blk.scsi) {
         status = VIRTIO_BLK_S_UNSUPP;
         goto fail;
     }
@@ -160,43 +160,42 @@ static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
     /*
      * No support for bidirection commands yet.
      */
-    if (req->elem.out_num > 2 && req->elem.in_num > 3) {
+    if (elem->out_num > 2 && elem->in_num > 3) {
         status = VIRTIO_BLK_S_UNSUPP;
         goto fail;
     }
 
 #ifdef __linux__
-    struct sg_io_hdr hdr;
     memset(&hdr, 0, sizeof(struct sg_io_hdr));
     hdr.interface_id = 'S';
-    hdr.cmd_len = req->elem.out_sg[1].iov_len;
-    hdr.cmdp = req->elem.out_sg[1].iov_base;
+    hdr.cmd_len = elem->out_sg[1].iov_len;
+    hdr.cmdp = elem->out_sg[1].iov_base;
     hdr.dxfer_len = 0;
 
-    if (req->elem.out_num > 2) {
+    if (elem->out_num > 2) {
         /*
          * If there are more than the minimally required 2 output segments
          * there is write payload starting from the third iovec.
          */
         hdr.dxfer_direction = SG_DXFER_TO_DEV;
-        hdr.iovec_count = req->elem.out_num - 2;
+        hdr.iovec_count = elem->out_num - 2;
 
         for (i = 0; i < hdr.iovec_count; i++)
-            hdr.dxfer_len += req->elem.out_sg[i + 2].iov_len;
+            hdr.dxfer_len += elem->out_sg[i + 2].iov_len;
 
-        hdr.dxferp = req->elem.out_sg + 2;
+        hdr.dxferp = elem->out_sg + 2;
 
-    } else if (req->elem.in_num > 3) {
+    } else if (elem->in_num > 3) {
         /*
          * If we have more than 3 input segments the guest wants to actually
          * read data.
          */
         hdr.dxfer_direction = SG_DXFER_FROM_DEV;
-        hdr.iovec_count = req->elem.in_num - 3;
+        hdr.iovec_count = elem->in_num - 3;
         for (i = 0; i < hdr.iovec_count; i++)
-            hdr.dxfer_len += req->elem.in_sg[i].iov_len;
+            hdr.dxfer_len += elem->in_sg[i].iov_len;
 
-        hdr.dxferp = req->elem.in_sg;
+        hdr.dxferp = elem->in_sg;
     } else {
         /*
          * Some SCSI commands don't actually transfer any data.
@@ -204,11 +203,11 @@ static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
         hdr.dxfer_direction = SG_DXFER_NONE;
     }
 
-    hdr.sbp = req->elem.in_sg[req->elem.in_num - 3].iov_base;
-    hdr.mx_sb_len = req->elem.in_sg[req->elem.in_num - 3].iov_len;
+    hdr.sbp = elem->in_sg[elem->in_num - 3].iov_base;
+    hdr.mx_sb_len = elem->in_sg[elem->in_num - 3].iov_len;
 
-    ret = bdrv_ioctl(req->dev->bs, SG_IO, &hdr);
-    if (ret) {
+    status = bdrv_ioctl(blk->bs, SG_IO, &hdr);
+    if (status) {
         status = VIRTIO_BLK_S_UNSUPP;
         goto fail;
     }
@@ -224,23 +223,31 @@ static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
         hdr.status = CHECK_CONDITION;
     }
 
-    stl_p(&req->scsi->errors,
+    stl_p(&scsi->errors,
           hdr.status | (hdr.msg_status << 8) |
           (hdr.host_status << 16) | (hdr.driver_status << 24));
-    stl_p(&req->scsi->residual, hdr.resid);
-    stl_p(&req->scsi->sense_len, hdr.sb_len_wr);
-    stl_p(&req->scsi->data_len, hdr.dxfer_len);
+    stl_p(&scsi->residual, hdr.resid);
+    stl_p(&scsi->sense_len, hdr.sb_len_wr);
+    stl_p(&scsi->data_len, hdr.dxfer_len);
 
-    virtio_blk_req_complete(req, status);
-    g_free(req);
-    return;
+    return status;
 #else
     abort();
 #endif
 
 fail:
     /* Just put anything nonzero so that the ioctl fails in the guest.  */
-    stl_p(&req->scsi->errors, 255);
+    if (scsi) {
+        stl_p(&scsi->errors, 255);
+    }
+    return status;
+}
+
+static void virtio_blk_handle_scsi(VirtIOBlockReq *req)
+{
+    int status;
+
+    status = virtio_blk_handle_scsi_req(req->dev, &req->elem);
     virtio_blk_req_complete(req, status);
     g_free(req);
 }
@@ -487,12 +494,12 @@ static void virtio_blk_update_config(VirtIODevice *vdev, uint8_t *config)
 
     bdrv_get_geometry(s->bs, &capacity);
     memset(&blkcfg, 0, sizeof(blkcfg));
-    stq_raw(&blkcfg.capacity, capacity);
-    stl_raw(&blkcfg.seg_max, 128 - 2);
-    stw_raw(&blkcfg.cylinders, s->conf->cyls);
-    stl_raw(&blkcfg.blk_size, blk_size);
-    stw_raw(&blkcfg.min_io_size, s->conf->min_io_size / blk_size);
-    stw_raw(&blkcfg.opt_io_size, s->conf->opt_io_size / blk_size);
+    stq_p(&blkcfg.capacity, capacity);
+    stl_p(&blkcfg.seg_max, 128 - 2);
+    stw_p(&blkcfg.cylinders, s->conf->cyls);
+    stl_p(&blkcfg.blk_size, blk_size);
+    stw_p(&blkcfg.min_io_size, s->conf->min_io_size / blk_size);
+    stw_p(&blkcfg.opt_io_size, s->conf->opt_io_size / blk_size);
     blkcfg.heads = s->conf->heads;
     /*
      * We must ensure that the block device capacity is a multiple of
@@ -523,7 +530,10 @@ static void virtio_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
     struct virtio_blk_config blkcfg;
 
     memcpy(&blkcfg, config, sizeof(blkcfg));
+
+    aio_context_acquire(bdrv_get_aio_context(s->bs));
     bdrv_set_enable_write_cache(s->bs, blkcfg.wce != 0);
+    aio_context_release(bdrv_get_aio_context(s->bs));
 }
 
 static uint32_t virtio_blk_get_features(VirtIODevice *vdev, uint32_t features)
@@ -582,7 +592,10 @@ static void virtio_blk_set_status(VirtIODevice *vdev, uint8_t status)
      * s->bs would erroneously be placed in writethrough mode.
      */
     if (!(features & (1 << VIRTIO_BLK_F_CONFIG_WCE))) {
-        bdrv_set_enable_write_cache(s->bs, !!(features & (1 << VIRTIO_BLK_F_WCE)));
+        aio_context_acquire(bdrv_get_aio_context(s->bs));
+        bdrv_set_enable_write_cache(s->bs,
+                                    !!(features & (1 << VIRTIO_BLK_F_WCE)));
+        aio_context_release(bdrv_get_aio_context(s->bs));
     }
 }
 

hw/char/serial-pci.c

@@ -34,6 +34,7 @@
 typedef struct PCISerialState {
     PCIDevice dev;
     SerialState state;
+    uint8_t prog_if;
 } PCISerialState;
 
 typedef struct PCIMultiSerialState {
@@ -44,6 +45,7 @@ typedef struct PCIMultiSerialState {
     SerialState  state[PCI_SERIAL_MAX_PORTS];
     uint32_t     level[PCI_SERIAL_MAX_PORTS];
     qemu_irq     *irqs;
+    uint8_t      prog_if;
 } PCIMultiSerialState;
 
 static int serial_pci_init(PCIDevice *dev)
@@ -60,6 +62,7 @@ static int serial_pci_init(PCIDevice *dev)
         return -1;
     }
 
+    pci->dev.config[PCI_CLASS_PROG] = pci->prog_if;
     pci->dev.config[PCI_INTERRUPT_PIN] = 0x01;
     s->irq = pci_allocate_irq(&pci->dev);
 
@@ -101,6 +104,7 @@ static int multi_serial_pci_init(PCIDevice *dev)
     assert(pci->ports > 0);
     assert(pci->ports <= PCI_SERIAL_MAX_PORTS);
 
+    pci->dev.config[PCI_CLASS_PROG] = pci->prog_if;
     pci->dev.config[PCI_INTERRUPT_PIN] = 0x01;
     memory_region_init(&pci->iobar, OBJECT(pci), "multiserial", 8 * pci->ports);
     pci_register_bar(&pci->dev, 0, PCI_BASE_ADDRESS_SPACE_IO, &pci->iobar);
@@ -177,12 +181,14 @@ static const VMStateDescription vmstate_pci_multi_serial = {
 
 static Property serial_pci_properties[] = {
     DEFINE_PROP_CHR("chardev",  PCISerialState, state.chr),
+    DEFINE_PROP_UINT8("prog_if",  PCISerialState, prog_if, 0x02),
     DEFINE_PROP_END_OF_LIST(),
 };
 
 static Property multi_2x_serial_pci_properties[] = {
     DEFINE_PROP_CHR("chardev1",  PCIMultiSerialState, state[0].chr),
     DEFINE_PROP_CHR("chardev2",  PCIMultiSerialState, state[1].chr),
+    DEFINE_PROP_UINT8("prog_if",  PCIMultiSerialState, prog_if, 0x02),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -191,6 +197,7 @@ static Property multi_4x_serial_pci_properties[] = {
     DEFINE_PROP_CHR("chardev2",  PCIMultiSerialState, state[1].chr),
     DEFINE_PROP_CHR("chardev3",  PCIMultiSerialState, state[2].chr),
     DEFINE_PROP_CHR("chardev4",  PCIMultiSerialState, state[3].chr),
+    DEFINE_PROP_UINT8("prog_if",  PCIMultiSerialState, prog_if, 0x02),
     DEFINE_PROP_END_OF_LIST(),
 };
 

hw/char/xilinx_uartlite.c

@@ -87,6 +87,11 @@ static void uart_update_status(XilinxUARTLite *s)
     s->regs[R_STATUS] = r;
 }
 
+static void xilinx_uartlite_reset(DeviceState *dev)
+{
+    uart_update_status(XILINX_UARTLITE(dev));
+}
+
 static uint64_t
 uart_read(void *opaque, hwaddr addr, unsigned int size)
 {
@@ -196,34 +201,39 @@ static void uart_event(void *opaque, int event)
 
 }
 
-static int xilinx_uartlite_init(SysBusDevice *dev)
+static void xilinx_uartlite_realize(DeviceState *dev, Error **errp)
 {
     XilinxUARTLite *s = XILINX_UARTLITE(dev);
 
-    sysbus_init_irq(dev, &s->irq);
-
-    uart_update_status(s);
-    memory_region_init_io(&s->mmio, OBJECT(s), &uart_ops, s,
-                          "xlnx.xps-uartlite", R_MAX * 4);
-    sysbus_init_mmio(dev, &s->mmio);
-
     s->chr = qemu_char_get_next_serial();
     if (s->chr)
         qemu_chr_add_handlers(s->chr, uart_can_rx, uart_rx, uart_event, s);
-    return 0;
+}
+
+static void xilinx_uartlite_init(Object *obj)
+{
+    XilinxUARTLite *s = XILINX_UARTLITE(obj);
+
+    sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq);
+
+    memory_region_init_io(&s->mmio, obj, &uart_ops, s,
+                          "xlnx.xps-uartlite", R_MAX * 4);
+    sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->mmio);
 }
 
 static void xilinx_uartlite_class_init(ObjectClass *klass, void *data)
 {
-    SysBusDeviceClass *sdc = SYS_BUS_DEVICE_CLASS(klass);
+    DeviceClass *dc = DEVICE_CLASS(klass);
 
-    sdc->init = xilinx_uartlite_init;
+    dc->reset = xilinx_uartlite_reset;
+    dc->realize = xilinx_uartlite_realize;
 }
 
 static const TypeInfo xilinx_uartlite_info = {
     .name          = TYPE_XILINX_UARTLITE,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(XilinxUARTLite),
+    .instance_init = xilinx_uartlite_init,
     .class_init    = xilinx_uartlite_class_init,
 };
 

hw/core/machine.c

@@ -11,6 +11,284 @@
  */
 
 #include "hw/boards.h"
+#include "qapi/visitor.h"
+
+static char *machine_get_accel(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return g_strdup(ms->accel);
+}
+
+static void machine_set_accel(Object *obj, const char *value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->accel = g_strdup(value);
+}
+
+static bool machine_get_kernel_irqchip(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return ms->kernel_irqchip;
+}
+
+static void machine_set_kernel_irqchip(Object *obj, bool value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->kernel_irqchip = value;
+}
+
+static void machine_get_kvm_shadow_mem(Object *obj, Visitor *v,
+                                       void *opaque, const char *name,
+                                       Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+    int64_t value = ms->kvm_shadow_mem;
+
+    visit_type_int(v, &value, name, errp);
+}
+
+static void machine_set_kvm_shadow_mem(Object *obj, Visitor *v,
+                                       void *opaque, const char *name,
+                                       Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+    Error *error = NULL;
+    int64_t value;
+
+    visit_type_int(v, &value, name, &error);
+    if (error) {
+        error_propagate(errp, error);
+        return;
+    }
+
+    ms->kvm_shadow_mem = value;
+}
+
+static char *machine_get_kernel(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return g_strdup(ms->kernel_filename);
+}
+
+static void machine_set_kernel(Object *obj, const char *value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->kernel_filename = g_strdup(value);
+}
+
+static char *machine_get_initrd(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return g_strdup(ms->initrd_filename);
+}
+
+static void machine_set_initrd(Object *obj, const char *value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->initrd_filename = g_strdup(value);
+}
+
+static char *machine_get_append(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return g_strdup(ms->kernel_cmdline);
+}
+
+static void machine_set_append(Object *obj, const char *value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->kernel_cmdline = g_strdup(value);
+}
+
+static char *machine_get_dtb(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return g_strdup(ms->dtb);
+}
+
+static void machine_set_dtb(Object *obj, const char *value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->dtb = g_strdup(value);
+}
+
+static char *machine_get_dumpdtb(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return g_strdup(ms->dumpdtb);
+}
+
+static void machine_set_dumpdtb(Object *obj, const char *value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->dumpdtb = g_strdup(value);
+}
+
+static void machine_get_phandle_start(Object *obj, Visitor *v,
+                                       void *opaque, const char *name,
+                                       Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+    int64_t value = ms->phandle_start;
+
+    visit_type_int(v, &value, name, errp);
+}
+
+static void machine_set_phandle_start(Object *obj, Visitor *v,
+                                       void *opaque, const char *name,
+                                       Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+    Error *error = NULL;
+    int64_t value;
+
+    visit_type_int(v, &value, name, &error);
+    if (error) {
+        error_propagate(errp, error);
+        return;
+    }
+
+    ms->phandle_start = value;
+}
+
+static char *machine_get_dt_compatible(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return g_strdup(ms->dt_compatible);
+}
+
+static void machine_set_dt_compatible(Object *obj, const char *value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->dt_compatible = g_strdup(value);
+}
+
+static bool machine_get_dump_guest_core(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return ms->dump_guest_core;
+}
+
+static void machine_set_dump_guest_core(Object *obj, bool value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->dump_guest_core = value;
+}
+
+static bool machine_get_mem_merge(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return ms->mem_merge;
+}
+
+static void machine_set_mem_merge(Object *obj, bool value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->mem_merge = value;
+}
+
+static bool machine_get_usb(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return ms->usb;
+}
+
+static void machine_set_usb(Object *obj, bool value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->usb = value;
+}
+
+static char *machine_get_firmware(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return g_strdup(ms->firmware);
+}
+
+static void machine_set_firmware(Object *obj, const char *value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->firmware = g_strdup(value);
+}
+
+static void machine_initfn(Object *obj)
+{
+    object_property_add_str(obj, "accel",
+                            machine_get_accel, machine_set_accel, NULL);
+    object_property_add_bool(obj, "kernel_irqchip",
+                             machine_get_kernel_irqchip,
+                             machine_set_kernel_irqchip,
+                             NULL);
+    object_property_add(obj, "kvm_shadow_mem", "int",
+                        machine_get_kvm_shadow_mem,
+                        machine_set_kvm_shadow_mem,
+                        NULL, NULL, NULL);
+    object_property_add_str(obj, "kernel",
+                            machine_get_kernel, machine_set_kernel, NULL);
+    object_property_add_str(obj, "initrd",
+                            machine_get_initrd, machine_set_initrd, NULL);
+    object_property_add_str(obj, "append",
+                            machine_get_append, machine_set_append, NULL);
+    object_property_add_str(obj, "dtb",
+                            machine_get_dtb, machine_set_dtb, NULL);
+    object_property_add_str(obj, "dumpdtb",
+                            machine_get_dumpdtb, machine_set_dumpdtb, NULL);
+    object_property_add(obj, "phandle_start", "int",
+                        machine_get_phandle_start,
+                        machine_set_phandle_start,
+                        NULL, NULL, NULL);
+    object_property_add_str(obj, "dt_compatible",
+                            machine_get_dt_compatible,
+                            machine_set_dt_compatible,
+                            NULL);
+    object_property_add_bool(obj, "dump-guest-core",
+                             machine_get_dump_guest_core,
+                             machine_set_dump_guest_core,
+                             NULL);
+    object_property_add_bool(obj, "mem-merge",
+                             machine_get_mem_merge, machine_set_mem_merge, NULL);
+    object_property_add_bool(obj, "usb", machine_get_usb, machine_set_usb, NULL);
+    object_property_add_str(obj, "firmware",
+                            machine_get_firmware, machine_set_firmware, NULL);
+}
+
+static void machine_finalize(Object *obj)
+{
+    MachineState *ms = MACHINE(obj);
+
+    g_free(ms->accel);
+    g_free(ms->kernel_filename);
+    g_free(ms->initrd_filename);
+    g_free(ms->kernel_cmdline);
+    g_free(ms->dtb);
+    g_free(ms->dumpdtb);
+    g_free(ms->dt_compatible);
+    g_free(ms->firmware);
+}
 
 static const TypeInfo machine_info = {
     .name = TYPE_MACHINE,
@@ -18,6 +296,8 @@ static const TypeInfo machine_info = {
     .abstract = true,
     .class_size = sizeof(MachineClass),
     .instance_size = sizeof(MachineState),
+    .instance_init = machine_initfn,
+    .instance_finalize = machine_finalize,
 };
 
 static void machine_register_types(void)

hw/core/null-machine.c

@@ -15,7 +15,7 @@
 #include "hw/hw.h"
 #include "hw/boards.h"
 
-static void machine_none_init(QEMUMachineInitArgs *args)
+static void machine_none_init(MachineState *machine)
 {
 }
 

hw/core/qdev-properties-system.c

@@ -439,11 +439,27 @@ PropertyInfo qdev_prop_iothread = {
 static int qdev_add_one_global(QemuOpts *opts, void *opaque)
 {
     GlobalProperty *g;
+    ObjectClass *oc;
 
     g = g_malloc0(sizeof(*g));
     g->driver   = qemu_opt_get(opts, "driver");
     g->property = qemu_opt_get(opts, "property");
     g->value    = qemu_opt_get(opts, "value");
+    oc = object_class_by_name(g->driver);
+    if (oc) {
+        DeviceClass *dc = DEVICE_CLASS(oc);
+
+        if (dc->hotpluggable) {
+            /* If hotpluggable then skip not_used checking. */
+            g->not_used = false;
+        } else {
+            /* Maybe a typo. */
+            g->not_used = true;
+        }
+    } else {
+        /* Maybe a typo. */
+        g->not_used = true;
+    }
     qdev_prop_register_global(g);
     return 0;
 }

hw/core/qdev-properties.c

@@ -955,6 +955,23 @@ void qdev_prop_register_global_list(GlobalProperty *props)
     }
 }
 
+int qdev_prop_check_global(void)
+{
+    GlobalProperty *prop;
+    int ret = 0;
+
+    QTAILQ_FOREACH(prop, &global_props, next) {
+        if (!prop->not_used) {
+            continue;
+        }
+        ret = 1;
+        error_report("Warning: \"-global %s.%s=%s\" not used",
+                     prop->driver, prop->property, prop->value);
+
+    }
+    return ret;
+}
+
 void qdev_prop_set_globals_for_type(DeviceState *dev, const char *typename,
                                     Error **errp)
 {
@@ -966,6 +983,7 @@ void qdev_prop_set_globals_for_type(DeviceState *dev, const char *typename,
         if (strcmp(typename, prop->driver) != 0) {
             continue;
         }
+        prop->not_used = false;
         object_property_parse(OBJECT(dev), prop->value, prop->property, &err);
         if (err != NULL) {
             error_propagate(errp, err);

hw/core/qdev.c

@@ -312,30 +312,82 @@ BusState *qdev_get_parent_bus(DeviceState *dev)
     return dev->parent_bus;
 }
 
+static NamedGPIOList *qdev_get_named_gpio_list(DeviceState *dev,
+                                               const char *name)
+{
+    NamedGPIOList *ngl;
+
+    QLIST_FOREACH(ngl, &dev->gpios, node) {
+        /* NULL is a valid and matchable name, otherwise do a normal
+         * strcmp match.
+         */
+        if ((!ngl->name && !name) ||
+                (name && ngl->name && strcmp(name, ngl->name) == 0)) {
+            return ngl;
+        }
+    }
+
+    ngl = g_malloc0(sizeof(*ngl));
+    ngl->name = g_strdup(name);
+    QLIST_INSERT_HEAD(&dev->gpios, ngl, node);
+    return ngl;
+}
+
+void qdev_init_gpio_in_named(DeviceState *dev, qemu_irq_handler handler,
+                             const char *name, int n)
+{
+    NamedGPIOList *gpio_list = qdev_get_named_gpio_list(dev, name);
+
+    gpio_list->in = qemu_extend_irqs(gpio_list->in, gpio_list->num_in, handler,
+                                     dev, n);
+    gpio_list->num_in += n;
+}
+
 void qdev_init_gpio_in(DeviceState *dev, qemu_irq_handler handler, int n)
 {
-    dev->gpio_in = qemu_extend_irqs(dev->gpio_in, dev->num_gpio_in, handler,
-                                        dev, n);
-    dev->num_gpio_in += n;
+    qdev_init_gpio_in_named(dev, handler, NULL, n);
+}
+
+void qdev_init_gpio_out_named(DeviceState *dev, qemu_irq *pins,
+                              const char *name, int n)
+{
+    NamedGPIOList *gpio_list = qdev_get_named_gpio_list(dev, name);
+
+    assert(gpio_list->num_out == 0);
+    gpio_list->num_out = n;
+    gpio_list->out = pins;
 }
 
 void qdev_init_gpio_out(DeviceState *dev, qemu_irq *pins, int n)
 {
-    assert(dev->num_gpio_out == 0);
-    dev->num_gpio_out = n;
-    dev->gpio_out = pins;
+    qdev_init_gpio_out_named(dev, pins, NULL, n);
+}
+
+qemu_irq qdev_get_gpio_in_named(DeviceState *dev, const char *name, int n)
+{
+    NamedGPIOList *gpio_list = qdev_get_named_gpio_list(dev, name);
+
+    assert(n >= 0 && n < gpio_list->num_in);
+    return gpio_list->in[n];
 }
 
 qemu_irq qdev_get_gpio_in(DeviceState *dev, int n)
 {
-    assert(n >= 0 && n < dev->num_gpio_in);
-    return dev->gpio_in[n];
+    return qdev_get_gpio_in_named(dev, NULL, n);
+}
+
+void qdev_connect_gpio_out_named(DeviceState *dev, const char *name, int n,
+                                 qemu_irq pin)
+{
+    NamedGPIOList *gpio_list = qdev_get_named_gpio_list(dev, name);
+
+    assert(n >= 0 && n < gpio_list->num_out);
+    gpio_list->out[n] = pin;
 }
 
 void qdev_connect_gpio_out(DeviceState * dev, int n, qemu_irq pin)
 {
-    assert(n >= 0 && n < dev->num_gpio_out);
-    dev->gpio_out[n] = pin;
+    qdev_connect_gpio_out_named(dev, NULL, n, pin);
 }
 
 BusState *qdev_get_child_bus(DeviceState *dev, const char *name)
@@ -844,6 +896,7 @@ static void device_initfn(Object *obj)
     object_property_add_link(OBJECT(dev), "parent_bus", TYPE_BUS,
                              (Object **)&dev->parent_bus, NULL, 0,
                              &error_abort);
+    QLIST_INIT(&dev->gpios);
 }
 
 static void device_post_init(Object *obj)
@@ -854,10 +907,22 @@ static void device_post_init(Object *obj)
 /* Unlink device from bus and free the structure.  */
 static void device_finalize(Object *obj)
 {
+    NamedGPIOList *ngl, *next;
+
     DeviceState *dev = DEVICE(obj);
     if (dev->opts) {
         qemu_opts_del(dev->opts);
     }
+
+    QLIST_FOREACH_SAFE(ngl, &dev->gpios, node, next) {
+        QLIST_REMOVE(ngl, node);
+        qemu_free_irqs(ngl->in);
+        g_free(ngl->name);
+        g_free(ngl);
+        /* ngl->out irqs are owned by the other end and should not be freed
+         * here
+         */
+    }
 }
 
 static void device_class_base_init(ObjectClass *class, void *data)

hw/cris/axis_dev88.c

@@ -243,12 +243,12 @@ static const MemoryRegionOps gpio_ops = {
 static struct cris_load_info li;
 
 static
-void axisdev88_init(QEMUMachineInitArgs *args)
+void axisdev88_init(MachineState *machine)
 {
-    ram_addr_t ram_size = args->ram_size;
-    const char *cpu_model = args->cpu_model;
-    const char *kernel_filename = args->kernel_filename;
-    const char *kernel_cmdline = args->kernel_cmdline;
+    ram_addr_t ram_size = machine->ram_size;
+    const char *cpu_model = machine->cpu_model;
+    const char *kernel_filename = machine->kernel_filename;
+    const char *kernel_cmdline = machine->kernel_cmdline;
     CRISCPU *cpu;
     CPUCRISState *env;
     DeviceState *dev;

hw/display/cg3.c

@@ -177,7 +177,7 @@ static uint64_t cg3_reg_read(void *opaque, hwaddr addr, unsigned size)
         /* monitor ID 6, board type = 1 (color) */
         val = s->regs[1] | CG3_SR_1152_900_76_B | CG3_SR_ID_COLOR;
         break;
-    case CG3_REG_FBC_CURSTART ... CG3_REG_SIZE:
+    case CG3_REG_FBC_CURSTART ... CG3_REG_SIZE - 1:
         val = s->regs[addr - 0x10];
         break;
     default:
@@ -247,7 +247,7 @@ static void cg3_reg_write(void *opaque, hwaddr addr, uint64_t val,
             qemu_irq_lower(s->irq);
         }
         break;
-    case CG3_REG_FBC_CURSTART ... CG3_REG_SIZE:
+    case CG3_REG_FBC_CURSTART ... CG3_REG_SIZE - 1:
         s->regs[addr - 0x10] = val;
         break;
     default:
@@ -274,6 +274,20 @@ static const GraphicHwOps cg3_ops = {
     .gfx_update = cg3_update_display,
 };
 
+static void cg3_initfn(Object *obj)
+{
+    SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
+    CG3State *s = CG3(obj);
+
+    memory_region_init_ram(&s->rom, NULL, "cg3.prom", FCODE_MAX_ROM_SIZE);
+    memory_region_set_readonly(&s->rom, true);
+    sysbus_init_mmio(sbd, &s->rom);
+
+    memory_region_init_io(&s->reg, NULL, &cg3_reg_ops, s, "cg3.reg",
+                          CG3_REG_SIZE);
+    sysbus_init_mmio(sbd, &s->reg);
+}
+
 static void cg3_realizefn(DeviceState *dev, Error **errp)
 {
     SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
@@ -282,11 +296,7 @@ static void cg3_realizefn(DeviceState *dev, Error **errp)
     char *fcode_filename;
 
     /* FCode ROM */
-    memory_region_init_ram(&s->rom, NULL, "cg3.prom", FCODE_MAX_ROM_SIZE);
     vmstate_register_ram_global(&s->rom);
-    memory_region_set_readonly(&s->rom, true);
-    sysbus_init_mmio(sbd, &s->rom);
-
     fcode_filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, CG3_ROM_FILE);
     if (fcode_filename) {
         ret = load_image_targphys(fcode_filename, s->prom_addr,
@@ -296,10 +306,6 @@ static void cg3_realizefn(DeviceState *dev, Error **errp)
         }
     }
 
-    memory_region_init_io(&s->reg, NULL, &cg3_reg_ops, s, "cg3.reg",
-                          CG3_REG_SIZE);
-    sysbus_init_mmio(sbd, &s->reg);
-
     memory_region_init_ram(&s->vram_mem, NULL, "cg3.vram", s->vram_size);
     vmstate_register_ram_global(&s->vram_mem);
     sysbus_init_mmio(sbd, &s->vram_mem);
@@ -374,6 +380,7 @@ static const TypeInfo cg3_info = {
     .name          = TYPE_CG3,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(CG3State),
+    .instance_init = cg3_initfn,
     .class_init    = cg3_class_init,
 };
 

hw/display/jazz_led.c

@@ -173,6 +173,7 @@ static void jazz_led_update_display(void *opaque)
             case 16:
                 color_segment = rgb_to_pixel16(0xaa, 0xaa, 0xaa);
                 color_led = rgb_to_pixel16(0x00, 0xff, 0x00);
+                break;
             case 24:
                 color_segment = rgb_to_pixel24(0xaa, 0xaa, 0xaa);
                 color_led = rgb_to_pixel24(0x00, 0xff, 0x00);

hw/display/omap_lcd_template.h

@@ -50,7 +50,7 @@ static void glue(draw_line2_, DEPTH)(void *opaque,
     uint8_t v, r, g, b;
 
     do {
-        v = ldub_raw((void *) s);
+        v = ldub_p((void *) s);
         r = (pal[v & 3] >> 4) & 0xf0;
         g = pal[v & 3] & 0xf0;
         b = (pal[v & 3] << 4) & 0xf0;
@@ -89,7 +89,7 @@ static void glue(draw_line4_, DEPTH)(void *opaque,
     uint8_t v, r, g, b;
 
     do {
-        v = ldub_raw((void *) s);
+        v = ldub_p((void *) s);
         r = (pal[v & 0xf] >> 4) & 0xf0;
         g = pal[v & 0xf] & 0xf0;
         b = (pal[v & 0xf] << 4) & 0xf0;
@@ -116,7 +116,7 @@ static void glue(draw_line8_, DEPTH)(void *opaque,
     uint8_t v, r, g, b;
 
     do {
-        v = ldub_raw((void *) s);
+        v = ldub_p((void *) s);
         r = (pal[v] >> 4) & 0xf0;
         g = pal[v] & 0xf0;
         b = (pal[v] << 4) & 0xf0;
@@ -136,7 +136,7 @@ static void glue(draw_line12_, DEPTH)(void *opaque,
     uint8_t r, g, b;
 
     do {
-        v = lduw_raw((void *) s);
+        v = lduw_p((void *) s);
         r = (v >> 4) & 0xf0;
         g = v & 0xf0;
         b = (v << 4) & 0xf0;
@@ -159,7 +159,7 @@ static void glue(draw_line16_, DEPTH)(void *opaque,
     uint8_t r, g, b;
 
     do {
-        v = lduw_raw((void *) s);
+        v = lduw_p((void *) s);
         r = (v >> 8) & 0xf8;
         g = (v >> 3) & 0xfc;
         b = (v << 3) & 0xf8;

hw/display/pxa2xx_lcd.c

@@ -620,17 +620,6 @@ static void pxa2xx_palette_parse(PXA2xxLCDState *s, int ch, int bpp)
             src += 2;
             break;
         case 1: /* 16 bpp plus transparency */
-            alpha = *(uint16_t *) src & (1 << 24);
-            if (s->control[0] & LCCR0_CMS)
-                r = g = b = *(uint16_t *) src & 0xff;
-            else {
-                r = (*(uint16_t *) src & 0xf800) >> 8;
-                g = (*(uint16_t *) src & 0x07e0) >> 3;
-                b = (*(uint16_t *) src & 0x001f) << 3;
-            }
-            src += 2;
-            break;
-        case 2: /* 18 bpp plus transparency */
             alpha = *(uint32_t *) src & (1 << 24);
             if (s->control[0] & LCCR0_CMS)
                 r = g = b = *(uint32_t *) src & 0xff;
@@ -641,6 +630,17 @@ static void pxa2xx_palette_parse(PXA2xxLCDState *s, int ch, int bpp)
             }
             src += 4;
             break;
+        case 2: /* 18 bpp plus transparency */
+            alpha = *(uint32_t *) src & (1 << 24);
+            if (s->control[0] & LCCR0_CMS)
+                r = g = b = *(uint32_t *) src & 0xff;
+            else {
+                r = (*(uint32_t *) src & 0xfc0000) >> 16;
+                g = (*(uint32_t *) src & 0x00fc00) >> 8;
+                b = (*(uint32_t *) src & 0x0000fc);
+            }
+            src += 4;
+            break;
         case 3: /* 24 bpp plus transparency */
             alpha = *(uint32_t *) src & (1 << 24);
             if (s->control[0] & LCCR0_CMS)

hw/display/sm501_template.h

@@ -47,7 +47,7 @@ static void glue(draw_line8_, PIXEL_NAME)(
 {
     uint8_t v, r, g, b;
     do {
-      	v = ldub_raw(s);
+	v = ldub_p(s);
 	r = (pal[v] >> 16) & 0xff;
 	g = (pal[v] >>  8) & 0xff;
 	b = (pal[v] >>  0) & 0xff;
@@ -64,7 +64,7 @@ static void glue(draw_line16_, PIXEL_NAME)(
     uint8_t r, g, b;
 
     do {
-	rgb565 = lduw_raw(s);
+	rgb565 = lduw_p(s);
 	r = ((rgb565 >> 11) & 0x1f) << 3;
 	g = ((rgb565 >>  5) & 0x3f) << 2;
 	b = ((rgb565 >>  0) & 0x1f) << 3;
@@ -80,7 +80,7 @@ static void glue(draw_line32_, PIXEL_NAME)(
     uint8_t r, g, b;
 
     do {
-	ldub_raw(s);
+	ldub_p(s);
 #if defined(TARGET_WORDS_BIGENDIAN)
         r = s[1];
         g = s[2];

hw/display/tcx.c

@@ -530,8 +530,36 @@ static const GraphicHwOps tcx24_ops = {
     .gfx_update = tcx24_update_display,
 };
 
-static int tcx_init1(SysBusDevice *dev)
+static void tcx_initfn(Object *obj)
 {
+    SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
+    TCXState *s = TCX(obj);
+
+    memory_region_init_ram(&s->rom, NULL, "tcx.prom", FCODE_MAX_ROM_SIZE);
+    memory_region_set_readonly(&s->rom, true);
+    sysbus_init_mmio(sbd, &s->rom);
+
+    /* DAC */
+    memory_region_init_io(&s->dac, OBJECT(s), &tcx_dac_ops, s,
+                          "tcx.dac", TCX_DAC_NREGS);
+    sysbus_init_mmio(sbd, &s->dac);
+
+    /* TEC (dummy) */
+    memory_region_init_io(&s->tec, OBJECT(s), &dummy_ops, s,
+                          "tcx.tec", TCX_TEC_NREGS);
+    sysbus_init_mmio(sbd, &s->tec);
+
+    /* THC: NetBSD writes here even with 8-bit display: dummy */
+    memory_region_init_io(&s->thc24, OBJECT(s), &dummy_ops, s, "tcx.thc24",
+                          TCX_THC_NREGS_24);
+    sysbus_init_mmio(sbd, &s->thc24);
+
+    return;
+}
+
+static void tcx_realizefn(DeviceState *dev, Error **errp)
+{
+    SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
     TCXState *s = TCX(dev);
     ram_addr_t vram_offset = 0;
     int size, ret;
@@ -544,18 +572,13 @@ static int tcx_init1(SysBusDevice *dev)
     vram_base = memory_region_get_ram_ptr(&s->vram_mem);
 
     /* FCode ROM */
-    memory_region_init_ram(&s->rom, NULL, "tcx.prom", FCODE_MAX_ROM_SIZE);
     vmstate_register_ram_global(&s->rom);
-    memory_region_set_readonly(&s->rom, true);
-    sysbus_init_mmio(dev, &s->rom);
-
     fcode_filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, TCX_ROM_FILE);
     if (fcode_filename) {
         ret = load_image_targphys(fcode_filename, s->prom_addr,
                                   FCODE_MAX_ROM_SIZE);
         if (ret < 0 || ret > FCODE_MAX_ROM_SIZE) {
-            fprintf(stderr, "tcx: could not load prom '%s'\n", TCX_ROM_FILE);
-            return -1;
+            error_report("tcx: could not load prom '%s'", TCX_ROM_FILE);
         }
     }
 
@@ -564,24 +587,10 @@ static int tcx_init1(SysBusDevice *dev)
     size = s->vram_size;
     memory_region_init_alias(&s->vram_8bit, OBJECT(s), "tcx.vram.8bit",
                              &s->vram_mem, vram_offset, size);
-    sysbus_init_mmio(dev, &s->vram_8bit);
+    sysbus_init_mmio(sbd, &s->vram_8bit);
     vram_offset += size;
     vram_base += size;
 
-    /* DAC */
-    memory_region_init_io(&s->dac, OBJECT(s), &tcx_dac_ops, s,
-                          "tcx.dac", TCX_DAC_NREGS);
-    sysbus_init_mmio(dev, &s->dac);
-
-    /* TEC (dummy) */
-    memory_region_init_io(&s->tec, OBJECT(s), &dummy_ops, s,
-                          "tcx.tec", TCX_TEC_NREGS);
-    sysbus_init_mmio(dev, &s->tec);
-    /* THC: NetBSD writes here even with 8-bit display: dummy */
-    memory_region_init_io(&s->thc24, OBJECT(s), &dummy_ops, s, "tcx.thc24",
-                          TCX_THC_NREGS_24);
-    sysbus_init_mmio(dev, &s->thc24);
-
     if (s->depth == 24) {
         /* 24-bit plane */
         size = s->vram_size * 4;
@@ -589,7 +598,7 @@ static int tcx_init1(SysBusDevice *dev)
         s->vram24_offset = vram_offset;
         memory_region_init_alias(&s->vram_24bit, OBJECT(s), "tcx.vram.24bit",
                                  &s->vram_mem, vram_offset, size);
-        sysbus_init_mmio(dev, &s->vram_24bit);
+        sysbus_init_mmio(sbd, &s->vram_24bit);
         vram_offset += size;
         vram_base += size;
 
@@ -599,20 +608,19 @@ static int tcx_init1(SysBusDevice *dev)
         s->cplane_offset = vram_offset;
         memory_region_init_alias(&s->vram_cplane, OBJECT(s), "tcx.vram.cplane",
                                  &s->vram_mem, vram_offset, size);
-        sysbus_init_mmio(dev, &s->vram_cplane);
+        sysbus_init_mmio(sbd, &s->vram_cplane);
 
         s->con = graphic_console_init(DEVICE(dev), 0, &tcx24_ops, s);
     } else {
         /* THC 8 bit (dummy) */
         memory_region_init_io(&s->thc8, OBJECT(s), &dummy_ops, s, "tcx.thc8",
                               TCX_THC_NREGS_8);
-        sysbus_init_mmio(dev, &s->thc8);
+        sysbus_init_mmio(sbd, &s->thc8);
 
         s->con = graphic_console_init(DEVICE(dev), 0, &tcx_ops, s);
     }
 
     qemu_console_resize(s->con, s->width, s->height);
-    return 0;
 }
 
 static Property tcx_properties[] = {
@@ -627,9 +635,8 @@ static Property tcx_properties[] = {
 static void tcx_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
-    SysBusDeviceClass *k = SYS_BUS_DEVICE_CLASS(klass);
 
-    k->init = tcx_init1;
+    dc->realize = tcx_realizefn;
     dc->reset = tcx_reset;
     dc->vmsd = &vmstate_tcx;
     dc->props = tcx_properties;
@@ -639,6 +646,7 @@ static const TypeInfo tcx_info = {
     .name          = TYPE_TCX,
     .parent        = TYPE_SYS_BUS_DEVICE,
     .instance_size = sizeof(TCXState),
+    .instance_init = tcx_initfn,
     .class_init    = tcx_class_init,
 };
 

hw/display/vga_template.h

@@ -361,7 +361,7 @@ static void glue(vga_draw_line15_, PIXEL_NAME)(VGACommonState *s1, uint8_t *d,
 
     w = width;
     do {
-        v = lduw_raw((void *)s);
+        v = lduw_p((void *)s);
         r = (v >> 7) & 0xf8;
         g = (v >> 2) & 0xf8;
         b = (v << 3) & 0xf8;
@@ -386,7 +386,7 @@ static void glue(vga_draw_line16_, PIXEL_NAME)(VGACommonState *s1, uint8_t *d,
 
     w = width;
     do {
-        v = lduw_raw((void *)s);
+        v = lduw_p((void *)s);
         r = (v >> 8) & 0xf8;
         g = (v >> 3) & 0xfc;
         b = (v << 3) & 0xf8;